From 8735f16803f00f5efca7738afe3b9a304b539181 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 26 Jun 2019 16:31:46 +0200 Subject: dma-buf: cleanup reservation_object_init/fini MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit They are not used that often and certainly not in a hot path. Make them normal functions instead of an inline. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/314480/ --- include/linux/reservation.h | 46 ++------------------------------------------- 1 file changed, 2 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 644a22dbe53b..02866ee54d67 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -81,50 +81,6 @@ struct reservation_object { #define reservation_object_assert_held(obj) \ lockdep_assert_held(&(obj)->lock.base) -/** - * reservation_object_init - initialize a reservation object - * @obj: the reservation object - */ -static inline void -reservation_object_init(struct reservation_object *obj) -{ - ww_mutex_init(&obj->lock, &reservation_ww_class); - - __seqcount_init(&obj->seq, reservation_seqcount_string, &reservation_seqcount_class); - RCU_INIT_POINTER(obj->fence, NULL); - RCU_INIT_POINTER(obj->fence_excl, NULL); -} - -/** - * reservation_object_fini - destroys a reservation object - * @obj: the reservation object - */ -static inline void -reservation_object_fini(struct reservation_object *obj) -{ - int i; - struct reservation_object_list *fobj; - struct dma_fence *excl; - - /* - * This object should be dead and all references must have - * been released to it, so no need to be protected with rcu. - */ - excl = rcu_dereference_protected(obj->fence_excl, 1); - if (excl) - dma_fence_put(excl); - - fobj = rcu_dereference_protected(obj->fence, 1); - if (fobj) { - for (i = 0; i < fobj->shared_count; ++i) - dma_fence_put(rcu_dereference_protected(fobj->shared[i], 1)); - - kfree(fobj); - } - - ww_mutex_destroy(&obj->lock); -} - /** * reservation_object_get_list - get the reservation object's * shared fence list, with update-side lock held @@ -271,6 +227,8 @@ reservation_object_get_excl_rcu(struct reservation_object *obj) return fence; } +void reservation_object_init(struct reservation_object *obj); +void reservation_object_fini(struct reservation_object *obj); int reservation_object_reserve_shared(struct reservation_object *obj, unsigned int num_fences); void reservation_object_add_shared_fence(struct reservation_object *obj, -- cgit v1.2.3-71-gd317 From 163fa23435cc9c705a71001d4aa15f3f945554a1 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 3 Jul 2019 16:25:52 +0800 Subject: percpu: Make pcpu_setup_first_chunk() void function pcpu_setup_first_chunk() will panic or BUG_ON if the are some error and doesn't return any error, hence it can be defined to return void. Reported-by: kbuild test robot Signed-off-by: Kefeng Wang Signed-off-by: Dennis Zhou [Dennis: fixed kbuild warning for pcpu_page_first_chunk()] --- arch/ia64/mm/contig.c | 5 +---- arch/ia64/mm/discontig.c | 5 +---- include/linux/percpu.h | 2 +- mm/percpu.c | 19 +++++++------------ 4 files changed, 10 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index d29fb6b9fa33..db09a693f094 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -134,10 +134,7 @@ setup_per_cpu_areas(void) ai->atom_size = PAGE_SIZE; ai->alloc_size = PERCPU_PAGE_SIZE; - rc = pcpu_setup_first_chunk(ai, __per_cpu_start + __per_cpu_offset[0]); - if (rc) - panic("failed to setup percpu area (err=%d)", rc); - + pcpu_setup_first_chunk(ai, __per_cpu_start + __per_cpu_offset[0]); pcpu_free_alloc_info(ai); } #else diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 05490dd073e6..004dee231874 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -245,10 +245,7 @@ void __init setup_per_cpu_areas(void) gi->cpu_map = &cpu_map[unit]; } - rc = pcpu_setup_first_chunk(ai, base); - if (rc) - panic("failed to setup percpu area (err=%d)", rc); - + pcpu_setup_first_chunk(ai, base); pcpu_free_alloc_info(ai); } #endif diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 9909dc0e273a..5e76af742c80 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -105,7 +105,7 @@ extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units); extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai); -extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, +extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr); #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK diff --git a/mm/percpu.c b/mm/percpu.c index 9821241fdede..5a918a4b1da0 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2267,12 +2267,9 @@ static void pcpu_dump_alloc_info(const char *lvl, * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. - * - * RETURNS: - * 0 on success, -errno on failure. */ -int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, - void *base_addr) +void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, + void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; @@ -2457,7 +2454,6 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, /* we're done */ pcpu_base_addr = base_addr; - return 0; } #ifdef CONFIG_SMP @@ -2710,7 +2706,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; - int group, i, highest_group, rc; + int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); @@ -2795,7 +2791,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); - rc = pcpu_setup_first_chunk(ai, base); + pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: @@ -2839,7 +2835,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, int unit_pages; size_t pages_size; struct page **pages; - int unit, i, j, rc; + int unit, i, j, rc = 0; int upa; int nr_g0_units; @@ -2920,7 +2916,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); - rc = pcpu_setup_first_chunk(ai, vm.addr); + pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: @@ -3014,8 +3010,7 @@ void __init setup_per_cpu_areas(void) ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; - if (pcpu_setup_first_chunk(ai, fc) < 0) - panic("Failed to initialize percpu areas."); + pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } -- cgit v1.2.3-71-gd317 From 66620f48cb59440fd265b77d30b9960e2cf1c345 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Tue, 16 Jul 2019 08:42:02 +0200 Subject: drm/meson: drop use of drmP.h Drop use of the deprecated drmP.h header. While doing so used the opportunity to clean up a little so includes are now sorted and removed unused include files. In a few cases added some forwards to allow header files to built in different include order. Signed-off-by: Sam Ravnborg Acked-by: Emil Velikov Reviewed-by: Alex Deucher Cc: Neil Armstrong Cc: Kevin Hilman Cc: Maxime Jourdan Cc: Jerome Brunet Cc: linux-amlogic@lists.infradead.org Cc: linux-arm-kernel@lists.infradead.org Link: https://patchwork.freedesktop.org/patch/msgid/20190716064220.18157-2-sam@ravnborg.org --- drivers/gpu/drm/meson/meson_crtc.c | 16 +++++++--------- drivers/gpu/drm/meson/meson_drv.c | 27 +++++++++++---------------- drivers/gpu/drm/meson/meson_drv.h | 11 +++++++---- drivers/gpu/drm/meson/meson_dw_hdmi.c | 19 ++++++++++--------- drivers/gpu/drm/meson/meson_overlay.c | 13 +++++-------- drivers/gpu/drm/meson/meson_plane.c | 16 ++++++---------- drivers/gpu/drm/meson/meson_registers.h | 2 ++ drivers/gpu/drm/meson/meson_vclk.c | 7 ++++--- drivers/gpu/drm/meson/meson_vclk.h | 4 ++++ drivers/gpu/drm/meson/meson_venc.c | 10 +++++----- drivers/gpu/drm/meson/meson_venc.h | 2 ++ drivers/gpu/drm/meson/meson_venc_cvbs.c | 11 +++++------ drivers/gpu/drm/meson/meson_viu.c | 7 ++----- drivers/gpu/drm/meson/meson_vpp.c | 7 +++---- drivers/gpu/drm/meson/meson_vpp.h | 3 +++ include/linux/soc/amlogic/meson-canvas.h | 1 + 16 files changed, 77 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c index aa8ea107524e..3320a74e67fa 100644 --- a/drivers/gpu/drm/meson/meson_crtc.c +++ b/drivers/gpu/drm/meson/meson_crtc.c @@ -9,23 +9,21 @@ * Jasper St. Pierre */ -#include -#include -#include -#include #include -#include -#include +#include + #include -#include +#include +#include #include +#include #include "meson_crtc.h" #include "meson_plane.h" +#include "meson_registers.h" #include "meson_venc.h" -#include "meson_vpp.h" #include "meson_viu.h" -#include "meson_registers.h" +#include "meson_vpp.h" #define MESON_G12A_VIU_OFFSET 0x5ec0 diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 37dca83d6eb1..42af49afdd75 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -8,35 +8,30 @@ * Jasper St. Pierre */ -#include -#include -#include -#include #include +#include #include +#include +#include -#include -#include #include -#include +#include #include -#include #include #include -#include +#include +#include #include -#include +#include +#include "meson_crtc.h" #include "meson_drv.h" -#include "meson_plane.h" #include "meson_overlay.h" -#include "meson_crtc.h" +#include "meson_plane.h" +#include "meson_registers.h" #include "meson_venc_cvbs.h" - -#include "meson_vpp.h" #include "meson_viu.h" -#include "meson_venc.h" -#include "meson_registers.h" +#include "meson_vpp.h" #define DRIVER_NAME "meson" #define DRIVER_DESC "Amlogic Meson DRM driver" diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h index 7b6593f33dfe..c9aaec1a846e 100644 --- a/drivers/gpu/drm/meson/meson_drv.h +++ b/drivers/gpu/drm/meson/meson_drv.h @@ -7,11 +7,14 @@ #ifndef __MESON_DRV_H #define __MESON_DRV_H -#include -#include +#include #include -#include -#include +#include + +struct drm_crtc; +struct drm_device; +struct drm_plane; +struct meson_drm; struct meson_drm { struct device *dev; diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index df3f9ddd2234..9f0b08eaf003 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -5,29 +5,30 @@ * Copyright (C) 2015 Amlogic, Inc. All rights reserved. */ +#include +#include #include #include -#include #include #include -#include -#include #include +#include -#include +#include #include +#include #include #include -#include +#include -#include -#include +#include +#include #include "meson_drv.h" -#include "meson_venc.h" -#include "meson_vclk.h" #include "meson_dw_hdmi.h" #include "meson_registers.h" +#include "meson_vclk.h" +#include "meson_venc.h" #define DRIVER_NAME "meson-dw-hdmi" #define DRIVER_DESC "Amlogic Meson HDMI-TX DRM driver" diff --git a/drivers/gpu/drm/meson/meson_overlay.c b/drivers/gpu/drm/meson/meson_overlay.c index cc7c6ae3013d..5aa9dcb4b35e 100644 --- a/drivers/gpu/drm/meson/meson_overlay.c +++ b/drivers/gpu/drm/meson/meson_overlay.c @@ -5,24 +5,21 @@ * Copyright (C) 2015 Amlogic, Inc. All rights reserved. */ -#include -#include -#include #include -#include -#include + #include #include +#include +#include #include #include #include #include -#include #include "meson_overlay.h" -#include "meson_vpp.h" -#include "meson_viu.h" #include "meson_registers.h" +#include "meson_viu.h" +#include "meson_vpp.h" /* VD1_IF0_GEN_REG */ #define VD_URGENT_CHROMA BIT(28) diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index 7a7e88dadd0b..80b8d70c4d75 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -9,24 +9,20 @@ * Jasper St. Pierre */ -#include -#include -#include #include -#include -#include + #include #include -#include -#include +#include #include +#include +#include #include -#include +#include #include "meson_plane.h" -#include "meson_vpp.h" -#include "meson_viu.h" #include "meson_registers.h" +#include "meson_viu.h" /* OSD_SCI_WH_M1 */ #define SCI_WH_M1_W(w) FIELD_PREP(GENMASK(28, 16), w) diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h index 410e324d6f93..057453ce027c 100644 --- a/drivers/gpu/drm/meson/meson_registers.h +++ b/drivers/gpu/drm/meson/meson_registers.h @@ -6,6 +6,8 @@ #ifndef __MESON_REGISTERS_H #define __MESON_REGISTERS_H +#include + /* Shift all registers by 2 */ #define _REG(reg) ((reg) << 2) diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c index 26732f038d19..8abff51f937d 100644 --- a/drivers/gpu/drm/meson/meson_vclk.c +++ b/drivers/gpu/drm/meson/meson_vclk.c @@ -5,9 +5,10 @@ * Copyright (C) 2015 Amlogic, Inc. All rights reserved. */ -#include -#include -#include +#include + +#include + #include "meson_drv.h" #include "meson_vclk.h" diff --git a/drivers/gpu/drm/meson/meson_vclk.h b/drivers/gpu/drm/meson/meson_vclk.h index ed993d20abda..b62125540aef 100644 --- a/drivers/gpu/drm/meson/meson_vclk.h +++ b/drivers/gpu/drm/meson/meson_vclk.h @@ -9,6 +9,10 @@ #ifndef __MESON_VCLK_H #define __MESON_VCLK_H +#include + +struct meson_drm; + enum { MESON_VCLK_TARGET_CVBS = 0, MESON_VCLK_TARGET_HDMI = 1, diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c index 7b7a0d8d737c..3d4791798ae0 100644 --- a/drivers/gpu/drm/meson/meson_venc.c +++ b/drivers/gpu/drm/meson/meson_venc.c @@ -5,14 +5,14 @@ * Copyright (C) 2015 Amlogic, Inc. All rights reserved. */ -#include -#include -#include +#include + +#include + #include "meson_drv.h" +#include "meson_registers.h" #include "meson_venc.h" #include "meson_vpp.h" -#include "meson_vclk.h" -#include "meson_registers.h" /** * DOC: Video Encoder diff --git a/drivers/gpu/drm/meson/meson_venc.h b/drivers/gpu/drm/meson/meson_venc.h index 985642a1678e..576768bdd08d 100644 --- a/drivers/gpu/drm/meson/meson_venc.h +++ b/drivers/gpu/drm/meson/meson_venc.h @@ -14,6 +14,8 @@ #ifndef __MESON_VENC_H #define __MESON_VENC_H +struct drm_display_mode; + enum { MESON_VENC_MODE_NONE = 0, MESON_VENC_MODE_CVBS_PAL, diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c index 6313a519f257..45a467f10b9b 100644 --- a/drivers/gpu/drm/meson/meson_venc_cvbs.c +++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c @@ -9,19 +9,18 @@ * Jasper St. Pierre */ -#include -#include +#include #include -#include #include +#include #include #include +#include -#include "meson_venc_cvbs.h" -#include "meson_venc.h" -#include "meson_vclk.h" #include "meson_registers.h" +#include "meson_vclk.h" +#include "meson_venc_cvbs.h" /* HHI VDAC Registers */ #define HHI_VDAC_CNTL0 0x2F4 /* 0xbd offset in data sheet */ diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index 4b2b3024d371..9f8a450d50d5 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -6,13 +6,10 @@ * Copyright (C) 2014 Endless Mobile */ -#include -#include -#include +#include + #include "meson_drv.h" #include "meson_viu.h" -#include "meson_vpp.h" -#include "meson_venc.h" #include "meson_registers.h" /** diff --git a/drivers/gpu/drm/meson/meson_vpp.c b/drivers/gpu/drm/meson/meson_vpp.c index bfee30fa6e34..cbe6cf46e541 100644 --- a/drivers/gpu/drm/meson/meson_vpp.c +++ b/drivers/gpu/drm/meson/meson_vpp.c @@ -6,12 +6,11 @@ * Copyright (C) 2014 Endless Mobile */ -#include -#include -#include +#include + #include "meson_drv.h" -#include "meson_vpp.h" #include "meson_registers.h" +#include "meson_vpp.h" /** * DOC: Video Post Processing diff --git a/drivers/gpu/drm/meson/meson_vpp.h b/drivers/gpu/drm/meson/meson_vpp.h index 9fc82db8a12d..afc9553ed8d3 100644 --- a/drivers/gpu/drm/meson/meson_vpp.h +++ b/drivers/gpu/drm/meson/meson_vpp.h @@ -9,6 +9,9 @@ #ifndef __MESON_VPP_H #define __MESON_VPP_H +struct drm_rect; +struct meson_drm; + /* Mux VIU/VPP to ENCI */ #define MESON_VIU_VPP_MUX_ENCI 0x5 /* Mux VIU/VPP to ENCP */ diff --git a/include/linux/soc/amlogic/meson-canvas.h b/include/linux/soc/amlogic/meson-canvas.h index b4dde2fbeb3f..0cb2a6050d1f 100644 --- a/include/linux/soc/amlogic/meson-canvas.h +++ b/include/linux/soc/amlogic/meson-canvas.h @@ -20,6 +20,7 @@ #define MESON_CANVAS_ENDIAN_SWAP64 0x7 #define MESON_CANVAS_ENDIAN_SWAP128 0xf +struct device; struct meson_canvas; /** -- cgit v1.2.3-71-gd317 From c9b07eab0c8760bdd4cf8624c482ee145a322a3b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 14 Jul 2019 13:22:27 -0400 Subject: audit_inode(): switch to passing AUDIT_INODE_... don't bother with remapping LOOKUP_... values - all callers pass constants and we can just as well pass the right ones from the very beginning. Signed-off-by: Al Viro --- fs/namei.c | 6 +++--- include/linux/audit.h | 20 +++++++------------- 2 files changed, 10 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 5b8c72dc0217..3fca26398bc2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2391,7 +2391,7 @@ static struct filename *filename_parentat(int dfd, struct filename *name, if (likely(!retval)) { *last = nd.last; *type = nd.last_type; - audit_inode(name, parent->dentry, LOOKUP_PARENT); + audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } else { putname(name); name = ERR_PTR(retval); @@ -2718,7 +2718,7 @@ filename_mountpoint(int dfd, struct filename *name, struct path *path, if (unlikely(error == -ESTALE)) error = path_mountpoint(&nd, flags | LOOKUP_REVAL, path); if (likely(!error)) - audit_inode(name, path->dentry, LOOKUP_NO_EVAL); + audit_inode(name, path->dentry, AUDIT_INODE_NOEVAL); restore_nameidata(); putname(name); return error; @@ -3299,7 +3299,7 @@ static int do_last(struct nameidata *nd, if (error) return error; - audit_inode(nd->name, dir, LOOKUP_PARENT); + audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ if (unlikely(nd->last.name[nd->last.len])) return -EISDIR; diff --git a/include/linux/audit.h b/include/linux/audit.h index 97d0925454df..543763ab0354 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -252,6 +252,10 @@ static inline int audit_signal_info(int sig, struct task_struct *t) #define audit_is_compat(arch) false #endif +#define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ +#define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ +#define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ + #ifdef CONFIG_AUDITSYSCALL #include /* for syscall_get_arch() */ @@ -265,9 +269,6 @@ extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); -#define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ -#define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ -#define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); @@ -328,16 +329,9 @@ static inline void audit_getname(struct filename *name) } static inline void audit_inode(struct filename *name, const struct dentry *dentry, - unsigned int flags) { - if (unlikely(!audit_dummy_context())) { - unsigned int aflags = 0; - - if (flags & LOOKUP_PARENT) - aflags |= AUDIT_INODE_PARENT; - if (flags & LOOKUP_NO_EVAL) - aflags |= AUDIT_INODE_NOEVAL; + unsigned int aflags) { + if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); - } } static inline void audit_file(struct file *file) { @@ -561,7 +555,7 @@ static inline void __audit_inode_child(struct inode *parent, { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, - unsigned int parent) + unsigned int aflags) { } static inline void audit_file(struct file *file) { -- cgit v1.2.3-71-gd317 From 9c71b9eb3cb25856e29f0486eae9ee1ba864ba51 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 10:16:44 +0200 Subject: dmaengine: omap-dma: make omap_dma_filter_fn private With the audio driver no longer referring to this function, it can be made private to the dmaengine driver itself, and the header file removed. Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/lkml/20190307151646.1016966-1-arnd@arndb.de/ Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20190722081705.2084961-1-arnd@arndb.de Signed-off-by: Vinod Koul --- drivers/dma/ti/omap-dma.c | 3 ++- include/linux/omap-dma.h | 2 -- include/linux/omap-dmaengine.h | 18 ------------------ 3 files changed, 2 insertions(+), 21 deletions(-) delete mode 100644 include/linux/omap-dmaengine.h (limited to 'include/linux') diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index ba2489d4ea24..49da402a1927 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -202,6 +202,7 @@ static const unsigned es_bytes[] = { [CSDP_DATA_TYPE_32] = 4, }; +static bool omap_dma_filter_fn(struct dma_chan *chan, void *param); static struct of_dma_filter_info omap_dma_info = { .filter_fn = omap_dma_filter_fn, }; @@ -1637,7 +1638,7 @@ static struct platform_driver omap_dma_driver = { }, }; -bool omap_dma_filter_fn(struct dma_chan *chan, void *param) +static bool omap_dma_filter_fn(struct dma_chan *chan, void *param) { if (chan->device->dev->driver == &omap_dma_driver.driver) { struct omap_dmadev *od = to_omap_dma_dev(chan->device); diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 840ce551e773..ba3cfbb52312 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_OMAP_DMA_H #define __LINUX_OMAP_DMA_H -#include - /* * Legacy OMAP DMA handling defines and functions * diff --git a/include/linux/omap-dmaengine.h b/include/linux/omap-dmaengine.h deleted file mode 100644 index b6e42f933c40..000000000000 --- a/include/linux/omap-dmaengine.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * OMAP DMA Engine support - */ -#ifndef __LINUX_OMAP_DMAENGINE_H -#define __LINUX_OMAP_DMAENGINE_H - -struct dma_chan; - -#if defined(CONFIG_DMA_OMAP) || (defined(CONFIG_DMA_OMAP_MODULE) && defined(MODULE)) -bool omap_dma_filter_fn(struct dma_chan *, void *); -#else -static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d) -{ - return false; -} -#endif -#endif /* __LINUX_OMAP_DMAENGINE_H */ -- cgit v1.2.3-71-gd317 From d2bfe7b5d182dad54aedb9dcdb736e8816ead1c3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Jul 2019 10:16:45 +0200 Subject: dmaengine: edma: make edma_filter_fn private With the audio driver no longer referring to this function, it can be made private to the dmaengine driver itself, and the header file removed. Acked-by: Peter Ujfalusi Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20190722081705.2084961-2-arnd@arndb.de Signed-off-by: Vinod Koul --- drivers/dma/ti/edma.c | 5 +++-- include/linux/edma.h | 29 ----------------------------- 2 files changed, 3 insertions(+), 31 deletions(-) delete mode 100644 include/linux/edma.h (limited to 'include/linux') diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index ceabdea40ae0..f2549ee3fb49 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -15,7 +15,6 @@ #include #include -#include #include #include #include @@ -2185,6 +2184,8 @@ static struct dma_chan *of_edma_xlate(struct of_phandle_args *dma_spec, } #endif +static bool edma_filter_fn(struct dma_chan *chan, void *param); + static int edma_probe(struct platform_device *pdev) { struct edma_soc_info *info = pdev->dev.platform_data; @@ -2524,7 +2525,7 @@ static struct platform_driver edma_tptc_driver = { }, }; -bool edma_filter_fn(struct dma_chan *chan, void *param) +static bool edma_filter_fn(struct dma_chan *chan, void *param) { bool match = false; diff --git a/include/linux/edma.h b/include/linux/edma.h deleted file mode 100644 index a1307e7827e8..000000000000 --- a/include/linux/edma.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * TI EDMA DMA engine driver - * - * Copyright 2012 Texas Instruments - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ -#ifndef __LINUX_EDMA_H -#define __LINUX_EDMA_H - -struct dma_chan; - -#if defined(CONFIG_TI_EDMA) || defined(CONFIG_TI_EDMA_MODULE) -bool edma_filter_fn(struct dma_chan *, void *); -#else -static inline bool edma_filter_fn(struct dma_chan *chan, void *param) -{ - return false; -} -#endif - -#endif -- cgit v1.2.3-71-gd317 From 60c1b220d8bc6baeaf837cd60f94a331b25c26bc Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 27 Jun 2019 12:52:58 -0700 Subject: cpu-topology: Move cpu topology code to common code. Both RISC-V & ARM64 are using cpu-map device tree to describe their cpu topology. It's better to move the relevant code to a common place instead of duplicate code. To: Will Deacon To: Catalin Marinas Signed-off-by: Atish Patra [Tested on QDF2400] Tested-by: Jeffrey Hugo [Tested on Juno and other embedded platforms.] Tested-by: Sudeep Holla Reviewed-by: Sudeep Holla Acked-by: Will Deacon Acked-by: Greg Kroah-Hartman Signed-off-by: Paul Walmsley --- arch/arm64/include/asm/topology.h | 23 --- arch/arm64/kernel/topology.c | 303 +------------------------------------- drivers/base/arch_topology.c | 296 +++++++++++++++++++++++++++++++++++++ include/linux/arch_topology.h | 28 ++++ include/linux/topology.h | 1 + 5 files changed, 329 insertions(+), 322 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 0524f2438649..a4d945db95a2 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -4,29 +4,6 @@ #include -struct cpu_topology { - int thread_id; - int core_id; - int package_id; - int llc_id; - cpumask_t thread_sibling; - cpumask_t core_sibling; - cpumask_t llc_sibling; -}; - -extern struct cpu_topology cpu_topology[NR_CPUS]; - -#define topology_physical_package_id(cpu) (cpu_topology[cpu].package_id) -#define topology_core_id(cpu) (cpu_topology[cpu].core_id) -#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) -#define topology_llc_cpumask(cpu) (&cpu_topology[cpu].llc_sibling) - -void init_cpu_topology(void); -void store_cpu_topology(unsigned int cpuid); -void remove_cpu_topology(unsigned int cpuid); -const struct cpumask *cpu_coregroup_mask(int cpu); - #ifdef CONFIG_NUMA struct pci_bus; diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 0825c4a856e3..6b95c91e7d67 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -14,250 +14,13 @@ #include #include #include -#include -#include #include #include -#include -#include -#include -#include -#include -#include -#include -#include #include #include #include -static int __init get_cpu_for_node(struct device_node *node) -{ - struct device_node *cpu_node; - int cpu; - - cpu_node = of_parse_phandle(node, "cpu", 0); - if (!cpu_node) - return -1; - - cpu = of_cpu_node_to_id(cpu_node); - if (cpu >= 0) - topology_parse_cpu_capacity(cpu_node, cpu); - else - pr_crit("Unable to find CPU node for %pOF\n", cpu_node); - - of_node_put(cpu_node); - return cpu; -} - -static int __init parse_core(struct device_node *core, int package_id, - int core_id) -{ - char name[10]; - bool leaf = true; - int i = 0; - int cpu; - struct device_node *t; - - do { - snprintf(name, sizeof(name), "thread%d", i); - t = of_get_child_by_name(core, name); - if (t) { - leaf = false; - cpu = get_cpu_for_node(t); - if (cpu >= 0) { - cpu_topology[cpu].package_id = package_id; - cpu_topology[cpu].core_id = core_id; - cpu_topology[cpu].thread_id = i; - } else { - pr_err("%pOF: Can't get CPU for thread\n", - t); - of_node_put(t); - return -EINVAL; - } - of_node_put(t); - } - i++; - } while (t); - - cpu = get_cpu_for_node(core); - if (cpu >= 0) { - if (!leaf) { - pr_err("%pOF: Core has both threads and CPU\n", - core); - return -EINVAL; - } - - cpu_topology[cpu].package_id = package_id; - cpu_topology[cpu].core_id = core_id; - } else if (leaf) { - pr_err("%pOF: Can't get CPU for leaf core\n", core); - return -EINVAL; - } - - return 0; -} - -static int __init parse_cluster(struct device_node *cluster, int depth) -{ - char name[10]; - bool leaf = true; - bool has_cores = false; - struct device_node *c; - static int package_id __initdata; - int core_id = 0; - int i, ret; - - /* - * First check for child clusters; we currently ignore any - * information about the nesting of clusters and present the - * scheduler with a flat list of them. - */ - i = 0; - do { - snprintf(name, sizeof(name), "cluster%d", i); - c = of_get_child_by_name(cluster, name); - if (c) { - leaf = false; - ret = parse_cluster(c, depth + 1); - of_node_put(c); - if (ret != 0) - return ret; - } - i++; - } while (c); - - /* Now check for cores */ - i = 0; - do { - snprintf(name, sizeof(name), "core%d", i); - c = of_get_child_by_name(cluster, name); - if (c) { - has_cores = true; - - if (depth == 0) { - pr_err("%pOF: cpu-map children should be clusters\n", - c); - of_node_put(c); - return -EINVAL; - } - - if (leaf) { - ret = parse_core(c, package_id, core_id++); - } else { - pr_err("%pOF: Non-leaf cluster with core %s\n", - cluster, name); - ret = -EINVAL; - } - - of_node_put(c); - if (ret != 0) - return ret; - } - i++; - } while (c); - - if (leaf && !has_cores) - pr_warn("%pOF: empty cluster\n", cluster); - - if (leaf) - package_id++; - - return 0; -} - -static int __init parse_dt_topology(void) -{ - struct device_node *cn, *map; - int ret = 0; - int cpu; - - cn = of_find_node_by_path("/cpus"); - if (!cn) { - pr_err("No CPU information found in DT\n"); - return 0; - } - - /* - * When topology is provided cpu-map is essentially a root - * cluster with restricted subnodes. - */ - map = of_get_child_by_name(cn, "cpu-map"); - if (!map) - goto out; - - ret = parse_cluster(map, 0); - if (ret != 0) - goto out_map; - - topology_normalize_cpu_scale(); - - /* - * Check that all cores are in the topology; the SMP code will - * only mark cores described in the DT as possible. - */ - for_each_possible_cpu(cpu) - if (cpu_topology[cpu].package_id == -1) - ret = -EINVAL; - -out_map: - of_node_put(map); -out: - of_node_put(cn); - return ret; -} - -/* - * cpu topology table - */ -struct cpu_topology cpu_topology[NR_CPUS]; -EXPORT_SYMBOL_GPL(cpu_topology); - -const struct cpumask *cpu_coregroup_mask(int cpu) -{ - const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); - - /* Find the smaller of NUMA, core or LLC siblings */ - if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { - /* not numa in package, lets use the package siblings */ - core_mask = &cpu_topology[cpu].core_sibling; - } - if (cpu_topology[cpu].llc_id != -1) { - if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask)) - core_mask = &cpu_topology[cpu].llc_sibling; - } - - return core_mask; -} - -static void update_siblings_masks(unsigned int cpuid) -{ - struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; - int cpu; - - /* update core and thread sibling masks */ - for_each_online_cpu(cpu) { - cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->llc_id == cpu_topo->llc_id) { - cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); - cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); - } - - if (cpuid_topo->package_id != cpu_topo->package_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); - - if (cpuid_topo->core_id != cpu_topo->core_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); - cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); - } -} - void store_cpu_topology(unsigned int cpuid) { struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; @@ -296,59 +59,19 @@ topology_populated: update_siblings_masks(cpuid); } -static void clear_cpu_topology(int cpu) -{ - struct cpu_topology *cpu_topo = &cpu_topology[cpu]; - - cpumask_clear(&cpu_topo->llc_sibling); - cpumask_set_cpu(cpu, &cpu_topo->llc_sibling); - - cpumask_clear(&cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpu_topo->core_sibling); - cpumask_clear(&cpu_topo->thread_sibling); - cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); -} - -static void __init reset_cpu_topology(void) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) { - struct cpu_topology *cpu_topo = &cpu_topology[cpu]; - - cpu_topo->thread_id = -1; - cpu_topo->core_id = 0; - cpu_topo->package_id = -1; - cpu_topo->llc_id = -1; - - clear_cpu_topology(cpu); - } -} - -void remove_cpu_topology(unsigned int cpu) -{ - int sibling; - - for_each_cpu(sibling, topology_core_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); - for_each_cpu(sibling, topology_sibling_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); - for_each_cpu(sibling, topology_llc_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling)); - - clear_cpu_topology(cpu); -} - #ifdef CONFIG_ACPI /* * Propagate the topology information of the processor_topology_node tree to the * cpu_topology array. */ -static int __init parse_acpi_topology(void) +int __init parse_acpi_topology(void) { bool is_threaded; int cpu, topology_id; + if (acpi_disabled) + return 0; + is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK; for_each_possible_cpu(cpu) { @@ -384,24 +107,6 @@ static int __init parse_acpi_topology(void) return 0; } - -#else -static inline int __init parse_acpi_topology(void) -{ - return -EINVAL; -} #endif -void __init init_cpu_topology(void) -{ - reset_cpu_topology(); - /* - * Discard anything that was parsed if we hit an error so we - * don't use partial information. - */ - if (!acpi_disabled && parse_acpi_topology()) - reset_cpu_topology(); - else if (of_have_populated_dt() && parse_dt_topology()) - reset_cpu_topology(); -} diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 63c1e76739f1..5dc0e1ddd080 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -15,6 +15,11 @@ #include #include #include +#include +#include +#include +#include +#include DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE; @@ -241,3 +246,294 @@ static void parsing_done_workfn(struct work_struct *work) #else core_initcall(free_raw_capacity); #endif + +#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV) +static int __init get_cpu_for_node(struct device_node *node) +{ + struct device_node *cpu_node; + int cpu; + + cpu_node = of_parse_phandle(node, "cpu", 0); + if (!cpu_node) + return -1; + + cpu = of_cpu_node_to_id(cpu_node); + if (cpu >= 0) + topology_parse_cpu_capacity(cpu_node, cpu); + else + pr_crit("Unable to find CPU node for %pOF\n", cpu_node); + + of_node_put(cpu_node); + return cpu; +} + +static int __init parse_core(struct device_node *core, int package_id, + int core_id) +{ + char name[10]; + bool leaf = true; + int i = 0; + int cpu; + struct device_node *t; + + do { + snprintf(name, sizeof(name), "thread%d", i); + t = of_get_child_by_name(core, name); + if (t) { + leaf = false; + cpu = get_cpu_for_node(t); + if (cpu >= 0) { + cpu_topology[cpu].package_id = package_id; + cpu_topology[cpu].core_id = core_id; + cpu_topology[cpu].thread_id = i; + } else { + pr_err("%pOF: Can't get CPU for thread\n", + t); + of_node_put(t); + return -EINVAL; + } + of_node_put(t); + } + i++; + } while (t); + + cpu = get_cpu_for_node(core); + if (cpu >= 0) { + if (!leaf) { + pr_err("%pOF: Core has both threads and CPU\n", + core); + return -EINVAL; + } + + cpu_topology[cpu].package_id = package_id; + cpu_topology[cpu].core_id = core_id; + } else if (leaf) { + pr_err("%pOF: Can't get CPU for leaf core\n", core); + return -EINVAL; + } + + return 0; +} + +static int __init parse_cluster(struct device_node *cluster, int depth) +{ + char name[10]; + bool leaf = true; + bool has_cores = false; + struct device_node *c; + static int package_id __initdata; + int core_id = 0; + int i, ret; + + /* + * First check for child clusters; we currently ignore any + * information about the nesting of clusters and present the + * scheduler with a flat list of them. + */ + i = 0; + do { + snprintf(name, sizeof(name), "cluster%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + leaf = false; + ret = parse_cluster(c, depth + 1); + of_node_put(c); + if (ret != 0) + return ret; + } + i++; + } while (c); + + /* Now check for cores */ + i = 0; + do { + snprintf(name, sizeof(name), "core%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + has_cores = true; + + if (depth == 0) { + pr_err("%pOF: cpu-map children should be clusters\n", + c); + of_node_put(c); + return -EINVAL; + } + + if (leaf) { + ret = parse_core(c, package_id, core_id++); + } else { + pr_err("%pOF: Non-leaf cluster with core %s\n", + cluster, name); + ret = -EINVAL; + } + + of_node_put(c); + if (ret != 0) + return ret; + } + i++; + } while (c); + + if (leaf && !has_cores) + pr_warn("%pOF: empty cluster\n", cluster); + + if (leaf) + package_id++; + + return 0; +} + +static int __init parse_dt_topology(void) +{ + struct device_node *cn, *map; + int ret = 0; + int cpu; + + cn = of_find_node_by_path("/cpus"); + if (!cn) { + pr_err("No CPU information found in DT\n"); + return 0; + } + + /* + * When topology is provided cpu-map is essentially a root + * cluster with restricted subnodes. + */ + map = of_get_child_by_name(cn, "cpu-map"); + if (!map) + goto out; + + ret = parse_cluster(map, 0); + if (ret != 0) + goto out_map; + + topology_normalize_cpu_scale(); + + /* + * Check that all cores are in the topology; the SMP code will + * only mark cores described in the DT as possible. + */ + for_each_possible_cpu(cpu) + if (cpu_topology[cpu].package_id == -1) + ret = -EINVAL; + +out_map: + of_node_put(map); +out: + of_node_put(cn); + return ret; +} + +/* + * cpu topology table + */ +struct cpu_topology cpu_topology[NR_CPUS]; +EXPORT_SYMBOL_GPL(cpu_topology); + +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); + + /* Find the smaller of NUMA, core or LLC siblings */ + if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { + /* not numa in package, lets use the package siblings */ + core_mask = &cpu_topology[cpu].core_sibling; + } + if (cpu_topology[cpu].llc_id != -1) { + if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask)) + core_mask = &cpu_topology[cpu].llc_sibling; + } + + return core_mask; +} + +void update_siblings_masks(unsigned int cpuid) +{ + struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int cpu; + + /* update core and thread sibling masks */ + for_each_online_cpu(cpu) { + cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->llc_id == cpu_topo->llc_id) { + cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); + cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); + } + + if (cpuid_topo->package_id != cpu_topo->package_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id != cpu_topo->core_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); + cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); + } +} + +static void clear_cpu_topology(int cpu) +{ + struct cpu_topology *cpu_topo = &cpu_topology[cpu]; + + cpumask_clear(&cpu_topo->llc_sibling); + cpumask_set_cpu(cpu, &cpu_topo->llc_sibling); + + cpumask_clear(&cpu_topo->core_sibling); + cpumask_set_cpu(cpu, &cpu_topo->core_sibling); + cpumask_clear(&cpu_topo->thread_sibling); + cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); +} + +static void __init reset_cpu_topology(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) { + struct cpu_topology *cpu_topo = &cpu_topology[cpu]; + + cpu_topo->thread_id = -1; + cpu_topo->core_id = -1; + cpu_topo->package_id = -1; + cpu_topo->llc_id = -1; + + clear_cpu_topology(cpu); + } +} + +void remove_cpu_topology(unsigned int cpu) +{ + int sibling; + + for_each_cpu(sibling, topology_core_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); + for_each_cpu(sibling, topology_llc_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling)); + + clear_cpu_topology(cpu); +} + +__weak int __init parse_acpi_topology(void) +{ + return 0; +} + +void __init init_cpu_topology(void) +{ + reset_cpu_topology(); + + /* + * Discard anything that was parsed if we hit an error so we + * don't use partial information. + */ + if (parse_acpi_topology()) + reset_cpu_topology(); + else if (of_have_populated_dt() && parse_dt_topology()) + reset_cpu_topology(); +} +#endif diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 1cfe05ea1d89..ede0ce4623b4 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -33,4 +33,32 @@ unsigned long topology_get_freq_scale(int cpu) return per_cpu(freq_scale, cpu); } +struct cpu_topology { + int thread_id; + int core_id; + int package_id; + int llc_id; + cpumask_t thread_sibling; + cpumask_t core_sibling; + cpumask_t llc_sibling; +}; + +#ifdef CONFIG_GENERIC_ARCH_TOPOLOGY +extern struct cpu_topology cpu_topology[NR_CPUS]; + +#define topology_physical_package_id(cpu) (cpu_topology[cpu].package_id) +#define topology_core_id(cpu) (cpu_topology[cpu].core_id) +#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) +#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_llc_cpumask(cpu) (&cpu_topology[cpu].llc_sibling) +void init_cpu_topology(void); +void store_cpu_topology(unsigned int cpuid); +const struct cpumask *cpu_coregroup_mask(int cpu); +#endif + +#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV) +void update_siblings_masks(unsigned int cpu); +#endif +void remove_cpu_topology(unsigned int cpuid); + #endif /* _LINUX_ARCH_TOPOLOGY_H_ */ diff --git a/include/linux/topology.h b/include/linux/topology.h index 47a3e3c08036..2a19d196af28 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -27,6 +27,7 @@ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H +#include #include #include #include -- cgit v1.2.3-71-gd317 From ca74b316df96d7c40ee3e8301065607c11c60c27 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 27 Jun 2019 12:52:59 -0700 Subject: arm: Use common cpu_topology structure and functions. Currently, ARM32 and ARM64 uses different data structures to represent their cpu topologies. Since, we are moving the ARM64 topology to common code to be used by other architectures, we can reuse that for ARM32 as well. Take this opprtunity to remove the redundant functions from ARM32 and reuse the common code instead. To: Russell King Signed-off-by: Atish Patra Tested-by: Sudeep Holla (on TC2) Reviewed-by: Sudeep Holla Signed-off-by: Paul Walmsley --- arch/arm/include/asm/topology.h | 20 -------------- arch/arm/kernel/topology.c | 60 +++++------------------------------------ drivers/base/arch_topology.c | 4 ++- include/linux/arch_topology.h | 6 ++--- 4 files changed, 11 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 2a786f54d8b8..8a0fae94d45e 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -5,26 +5,6 @@ #ifdef CONFIG_ARM_CPU_TOPOLOGY #include - -struct cputopo_arm { - int thread_id; - int core_id; - int socket_id; - cpumask_t thread_sibling; - cpumask_t core_sibling; -}; - -extern struct cputopo_arm cpu_topology[NR_CPUS]; - -#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) -#define topology_core_id(cpu) (cpu_topology[cpu].core_id) -#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) - -void init_cpu_topology(void); -void store_cpu_topology(unsigned int cpuid); -const struct cpumask *cpu_coregroup_mask(int cpu); - #include /* Replace task scheduler's default frequency-invariant accounting */ diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index d17cb1e6d679..5b9faba03afb 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -177,17 +177,6 @@ static inline void parse_dt_topology(void) {} static inline void update_cpu_capacity(unsigned int cpuid) {} #endif - /* - * cpu topology table - */ -struct cputopo_arm cpu_topology[NR_CPUS]; -EXPORT_SYMBOL_GPL(cpu_topology); - -const struct cpumask *cpu_coregroup_mask(int cpu) -{ - return &cpu_topology[cpu].core_sibling; -} - /* * The current assumption is that we can power gate each core independently. * This will be superseded by DT binding once available. @@ -197,32 +186,6 @@ const struct cpumask *cpu_corepower_mask(int cpu) return &cpu_topology[cpu].thread_sibling; } -static void update_siblings_masks(unsigned int cpuid) -{ - struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; - int cpu; - - /* update core and thread sibling masks */ - for_each_possible_cpu(cpu) { - cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->socket_id != cpu_topo->socket_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); - - if (cpuid_topo->core_id != cpu_topo->core_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); - } - smp_wmb(); -} - /* * store_cpu_topology is called at boot when only one cpu is running * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, @@ -230,7 +193,7 @@ static void update_siblings_masks(unsigned int cpuid) */ void store_cpu_topology(unsigned int cpuid) { - struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; unsigned int mpidr; /* If the cpu topology has been already set, just return */ @@ -250,12 +213,12 @@ void store_cpu_topology(unsigned int cpuid) /* core performance interdependency */ cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); - cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 2); + cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2); } else { /* largely independent cores */ cpuid_topo->thread_id = -1; cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); - cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); + cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); } } else { /* @@ -265,7 +228,7 @@ void store_cpu_topology(unsigned int cpuid) */ cpuid_topo->thread_id = -1; cpuid_topo->core_id = 0; - cpuid_topo->socket_id = -1; + cpuid_topo->package_id = -1; } update_siblings_masks(cpuid); @@ -275,7 +238,7 @@ void store_cpu_topology(unsigned int cpuid) pr_info("CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, cpu_topology[cpuid].core_id, - cpu_topology[cpuid].socket_id, mpidr); + cpu_topology[cpuid].package_id, mpidr); } static inline int cpu_corepower_flags(void) @@ -298,18 +261,7 @@ static struct sched_domain_topology_level arm_topology[] = { */ void __init init_cpu_topology(void) { - unsigned int cpu; - - /* init core mask and capacity */ - for_each_possible_cpu(cpu) { - struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); - - cpu_topo->thread_id = -1; - cpu_topo->core_id = -1; - cpu_topo->socket_id = -1; - cpumask_clear(&cpu_topo->core_sibling); - cpumask_clear(&cpu_topo->thread_sibling); - } + reset_cpu_topology(); smp_wmb(); parse_dt_topology(); diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 5dc0e1ddd080..b54d241a2ff5 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -423,6 +423,7 @@ out: of_node_put(cn); return ret; } +#endif /* * cpu topology table @@ -488,7 +489,7 @@ static void clear_cpu_topology(int cpu) cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); } -static void __init reset_cpu_topology(void) +void __init reset_cpu_topology(void) { unsigned int cpu; @@ -523,6 +524,7 @@ __weak int __init parse_acpi_topology(void) return 0; } +#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV) void __init init_cpu_topology(void) { reset_cpu_topology(); diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index ede0ce4623b4..42f2b5126094 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -54,11 +54,9 @@ extern struct cpu_topology cpu_topology[NR_CPUS]; void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); -#endif - -#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV) void update_siblings_masks(unsigned int cpu); -#endif void remove_cpu_topology(unsigned int cpuid); +void reset_cpu_topology(void); +#endif #endif /* _LINUX_ARCH_TOPOLOGY_H_ */ -- cgit v1.2.3-71-gd317 From af311ff9a69189a03548efd5a47d4bb44644fd45 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 17 May 2019 14:09:22 -0700 Subject: firmware: qcom_scm: Cleanup code in qcom_scm_assign_mem() There are some questionable coding styles in this function. It looks quite odd to deref a pointer with array indexing that only uses the first element. Also, destroying an input/output variable halfway through the function and then overwriting it on success is not clear. It's better to use a local variable and the kernel macros to step through each bit set in a bitmask and clearly show where outputs are set. Cc: Ian Jackson Cc: Julien Grall Cc: Bjorn Andersson Cc: Avaneesh Kumar Dwivedi Tested-by: Bjorn Andersson Signed-off-by: Stephen Boyd [bjorn: Changed for_each_set_bit() size to BITS_PER_LONG] Signed-off-by: Bjorn Andersson --- drivers/firmware/qcom_scm.c | 34 ++++++++++++++++------------------ include/linux/qcom_scm.h | 9 +++++---- 2 files changed, 21 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index c7e63af91567..4802ab170fe5 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -434,7 +434,8 @@ EXPORT_SYMBOL(qcom_scm_set_remote_state); */ int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, unsigned int *srcvm, - struct qcom_scm_vmperm *newvm, int dest_cnt) + const struct qcom_scm_vmperm *newvm, + unsigned int dest_cnt) { struct qcom_scm_current_perm_info *destvm; struct qcom_scm_mem_map_info *mem_to_map; @@ -449,11 +450,10 @@ int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, int next_vm; __le32 *src; void *ptr; - int ret; - int len; - int i; + int ret, i, b; + unsigned long srcvm_bits = *srcvm; - src_sz = hweight_long(*srcvm) * sizeof(*src); + src_sz = hweight_long(srcvm_bits) * sizeof(*src); mem_to_map_sz = sizeof(*mem_to_map); dest_sz = dest_cnt * sizeof(*destvm); ptr_sz = ALIGN(src_sz, SZ_64) + ALIGN(mem_to_map_sz, SZ_64) + @@ -466,28 +466,26 @@ int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, /* Fill source vmid detail */ src = ptr; - len = hweight_long(*srcvm); - for (i = 0; i < len; i++) { - src[i] = cpu_to_le32(ffs(*srcvm) - 1); - *srcvm ^= 1 << (ffs(*srcvm) - 1); - } + i = 0; + for_each_set_bit(b, &srcvm_bits, BITS_PER_LONG) + src[i++] = cpu_to_le32(b); /* Fill details of mem buff to map */ mem_to_map = ptr + ALIGN(src_sz, SZ_64); mem_to_map_phys = ptr_phys + ALIGN(src_sz, SZ_64); - mem_to_map[0].mem_addr = cpu_to_le64(mem_addr); - mem_to_map[0].mem_size = cpu_to_le64(mem_sz); + mem_to_map->mem_addr = cpu_to_le64(mem_addr); + mem_to_map->mem_size = cpu_to_le64(mem_sz); next_vm = 0; /* Fill details of next vmid detail */ destvm = ptr + ALIGN(mem_to_map_sz, SZ_64) + ALIGN(src_sz, SZ_64); dest_phys = ptr_phys + ALIGN(mem_to_map_sz, SZ_64) + ALIGN(src_sz, SZ_64); - for (i = 0; i < dest_cnt; i++) { - destvm[i].vmid = cpu_to_le32(newvm[i].vmid); - destvm[i].perm = cpu_to_le32(newvm[i].perm); - destvm[i].ctx = 0; - destvm[i].ctx_size = 0; - next_vm |= BIT(newvm[i].vmid); + for (i = 0; i < dest_cnt; i++, destvm++, newvm++) { + destvm->vmid = cpu_to_le32(newvm->vmid); + destvm->perm = cpu_to_le32(newvm->perm); + destvm->ctx = 0; + destvm->ctx_size = 0; + next_vm |= BIT(newvm->vmid); } ret = __qcom_scm_assign_mem(__scm->dev, mem_to_map_phys, mem_to_map_sz, diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 3f12cc77fb58..2d5eff506e13 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -49,8 +49,9 @@ extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, extern int qcom_scm_pas_auth_and_reset(u32 peripheral); extern int qcom_scm_pas_shutdown(u32 peripheral); extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, - unsigned int *src, struct qcom_scm_vmperm *newvm, - int dest_cnt); + unsigned int *src, + const struct qcom_scm_vmperm *newvm, + unsigned int dest_cnt); extern void qcom_scm_cpu_power_down(u32 flags); extern u32 qcom_scm_get_version(void); extern int qcom_scm_set_remote_state(u32 state, u32 id); @@ -87,8 +88,8 @@ qcom_scm_pas_auth_and_reset(u32 peripheral) { return -ENODEV; } static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; } static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, unsigned int *src, - struct qcom_scm_vmperm *newvm, - int dest_cnt) { return -ENODEV; } + const struct qcom_scm_vmperm *newvm, + unsigned int dest_cnt) { return -ENODEV; } static inline void qcom_scm_cpu_power_down(u32 flags) {} static inline u32 qcom_scm_get_version(void) { return 0; } static inline u32 -- cgit v1.2.3-71-gd317 From d8e18a516f8f67404c0d21af8c93d0474fba0876 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:26 -0700 Subject: net: Use skb accessors in network core In preparation for unifying the skb_frag and bio_vec, use the fine accessors which already exist and use skb_frag_t instead of struct skb_frag_struct. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/core/skbuff.c | 24 ++++++++++++++---------- net/core/tso.c | 8 ++++---- net/ipv4/tcp.c | 14 ++++++++------ net/kcm/kcmsock.c | 8 ++++---- net/tls/tls_device.c | 14 +++++++------- 6 files changed, 38 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d8af86d995d6..f9078e7edb53 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3166,7 +3166,7 @@ static inline bool skb_can_coalesce(struct sk_buff *skb, int i, if (skb_zcopy(skb)) return false; if (i) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && off == frag->page_offset + skb_frag_size(frag); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0338820ee0ec..ba9a36903503 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2485,19 +2485,19 @@ do_frag_list: for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; - if (offset < frag->size) + if (offset < skb_frag_size(frag)) break; - offset -= frag->size; + offset -= skb_frag_size(frag); } for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; - slen = min_t(size_t, len, frag->size - offset); + slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { - ret = kernel_sendpage_locked(sk, frag->page.p, + ret = kernel_sendpage_locked(sk, skb_frag_page(frag), frag->page_offset + offset, slen, MSG_DONTWAIT); if (ret <= 0) @@ -2975,11 +2975,15 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { + int size; + if (!len) break; skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; - skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); - len -= skb_shinfo(to)->frags[j].size; + size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]), + len); + skb_frag_size_set(&skb_shinfo(to)->frags[j], size); + len -= size; skb_frag_ref(to, j); j++; } @@ -3293,7 +3297,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { int from, to, merge, todo; - struct skb_frag_struct *fragfrom, *fragto; + skb_frag_t *fragfrom, *fragto; BUG_ON(shiftlen > skb->len); @@ -3625,10 +3629,10 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) struct page *page; page = virt_to_head_page(frag_skb->head); - head_frag.page.p = page; + __skb_frag_set_page(&head_frag, page); head_frag.page_offset = frag_skb->data - (unsigned char *)page_address(page); - head_frag.size = skb_headlen(frag_skb); + skb_frag_size_set(&head_frag, skb_headlen(frag_skb)); return head_frag; } @@ -4021,7 +4025,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; - frag->page.p = page; + __skb_frag_set_page(frag, page); frag->page_offset = first_offset; skb_frag_size_set(frag, first_size); diff --git a/net/core/tso.c b/net/core/tso.c index 43f4eba61933..d4d5c077ad72 100644 --- a/net/core/tso.c +++ b/net/core/tso.c @@ -55,8 +55,8 @@ void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size) skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; /* Move to next segment */ - tso->size = frag->size; - tso->data = page_address(frag->page.p) + frag->page_offset; + tso->size = skb_frag_size(frag); + tso->data = skb_frag_address(frag); tso->next_frag_idx++; } } @@ -79,8 +79,8 @@ void tso_start(struct sk_buff *skb, struct tso_t *tso) skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; /* Move to next segment */ - tso->size = frag->size; - tso->data = page_address(frag->page.p) + frag->page_offset; + tso->size = skb_frag_size(frag); + tso->data = skb_frag_address(frag); tso->next_frag_idx++; } } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 776905899ac0..f62f0e7e3cdd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1776,19 +1776,21 @@ static int tcp_zerocopy_receive(struct sock *sk, break; frags = skb_shinfo(skb)->frags; while (offset) { - if (frags->size > offset) + if (skb_frag_size(frags) > offset) goto out; - offset -= frags->size; + offset -= skb_frag_size(frags); frags++; } } - if (frags->size != PAGE_SIZE || frags->page_offset) { + if (skb_frag_size(frags) != PAGE_SIZE || frags->page_offset) { int remaining = zc->recv_skip_hint; + int size = skb_frag_size(frags); - while (remaining && (frags->size != PAGE_SIZE || + while (remaining && (size != PAGE_SIZE || frags->page_offset)) { - remaining -= frags->size; + remaining -= size; frags++; + size = skb_frag_size(frags); } zc->recv_skip_hint -= remaining; break; @@ -3781,7 +3783,7 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, return 1; for (i = 0; i < shi->nr_frags; ++i) { - const struct skb_frag_struct *f = &shi->frags[i]; + const skb_frag_t *f = &shi->frags[i]; unsigned int offset = f->page_offset; struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 5dbc0c48f8cb..05f63c4300e9 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -635,15 +635,15 @@ do_frag_list: frag_offset = 0; do_frag: frag = &skb_shinfo(skb)->frags[fragidx]; - if (WARN_ON(!frag->size)) { + if (WARN_ON(!skb_frag_size(frag))) { ret = -EINVAL; goto out; } ret = kernel_sendpage(psock->sk->sk_socket, - frag->page.p, + skb_frag_page(frag), frag->page_offset + frag_offset, - frag->size - frag_offset, + skb_frag_size(frag) - frag_offset, MSG_DONTWAIT); if (ret <= 0) { if (ret == -EAGAIN) { @@ -678,7 +678,7 @@ do_frag: sent += ret; frag_offset += ret; KCM_STATS_ADD(psock->stats.tx_bytes, ret); - if (frag_offset < frag->size) { + if (frag_offset < skb_frag_size(frag)) { /* Not finished with this frag */ goto do_frag; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 7c0b2b778703..4ec8a06fa5d1 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -243,14 +243,14 @@ static void tls_append_frag(struct tls_record_info *record, skb_frag_t *frag; frag = &record->frags[record->num_frags - 1]; - if (frag->page.p == pfrag->page && - frag->page_offset + frag->size == pfrag->offset) { - frag->size += size; + if (skb_frag_page(frag) == pfrag->page && + frag->page_offset + skb_frag_size(frag) == pfrag->offset) { + skb_frag_size_add(frag, size); } else { ++frag; - frag->page.p = pfrag->page; + __skb_frag_set_page(frag, pfrag->page); frag->page_offset = pfrag->offset; - frag->size = size; + skb_frag_size_set(frag, size); ++record->num_frags; get_page(pfrag->page); } @@ -301,8 +301,8 @@ static int tls_push_record(struct sock *sk, frag = &record->frags[i]; sg_unmark_end(&offload_ctx->sg_tx_data[i]); sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), - frag->size, frag->page_offset); - sk_mem_charge(sk, frag->size); + skb_frag_size(frag), frag->page_offset); + sk_mem_charge(sk, skb_frag_size(frag)); get_page(skb_frag_page(frag)); } sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]); -- cgit v1.2.3-71-gd317 From b656722906efe434f0befe1d4ae4bb7a66fdc124 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:27 -0700 Subject: net: Increase the size of skb_frag_t To increase commonality between block and net, we are going to replace the skb_frag_t with the bio_vec. This patch increases the size of skb_frag_t on 32-bit machines from 8 bytes to 12 bytes. The size is unchanged on 64-bit machines. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f9078e7edb53..7910935410e6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,13 +314,8 @@ struct skb_frag_struct { struct { struct page *p; } page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) __u32 page_offset; __u32 size; -#else - __u16 page_offset; - __u16 size; -#endif }; /** -- cgit v1.2.3-71-gd317 From f58ecf1b7d58911921014ffd12c77a4ad33ade71 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:28 -0700 Subject: net: Reorder the contents of skb_frag_t Match the layout of bio_vec. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7910935410e6..b9dc8b4f24b1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,8 +314,8 @@ struct skb_frag_struct { struct { struct page *p; } page; - __u32 page_offset; __u32 size; + __u32 page_offset; }; /** -- cgit v1.2.3-71-gd317 From 1dfa5bd38545c6f6a8b6c496e58db93f80da1076 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:29 -0700 Subject: net: Rename skb_frag page to bv_page One step closer to turning the skb_frag_t into a bio_vec. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 +++++------- net/core/skbuff.c | 2 +- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b9dc8b4f24b1..8076e2ba8349 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -311,9 +311,7 @@ extern int sysctl_max_skb_frags; typedef struct skb_frag_struct skb_frag_t; struct skb_frag_struct { - struct { - struct page *p; - } page; + struct page *bv_page; __u32 size; __u32 page_offset; }; @@ -374,7 +372,7 @@ static inline bool skb_frag_must_loop(struct page *p) * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on - * @f_off: offset from start of f->page.p + * @f_off: offset from start of f->bv_page * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, @@ -2084,7 +2082,7 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ - frag->page.p = page; + frag->bv_page = page; frag->page_offset = off; skb_frag_size_set(frag, size); @@ -2872,7 +2870,7 @@ static inline void skb_propagate_pfmemalloc(struct page *page, */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { - return frag->page.p; + return frag->bv_page; } /** @@ -2958,7 +2956,7 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) */ static inline void __skb_frag_set_page(skb_frag_t *frag, struct page *page) { - frag->page.p = page; + frag->bv_page = page; } /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ba9a36903503..0b788df5a75b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3364,7 +3364,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) } else { __skb_frag_ref(fragfrom); - fragto->page = fragfrom->page; + fragto->bv_page = fragfrom->bv_page; fragto->page_offset = fragfrom->page_offset; skb_frag_size_set(fragto, todo); -- cgit v1.2.3-71-gd317 From b8b576a16f79efbdde49348147f491b176537d88 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:30 -0700 Subject: net: Rename skb_frag_t size to bv_len Improved compatibility with bvec Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8076e2ba8349..e849e411d1f3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -312,7 +312,7 @@ typedef struct skb_frag_struct skb_frag_t; struct skb_frag_struct { struct page *bv_page; - __u32 size; + unsigned int bv_len; __u32 page_offset; }; @@ -322,7 +322,7 @@ struct skb_frag_struct { */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { - return frag->size; + return frag->bv_len; } /** @@ -332,7 +332,7 @@ static inline unsigned int skb_frag_size(const skb_frag_t *frag) */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { - frag->size = size; + frag->bv_len = size; } /** @@ -342,7 +342,7 @@ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { - frag->size += delta; + frag->bv_len += delta; } /** @@ -352,7 +352,7 @@ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { - frag->size -= delta; + frag->bv_len -= delta; } /** -- cgit v1.2.3-71-gd317 From 8842d285bafa9ff7719f4107b6545a11dcd41995 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:31 -0700 Subject: net: Convert skb_frag_t to bio_vec There are a lot of users of frag->page_offset, so use a union to avoid converting those users today. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/bvec.h | 5 ++++- include/linux/skbuff.h | 9 ++------- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index a032f01e928c..7f2b2ea9399c 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -18,7 +18,10 @@ struct bio_vec { struct page *bv_page; unsigned int bv_len; - unsigned int bv_offset; + union { + __u32 page_offset; + unsigned int bv_offset; + }; }; struct bvec_iter { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e849e411d1f3..718742b1c505 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -308,13 +309,7 @@ extern int sysctl_max_skb_frags; */ #define GSO_BY_FRAGS 0xFFFF -typedef struct skb_frag_struct skb_frag_t; - -struct skb_frag_struct { - struct page *bv_page; - unsigned int bv_len; - __u32 page_offset; -}; +typedef struct bio_vec skb_frag_t; /** * skb_frag_size - Returns the size of a skb fragment -- cgit v1.2.3-71-gd317 From 3a79bc63d90750f737ab9d7219bd3091d2fd6d84 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 15 Jul 2019 13:03:20 +0200 Subject: PCI: irq: Introduce rearm_wake_irq() Introduce a new function, rearm_wake_irq(), allowing a wakeup IRQ to be armed for systen wakeup detection again without running any action handlers associated with it after it has been armed for wakeup detection and triggered. That is useful for IRQs, like ACPI SCI, that may deliver wakeup as well as non-wakeup interrupts when armed for systen wakeup detection. In those cases, it may be possible to determine whether or not the delivered interrupt is a systen wakeup one without running the entire action handler (or handlers, if the IRQ is shared) for the IRQ, and if the interrupt turns out to be a non-wakeup one, the IRQ can be rearmed with the help of the new function. Signed-off-by: Rafael J. Wysocki Acked-by: Thomas Gleixner --- include/linux/interrupt.h | 1 + kernel/irq/pm.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5b8328a99b2a..0e9cdb3efda7 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -238,6 +238,7 @@ extern void teardown_percpu_nmi(unsigned int irq); /* The following three functions are for the core kernel use only. */ extern void suspend_device_irqs(void); extern void resume_device_irqs(void); +extern void rearm_wake_irq(unsigned int irq); /** * struct irq_affinity_notify - context for notification of IRQ affinity changes diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index d6961d3c6f9e..8f557fa1f4fe 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -176,6 +176,26 @@ static void resume_irqs(bool want_early) } } +/** + * rearm_wake_irq - rearm a wakeup interrupt line after signaling wakeup + * @irq: Interrupt to rearm + */ +void rearm_wake_irq(unsigned int irq) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc || !(desc->istate & IRQS_SUSPENDED) || + !irqd_is_wakeup_set(&desc->irq_data)) + return; + + desc->istate &= ~IRQS_SUSPENDED; + irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED); + __enable_irq(desc); + + irq_put_desc_busunlock(desc, flags); +} + /** * irq_pm_syscore_ops - enable interrupt lines early * -- cgit v1.2.3-71-gd317 From 56b991849009f5def0443bfb2f48c8321d888e15 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 15 Jul 2019 23:52:03 +0200 Subject: PM: sleep: Simplify suspend-to-idle control flow After commit 33e4f80ee69b ("ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle") the "noirq" phases of device suspend and resume may run for multiple times during suspend-to-idle, if there are spurious system wakeup events while suspended. However, this is complicated and fragile and actually unnecessary. The main reason for doing this is that on some systems the EC may signal system wakeup events (power button events, for example) as well as events that should not cause the system to resume (spurious system wakeup events). Thus, in order to determine whether or not a given event signaled by the EC while suspended is a proper system wakeup one, the EC GPE needs to be dispatched and to start with that was achieved by allowing the ACPI SCI action handler to run, which was only possible after calling resume_device_irqs(). However, dispatching the EC GPE this way turned out to take too much time in some cases and some EC events might be missed due to that, so commit 68e22011856f ("ACPI: EC: Dispatch the EC GPE directly on s2idle wake") started to dispatch the EC GPE right after a wakeup event has been detected, so in fact the full ACPI SCI action handler doesn't need to run any more to deal with the wakeups coming from the EC. Use this observation to simplify the suspend-to-idle control flow so that the "noirq" phases of device suspend and resume are each run only once in every suspend-to-idle cycle, which is reported to significantly reduce power drawn by some systems when suspended to idle (by allowing them to reach a deep platform-wide low-power state through the suspend-to-idle flow). [What appears to happen is that the "noirq" resume of devices after a spurious EC wakeup brings some devices into a state in which they prevent the platform from reaching the deep low-power state going forward, even after a subsequent "noirq" suspend phase, and on some systems the EC triggers such wakeups already when the "noirq" suspend of devices is running for the first time in the given suspend/resume cycle, so the platform cannot reach the deep low-power state at all.] First, make acpi_s2idle_wake() use the acpi_ec_dispatch_gpe() return value to determine whether or not the wakeup may have been triggered by the EC (in which case the system wakeup is canceled and ACPI events are processed in order to determine whether or not the event is a proper system wakeup one) and use rearm_wake_irq() (introduced by a previous change) in it to rearm the ACPI SCI for system wakeup detection in case the system will remain suspended. Second, drop acpi_s2idle_sync(), which is not needed any more, and the corresponding global platform suspend-to-idle callback. Next, drop the pm_wakeup_pending() check (which is an optimization only) from __device_suspend_noirq() to prevent it from returning errors on system wakeups occurring before the "noirq" phase of device suspend is complete (as in the case of suspend-to-idle it is not known whether or not these wakeups are suprious at that point), in order to avoid having to carry out a "noirq" resume of devices on a spurious system wakeup. Finally, change the code flow in s2idle_loop() to (1) run the "noirq" suspend of devices once before starting the loop, (2) check for spurious EC wakeups (via the platform ->wake callback) for the first time before calling s2idle_enter(), and (3) run the "noirq" resume of devices once after leaving the loop. Signed-off-by: Rafael J. Wysocki Acked-by: Thomas Gleixner --- drivers/acpi/sleep.c | 47 +++++++++++++++++++++-------------------- drivers/base/power/main.c | 5 ----- include/linux/suspend.h | 1 - kernel/power/suspend.c | 53 ++++++++++++++++++++--------------------------- 4 files changed, 48 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 3debe1a42655..970ae7c7a3f7 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -986,33 +986,37 @@ static void acpi_s2idle_wake(void) lpi_check_constraints(); /* - * If IRQD_WAKEUP_ARMED is not set for the SCI at this point, it means - * that the SCI has triggered while suspended, so cancel the wakeup in - * case it has not been a wakeup event (the GPEs will be checked later). + * If IRQD_WAKEUP_ARMED is set for the SCI at this point, the SCI has + * not triggered while suspended, so bail out. */ - if (acpi_sci_irq_valid() && - !irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) { + if (!acpi_sci_irq_valid() || + irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) + return; + + /* + * If there are EC events to process, the wakeup may be a spurious one + * coming from the EC. + */ + if (acpi_ec_dispatch_gpe()) { + /* + * Cancel the wakeup and process all pending events in case + * there are any wakeup ones in there. + * + * Note that if any non-EC GPEs are active at this point, the + * SCI will retrigger after the rearming below, so no events + * should be missed by canceling the wakeup here. + */ pm_system_cancel_wakeup(); /* - * On some platforms with the LPS0 _DSM device noirq resume - * takes too much time for EC wakeup events to survive, so look - * for them now. + * The EC driver uses the system workqueue and an additional + * special one, so those need to be flushed too. */ - acpi_ec_dispatch_gpe(); + acpi_os_wait_events_complete(); /* synchronize EC GPE processing */ + acpi_ec_flush_work(); + acpi_os_wait_events_complete(); /* synchronize Notify handling */ } -} -static void acpi_s2idle_sync(void) -{ - /* - * Process all pending events in case there are any wakeup ones. - * - * The EC driver uses the system workqueue and an additional special - * one, so those need to be flushed too. - */ - acpi_os_wait_events_complete(); /* synchronize SCI IRQ handling */ - acpi_ec_flush_work(); - acpi_os_wait_events_complete(); /* synchronize Notify handling */ + rearm_wake_irq(acpi_sci_irq); } static void acpi_s2idle_restore(void) @@ -1044,7 +1048,6 @@ static const struct platform_s2idle_ops acpi_s2idle_ops = { .begin = acpi_s2idle_begin, .prepare = acpi_s2idle_prepare, .wake = acpi_s2idle_wake, - .sync = acpi_s2idle_sync, .restore = acpi_s2idle_restore, .end = acpi_s2idle_end, }; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 7fb2c39bc725..f08332fab531 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1291,11 +1291,6 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a if (async_error) goto Complete; - if (pm_wakeup_pending()) { - async_error = -EBUSY; - goto Complete; - } - if (dev->power.syscore || dev->power.direct_complete) goto Complete; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 9c0ad1a3a727..66ce3871ed61 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -191,7 +191,6 @@ struct platform_s2idle_ops { int (*begin)(void); int (*prepare)(void); void (*wake)(void); - void (*sync)(void); void (*restore)(void); void (*end)(void); }; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index c874a7026e24..907b2be0372f 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -119,48 +119,41 @@ static void s2idle_enter(void) static void s2idle_loop(void) { + int error; + + dpm_noirq_begin(); + error = dpm_noirq_suspend_devices(PMSG_SUSPEND); + if (error) + goto resume; + pm_pr_dbg("suspend-to-idle\n"); + /* + * Suspend-to-idle equals: + * frozen processes + suspended devices + idle processors. + * Thus s2idle_enter() should be called right after all devices have + * been suspended. + * + * Wakeups during the noirq suspend of devices may be spurious, so try + * to avoid them upfront. + */ for (;;) { - int error; - - dpm_noirq_begin(); - - /* - * Suspend-to-idle equals - * frozen processes + suspended devices + idle processors. - * Thus s2idle_enter() should be called right after - * all devices have been suspended. - * - * Wakeups during the noirq suspend of devices may be spurious, - * so prevent them from terminating the loop right away. - */ - error = dpm_noirq_suspend_devices(PMSG_SUSPEND); - if (!error) - s2idle_enter(); - else if (error == -EBUSY && pm_wakeup_pending()) - error = 0; - - if (!error && s2idle_ops && s2idle_ops->wake) + if (s2idle_ops && s2idle_ops->wake) s2idle_ops->wake(); - dpm_noirq_resume_devices(PMSG_RESUME); - - dpm_noirq_end(); - - if (error) - break; - - if (s2idle_ops && s2idle_ops->sync) - s2idle_ops->sync(); - if (pm_wakeup_pending()) break; pm_wakeup_clear(false); + + s2idle_enter(); } pm_pr_dbg("resume from suspend-to-idle\n"); + +resume: + dpm_noirq_resume_devices(PMSG_RESUME); + dpm_noirq_end(); } void s2idle_wake(void) -- cgit v1.2.3-71-gd317 From b605c44c30b59990e806f930c37bd288b9d901a5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 15 Jul 2019 23:52:18 +0200 Subject: PM: sleep: Drop dpm_noirq_begin() and dpm_noirq_end() Note that after previous changes dpm_noirq_begin() and dpm_noirq_end() each have only one caller, so move the code from them to their respective callers and drop them. Also note that dpm_noirq_resume_devices() and dpm_noirq_suspend_devices() need not be exported any more, so make them both static. This change is not expected to alter functionality. Signed-off-by: Rafael J. Wysocki Acked-by: Thomas Gleixner --- drivers/base/power/main.c | 30 ++++++++++++------------------ include/linux/pm.h | 4 ---- 2 files changed, 12 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index f08332fab531..134a8af51511 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -716,7 +716,7 @@ static void async_resume_noirq(void *data, async_cookie_t cookie) put_device(dev); } -void dpm_noirq_resume_devices(pm_message_t state) +static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); @@ -760,13 +760,6 @@ void dpm_noirq_resume_devices(pm_message_t state) trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false); } -void dpm_noirq_end(void) -{ - resume_device_irqs(); - device_wakeup_disarm_wake_irqs(); - cpuidle_resume(); -} - /** * dpm_resume_noirq - Execute "noirq resume" callbacks for all devices. * @state: PM transition of the system being carried out. @@ -777,7 +770,11 @@ void dpm_noirq_end(void) void dpm_resume_noirq(pm_message_t state) { dpm_noirq_resume_devices(state); - dpm_noirq_end(); + + resume_device_irqs(); + device_wakeup_disarm_wake_irqs(); + + cpuidle_resume(); } static pm_callback_t dpm_subsys_resume_early_cb(struct device *dev, @@ -1357,14 +1354,7 @@ static int device_suspend_noirq(struct device *dev) return __device_suspend_noirq(dev, pm_transition, false); } -void dpm_noirq_begin(void) -{ - cpuidle_pause(); - device_wakeup_arm_wake_irqs(); - suspend_device_irqs(); -} - -int dpm_noirq_suspend_devices(pm_message_t state) +static int dpm_noirq_suspend_devices(pm_message_t state) { ktime_t starttime = ktime_get(); int error = 0; @@ -1421,7 +1411,11 @@ int dpm_suspend_noirq(pm_message_t state) { int ret; - dpm_noirq_begin(); + cpuidle_pause(); + + device_wakeup_arm_wake_irqs(); + suspend_device_irqs(); + ret = dpm_noirq_suspend_devices(state); if (ret) dpm_resume_noirq(resume_event(state)); diff --git a/include/linux/pm.h b/include/linux/pm.h index 3619a870eaa4..4c441be03079 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -712,8 +712,6 @@ struct dev_pm_domain { extern void device_pm_lock(void); extern void dpm_resume_start(pm_message_t state); extern void dpm_resume_end(pm_message_t state); -extern void dpm_noirq_resume_devices(pm_message_t state); -extern void dpm_noirq_end(void); extern void dpm_resume_noirq(pm_message_t state); extern void dpm_resume_early(pm_message_t state); extern void dpm_resume(pm_message_t state); @@ -722,8 +720,6 @@ extern void dpm_complete(pm_message_t state); extern void device_pm_unlock(void); extern int dpm_suspend_end(pm_message_t state); extern int dpm_suspend_start(pm_message_t state); -extern void dpm_noirq_begin(void); -extern int dpm_noirq_suspend_devices(pm_message_t state); extern int dpm_suspend_noirq(pm_message_t state); extern int dpm_suspend_late(pm_message_t state); extern int dpm_suspend(pm_message_t state); -- cgit v1.2.3-71-gd317 From 3b8720e63f4a1fc6f422a49ecbaa3b59c86d5aaf Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Sun, 21 Jul 2019 22:19:56 +0200 Subject: fbdev: Ditch fb_edid_add_monspecs It's dead code ever since commit 34280340b1dc74c521e636f45cd728f9abf56ee2 Author: Geert Uytterhoeven Date: Fri Dec 4 17:01:43 2015 +0100 fbdev: Remove unused SH-Mobile HDMI driver Also with this gone we can remove the cea_modes db. This entire thing is massively incomplete anyway, compared to the CEA parsing that drm_edid.c does. Acked-by: Linus Torvalds Cc: Tavis Ormandy Signed-off-by: Daniel Vetter Signed-off-by: Bartlomiej Zolnierkiewicz Link: https://patchwork.freedesktop.org/patch/msgid/20190721201956.941-1-daniel.vetter@ffwll.ch --- drivers/video/fbdev/core/fbmon.c | 96 --------------------------------------- drivers/video/fbdev/core/modedb.c | 57 ----------------------- include/linux/fb.h | 3 -- 3 files changed, 156 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index 3558a70a6664..8e2e19f3bf44 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -999,98 +999,6 @@ void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs) DPRINTK("========================================\n"); } -/** - * fb_edid_add_monspecs() - add monitor video modes from E-EDID data - * @edid: 128 byte array with an E-EDID block - * @spacs: monitor specs to be extended - */ -void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs) -{ - unsigned char *block; - struct fb_videomode *m; - int num = 0, i; - u8 svd[64], edt[(128 - 4) / DETAILED_TIMING_DESCRIPTION_SIZE]; - u8 pos = 4, svd_n = 0; - - if (!edid) - return; - - if (!edid_checksum(edid)) - return; - - if (edid[0] != 0x2 || - edid[2] < 4 || edid[2] > 128 - DETAILED_TIMING_DESCRIPTION_SIZE) - return; - - DPRINTK(" Short Video Descriptors\n"); - - while (pos < edid[2]) { - u8 len = edid[pos] & 0x1f, type = (edid[pos] >> 5) & 7; - pr_debug("Data block %u of %u bytes\n", type, len); - if (type == 2) { - for (i = pos; i < pos + len; i++) { - u8 idx = edid[pos + i] & 0x7f; - svd[svd_n++] = idx; - pr_debug("N%sative mode #%d\n", - edid[pos + i] & 0x80 ? "" : "on-n", idx); - } - } else if (type == 3 && len >= 3) { - /* Check Vendor Specific Data Block. For HDMI, - it is always 00-0C-03 for HDMI Licensing, LLC. */ - if (edid[pos + 1] == 3 && edid[pos + 2] == 0xc && - edid[pos + 3] == 0) - specs->misc |= FB_MISC_HDMI; - } - pos += len + 1; - } - - block = edid + edid[2]; - - DPRINTK(" Extended Detailed Timings\n"); - - for (i = 0; i < (128 - edid[2]) / DETAILED_TIMING_DESCRIPTION_SIZE; - i++, block += DETAILED_TIMING_DESCRIPTION_SIZE) - if (PIXEL_CLOCK != 0) - edt[num++] = block - edid; - - /* Yikes, EDID data is totally useless */ - if (!(num + svd_n)) - return; - - m = kcalloc(specs->modedb_len + num + svd_n, - sizeof(struct fb_videomode), - GFP_KERNEL); - - if (!m) - return; - - memcpy(m, specs->modedb, specs->modedb_len * sizeof(struct fb_videomode)); - - for (i = specs->modedb_len; i < specs->modedb_len + num; i++) { - get_detailed_timing(edid + edt[i - specs->modedb_len], &m[i]); - if (i == specs->modedb_len) - m[i].flag |= FB_MODE_IS_FIRST; - pr_debug("Adding %ux%u@%u\n", m[i].xres, m[i].yres, m[i].refresh); - } - - for (i = specs->modedb_len + num; i < specs->modedb_len + num + svd_n; i++) { - int idx = svd[i - specs->modedb_len - num]; - if (!idx || idx >= ARRAY_SIZE(cea_modes)) { - pr_warn("Reserved SVD code %d\n", idx); - } else if (!cea_modes[idx].xres) { - pr_warn("Unimplemented SVD code %d\n", idx); - } else { - memcpy(&m[i], cea_modes + idx, sizeof(m[i])); - pr_debug("Adding SVD #%d: %ux%u@%u\n", idx, - m[i].xres, m[i].yres, m[i].refresh); - } - } - - kfree(specs->modedb); - specs->modedb = m; - specs->modedb_len = specs->modedb_len + num + svd_n; -} - /* * VESA Generalized Timing Formula (GTF) */ @@ -1500,9 +1408,6 @@ int fb_parse_edid(unsigned char *edid, struct fb_var_screeninfo *var) void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs) { } -void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs) -{ -} void fb_destroy_modedb(struct fb_videomode *modedb) { } @@ -1610,7 +1515,6 @@ EXPORT_SYMBOL(fb_firmware_edid); EXPORT_SYMBOL(fb_parse_edid); EXPORT_SYMBOL(fb_edid_to_monspecs); -EXPORT_SYMBOL(fb_edid_add_monspecs); EXPORT_SYMBOL(fb_get_mode); EXPORT_SYMBOL(fb_validate_mode); EXPORT_SYMBOL(fb_destroy_modedb); diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c index ac049871704d..6473e0dfe146 100644 --- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -289,63 +289,6 @@ static const struct fb_videomode modedb[] = { }; #ifdef CONFIG_FB_MODE_HELPERS -const struct fb_videomode cea_modes[65] = { - /* #1: 640x480p@59.94/60Hz */ - [1] = { - NULL, 60, 640, 480, 39722, 48, 16, 33, 10, 96, 2, 0, - FB_VMODE_NONINTERLACED, 0, - }, - /* #3: 720x480p@59.94/60Hz */ - [3] = { - NULL, 60, 720, 480, 37037, 60, 16, 30, 9, 62, 6, 0, - FB_VMODE_NONINTERLACED, 0, - }, - /* #5: 1920x1080i@59.94/60Hz */ - [5] = { - NULL, 60, 1920, 1080, 13763, 148, 88, 15, 2, 44, 5, - FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, - FB_VMODE_INTERLACED, 0, - }, - /* #7: 720(1440)x480iH@59.94/60Hz */ - [7] = { - NULL, 60, 1440, 480, 18554/*37108*/, 114, 38, 15, 4, 124, 3, 0, - FB_VMODE_INTERLACED, 0, - }, - /* #9: 720(1440)x240pH@59.94/60Hz */ - [9] = { - NULL, 60, 1440, 240, 18554, 114, 38, 16, 4, 124, 3, 0, - FB_VMODE_NONINTERLACED, 0, - }, - /* #18: 720x576pH@50Hz */ - [18] = { - NULL, 50, 720, 576, 37037, 68, 12, 39, 5, 64, 5, 0, - FB_VMODE_NONINTERLACED, 0, - }, - /* #19: 1280x720p@50Hz */ - [19] = { - NULL, 50, 1280, 720, 13468, 220, 440, 20, 5, 40, 5, - FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, - FB_VMODE_NONINTERLACED, 0, - }, - /* #20: 1920x1080i@50Hz */ - [20] = { - NULL, 50, 1920, 1080, 13480, 148, 528, 15, 5, 528, 5, - FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, - FB_VMODE_INTERLACED, 0, - }, - /* #32: 1920x1080p@23.98/24Hz */ - [32] = { - NULL, 24, 1920, 1080, 13468, 148, 638, 36, 4, 44, 5, - FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, - FB_VMODE_NONINTERLACED, 0, - }, - /* #35: (2880)x480p4x@59.94/60Hz */ - [35] = { - NULL, 60, 2880, 480, 9250, 240, 64, 30, 9, 248, 6, 0, - FB_VMODE_NONINTERLACED, 0, - }, -}; - const struct fb_videomode vesa_modes[] = { /* 0 640x350-85 VESA */ { NULL, 85, 640, 350, 31746, 96, 32, 60, 32, 64, 3, diff --git a/include/linux/fb.h b/include/linux/fb.h index 303771264644..50948e519897 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -721,8 +721,6 @@ extern int fb_parse_edid(unsigned char *edid, struct fb_var_screeninfo *var); extern const unsigned char *fb_firmware_edid(struct device *device); extern void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs); -extern void fb_edid_add_monspecs(unsigned char *edid, - struct fb_monspecs *specs); extern void fb_destroy_modedb(struct fb_videomode *modedb); extern int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb); extern unsigned char *fb_ddc_read(struct i2c_adapter *adapter); @@ -796,7 +794,6 @@ struct dmt_videomode { extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; -extern const struct fb_videomode cea_modes[65]; extern const struct dmt_videomode dmt_modes[]; struct fb_modelist { -- cgit v1.2.3-71-gd317 From 4f77e0956bd99901af2bfc6641437ff8bff8d4a4 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Mon, 15 Jul 2019 14:34:16 -0600 Subject: PCI: Remove pci_block_cfg_access() et al (unused) Remove the following unused functions from include/linux/pci.h: pci_block_cfg_access() pci_block_cfg_access_in_atomic() pci_unblock_cfg_access() These were added by fb51ccbf217c ("PCI: Rework config space blocking services"), though no callers were added. Link: https://lore.kernel.org/r/20190715203416.37547-1-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas Reviewed-by: Lukas Bulwahn --- include/linux/pci.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 9e700d9f9f28..61b64fa1b0b1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1747,11 +1747,6 @@ static inline void pci_release_regions(struct pci_dev *dev) { } static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; } -static inline void pci_block_cfg_access(struct pci_dev *dev) { } -static inline int pci_block_cfg_access_in_atomic(struct pci_dev *dev) -{ return 0; } -static inline void pci_unblock_cfg_access(struct pci_dev *dev) { } - static inline struct pci_bus *pci_find_next_bus(const struct pci_bus *from) { return NULL; } static inline struct pci_dev *pci_get_slot(struct pci_bus *bus, -- cgit v1.2.3-71-gd317 From 60649d4e0af6c26b6c423dea9c57f39e823fc0c5 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 23 Jul 2019 14:08:47 +0200 Subject: can: remove obsolete empty ioctl() handler With commit c7cbdbf29f488a ("net: rework SIOCGSTAMP ioctl handling") the only ioctl function in can_ioctl() has been removed. As this SIOCGSTAMP ioctl command is now handled in net/socket.c we can entirely remove the CAN specific ioctl functions. Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 1 - net/can/af_can.c | 9 --------- net/can/bcm.c | 2 +- net/can/raw.c | 2 +- 4 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 6099bc18bd0c..f8284a94a13d 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -57,6 +57,5 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); -extern int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); #endif /* !_CAN_CORE_H */ diff --git a/net/can/af_can.c b/net/can/af_can.c index 80281ef2ccbd..9c86de2da45e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -87,15 +87,6 @@ static atomic_t skbcounter = ATOMIC_INIT(0); * af_can socket functions */ -int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - default: - return -ENOIOCTLCMD; - } -} -EXPORT_SYMBOL(can_ioctl); - static void can_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); diff --git a/net/can/bcm.c b/net/can/bcm.c index a34ee52f19ea..1eecf4d3e8d2 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1688,7 +1688,7 @@ static const struct proto_ops bcm_ops = { .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = sock_no_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/can/raw.c b/net/can/raw.c index afcbff063a67..bbbe3dd0abe9 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -845,7 +845,7 @@ static const struct proto_ops raw_ops = { .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = sock_no_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, -- cgit v1.2.3-71-gd317 From fba76a58452694b9b13c07e48839fa84c75f57af Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 23 Jul 2019 15:17:55 +0200 Subject: can: Add SPDX license identifiers for CAN subsystem Add missing SPDX identifiers for the CAN network layer and correct the SPDX license for two of its include files to make sure the BSD-3-Clause applies for the entire subsystem. Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 2 +- include/linux/can/skb.h | 2 +- net/can/af_can.c | 1 + net/can/af_can.h | 1 + net/can/bcm.c | 1 + net/can/gw.c | 1 + net/can/proc.c | 1 + net/can/raw.c | 1 + 8 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index f8284a94a13d..708c10d3417a 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/core.h * diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index b3379a97245c..a954def26c0d 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/skb.h * diff --git a/net/can/af_can.c b/net/can/af_can.c index 9c86de2da45e..76cf83b2bd40 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * af_can.c - Protocol family CAN core module * (used by different CAN protocol modules) diff --git a/net/can/af_can.h b/net/can/af_can.h index 9cb3719632bd..ef21f7c6bc80 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. diff --git a/net/can/bcm.c b/net/can/bcm.c index 1eecf4d3e8d2..8da986b19d88 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * diff --git a/net/can/gw.c b/net/can/gw.c index 5275ddf580bc..8abae841d504 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * gw.c - CAN frame Gateway/Router/Bridge with netlink interface * diff --git a/net/can/proc.c b/net/can/proc.c index 70fea17bb04c..edb822c31902 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * proc.c - procfs support for Protocol family CAN core module * diff --git a/net/can/raw.c b/net/can/raw.c index bbbe3dd0abe9..ff720272f7b7 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * raw.c - Raw sockets for protocol family CAN * -- cgit v1.2.3-71-gd317 From 6d1bcb957be2850e0776f24c289e1f87c256baeb Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:43:07 +0100 Subject: iommu: Remove empty iommu_tlb_range_add() callback from iommu_ops Commit add02cfdc9bc ("iommu: Introduce Interface for IOMMU TLB Flushing") added three new TLB flushing operations to the IOMMU API so that the underlying driver operations can be batched when unmapping large regions of IO virtual address space. However, the ->iotlb_range_add() callback has not been implemented by any IOMMU drivers (amd_iommu.c implements it as an empty function, which incurs the overhead of an indirect branch). Instead, drivers either flush the entire IOTLB in the ->iotlb_sync() callback or perform the necessary invalidation during ->unmap(). Attempting to implement ->iotlb_range_add() for arm-smmu-v3.c revealed two major issues: 1. The page size used to map the region in the page-table is not known, and so it is not generally possible to issue TLB flushes in the most efficient manner. 2. The only mutable state passed to the callback is a pointer to the iommu_domain, which can be accessed concurrently and therefore requires expensive synchronisation to keep track of the outstanding flushes. Remove the callback entirely in preparation for extending ->unmap() and ->iotlb_sync() to update a token on the caller's stack. Signed-off-by: Will Deacon --- drivers/iommu/amd_iommu.c | 6 ------ drivers/iommu/iommu.c | 3 --- drivers/vfio/vfio_iommu_type1.c | 1 - include/linux/iommu.h | 15 --------------- 4 files changed, 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index b607a92791d3..f93b148cf55e 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3196,11 +3196,6 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain) domain_flush_complete(dom); } -static void amd_iommu_iotlb_range_add(struct iommu_domain *domain, - unsigned long iova, size_t size) -{ -} - const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .domain_alloc = amd_iommu_domain_alloc, @@ -3219,7 +3214,6 @@ const struct iommu_ops amd_iommu_ops = { .is_attach_deferred = amd_iommu_is_attach_deferred, .pgsize_bitmap = AMD_IOMMU_PGSIZES, .flush_iotlb_all = amd_iommu_flush_iotlb_all, - .iotlb_range_add = amd_iommu_iotlb_range_add, .iotlb_sync = amd_iommu_flush_iotlb_all, }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 0c674d80c37f..6d7b25fe2474 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1903,9 +1903,6 @@ static size_t __iommu_unmap(struct iommu_domain *domain, if (!unmapped_page) break; - if (sync && ops->iotlb_range_add) - ops->iotlb_range_add(domain, iova, pgsize); - pr_debug("unmapped: iova 0x%lx size 0x%zx\n", iova, unmapped_page); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 054391f30fa8..fad7fd8c167c 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -696,7 +696,6 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain, if (!unmapped) { kfree(entry); } else { - iommu_tlb_range_add(domain->domain, *iova, unmapped); entry->iova = *iova; entry->phys = phys; entry->len = unmapped; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index fdc355ccc570..1e21431262d9 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -201,7 +201,6 @@ struct iommu_sva_ops { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain - * @iotlb_range_add: Add a given iova range to the flush queue for this domain * @iotlb_sync_map: Sync mappings created recently using @map to the hardware * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue @@ -244,8 +243,6 @@ struct iommu_ops { size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size); void (*flush_iotlb_all)(struct iommu_domain *domain); - void (*iotlb_range_add)(struct iommu_domain *domain, - unsigned long iova, size_t size); void (*iotlb_sync_map)(struct iommu_domain *domain); void (*iotlb_sync)(struct iommu_domain *domain); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); @@ -476,13 +473,6 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain) domain->ops->flush_iotlb_all(domain); } -static inline void iommu_tlb_range_add(struct iommu_domain *domain, - unsigned long iova, size_t size) -{ - if (domain->ops->iotlb_range_add) - domain->ops->iotlb_range_add(domain, iova, size); -} - static inline void iommu_tlb_sync(struct iommu_domain *domain) { if (domain->ops->iotlb_sync) @@ -637,11 +627,6 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain) { } -static inline void iommu_tlb_range_add(struct iommu_domain *domain, - unsigned long iova, size_t size) -{ -} - static inline void iommu_tlb_sync(struct iommu_domain *domain) { } -- cgit v1.2.3-71-gd317 From 298f78895b081911e0b3605f07d79ebd3d4cf7b0 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:43:34 +0100 Subject: iommu/io-pgtable: Rename iommu_gather_ops to iommu_flush_ops In preparation for TLB flush gathering in the IOMMU API, rename the iommu_gather_ops structure in io-pgtable to iommu_flush_ops, which better describes its purpose and avoids the potential for confusion between different levels of the API. $ find linux/ -type f -name '*.[ch]' | xargs sed -i 's/gather_ops/flush_ops/g' Signed-off-by: Will Deacon --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 2 +- drivers/iommu/arm-smmu-v3.c | 4 ++-- drivers/iommu/arm-smmu.c | 8 ++++---- drivers/iommu/io-pgtable-arm-v7s.c | 2 +- drivers/iommu/io-pgtable-arm.c | 2 +- drivers/iommu/ipmmu-vmsa.c | 4 ++-- drivers/iommu/msm_iommu.c | 4 ++-- drivers/iommu/mtk_iommu.c | 4 ++-- drivers/iommu/qcom_iommu.c | 4 ++-- include/linux/io-pgtable.h | 6 +++--- 10 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 92ac995dd9c6..17bceb11e708 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -257,7 +257,7 @@ static void mmu_tlb_sync_context(void *cookie) // TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X } -static const struct iommu_gather_ops mmu_tlb_ops = { +static const struct iommu_flush_ops mmu_tlb_ops = { .tlb_flush_all = mmu_tlb_inv_context_s1, .tlb_add_flush = mmu_tlb_inv_range_nosync, .tlb_sync = mmu_tlb_sync_context, diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index a9a9fabd3968..7e137e1e28f1 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1603,7 +1603,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, } while (size -= granule); } -static const struct iommu_gather_ops arm_smmu_gather_ops = { +static const struct iommu_flush_ops arm_smmu_flush_ops = { .tlb_flush_all = arm_smmu_tlb_inv_context, .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, .tlb_sync = arm_smmu_tlb_sync, @@ -1796,7 +1796,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) .ias = ias, .oas = oas, .coherent_walk = smmu->features & ARM_SMMU_FEAT_COHERENCY, - .tlb = &arm_smmu_gather_ops, + .tlb = &arm_smmu_flush_ops, .iommu_dev = smmu->dev, }; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 64977c131ee6..dc08db347ef3 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -251,7 +251,7 @@ enum arm_smmu_domain_stage { struct arm_smmu_domain { struct arm_smmu_device *smmu; struct io_pgtable_ops *pgtbl_ops; - const struct iommu_gather_ops *tlb_ops; + const struct iommu_flush_ops *tlb_ops; struct arm_smmu_cfg cfg; enum arm_smmu_domain_stage stage; bool non_strict; @@ -547,19 +547,19 @@ static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size, writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID); } -static const struct iommu_gather_ops arm_smmu_s1_tlb_ops = { +static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = { .tlb_flush_all = arm_smmu_tlb_inv_context_s1, .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, .tlb_sync = arm_smmu_tlb_sync_context, }; -static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v2 = { +static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = { .tlb_flush_all = arm_smmu_tlb_inv_context_s2, .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, .tlb_sync = arm_smmu_tlb_sync_context, }; -static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = { +static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = { .tlb_flush_all = arm_smmu_tlb_inv_context_s2, .tlb_add_flush = arm_smmu_tlb_inv_vmid_nosync, .tlb_sync = arm_smmu_tlb_sync_vmid, diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index a62733c6a632..116f97ee991e 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -817,7 +817,7 @@ static void dummy_tlb_sync(void *cookie) WARN_ON(cookie != cfg_cookie); } -static const struct iommu_gather_ops dummy_tlb_ops = { +static const struct iommu_flush_ops dummy_tlb_ops = { .tlb_flush_all = dummy_tlb_flush_all, .tlb_add_flush = dummy_tlb_add_flush, .tlb_sync = dummy_tlb_sync, diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 0d6633921c1e..402f913b6f6d 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -1081,7 +1081,7 @@ static void dummy_tlb_sync(void *cookie) WARN_ON(cookie != cfg_cookie); } -static const struct iommu_gather_ops dummy_tlb_ops __initconst = { +static const struct iommu_flush_ops dummy_tlb_ops __initconst = { .tlb_flush_all = dummy_tlb_flush_all, .tlb_add_flush = dummy_tlb_add_flush, .tlb_sync = dummy_tlb_sync, diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index ad0098c0c87c..2c14a2c65b22 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -367,7 +367,7 @@ static void ipmmu_tlb_add_flush(unsigned long iova, size_t size, /* The hardware doesn't support selective TLB flush. */ } -static const struct iommu_gather_ops ipmmu_gather_ops = { +static const struct iommu_flush_ops ipmmu_flush_ops = { .tlb_flush_all = ipmmu_tlb_flush_all, .tlb_add_flush = ipmmu_tlb_add_flush, .tlb_sync = ipmmu_tlb_flush_all, @@ -480,7 +480,7 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain) domain->cfg.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K; domain->cfg.ias = 32; domain->cfg.oas = 40; - domain->cfg.tlb = &ipmmu_gather_ops; + domain->cfg.tlb = &ipmmu_flush_ops; domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32); domain->io_domain.geometry.force_aperture = true; /* diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index b25e2eb9e038..8b602384a385 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -178,7 +178,7 @@ static void __flush_iotlb_sync(void *cookie) */ } -static const struct iommu_gather_ops msm_iommu_gather_ops = { +static const struct iommu_flush_ops msm_iommu_flush_ops = { .tlb_flush_all = __flush_iotlb, .tlb_add_flush = __flush_iotlb_range, .tlb_sync = __flush_iotlb_sync, @@ -345,7 +345,7 @@ static int msm_iommu_domain_config(struct msm_priv *priv) .pgsize_bitmap = msm_iommu_ops.pgsize_bitmap, .ias = 32, .oas = 32, - .tlb = &msm_iommu_gather_ops, + .tlb = &msm_iommu_flush_ops, .iommu_dev = priv->dev, }; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 82e4be4dfdaf..fed77658d67e 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -188,7 +188,7 @@ static void mtk_iommu_tlb_sync(void *cookie) } } -static const struct iommu_gather_ops mtk_iommu_gather_ops = { +static const struct iommu_flush_ops mtk_iommu_flush_ops = { .tlb_flush_all = mtk_iommu_tlb_flush_all, .tlb_add_flush = mtk_iommu_tlb_add_flush_nosync, .tlb_sync = mtk_iommu_tlb_sync, @@ -267,7 +267,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom) .pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap, .ias = 32, .oas = 32, - .tlb = &mtk_iommu_gather_ops, + .tlb = &mtk_iommu_flush_ops, .iommu_dev = data->dev, }; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 34d0b9783b3e..fd9d9f4da735 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -164,7 +164,7 @@ static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size, } } -static const struct iommu_gather_ops qcom_gather_ops = { +static const struct iommu_flush_ops qcom_flush_ops = { .tlb_flush_all = qcom_iommu_tlb_inv_context, .tlb_add_flush = qcom_iommu_tlb_inv_range_nosync, .tlb_sync = qcom_iommu_tlb_sync, @@ -215,7 +215,7 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, .pgsize_bitmap = qcom_iommu_ops.pgsize_bitmap, .ias = 32, .oas = 40, - .tlb = &qcom_gather_ops, + .tlb = &qcom_flush_ops, .iommu_dev = qcom_iommu->dev, }; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index b5a450a3bb47..6292ea15d674 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -17,7 +17,7 @@ enum io_pgtable_fmt { }; /** - * struct iommu_gather_ops - IOMMU callbacks for TLB and page table management. + * struct iommu_flush_ops - IOMMU callbacks for TLB and page table management. * * @tlb_flush_all: Synchronously invalidate the entire TLB context. * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range. @@ -28,7 +28,7 @@ enum io_pgtable_fmt { * Note that these can all be called in atomic context and must therefore * not block. */ -struct iommu_gather_ops { +struct iommu_flush_ops { void (*tlb_flush_all)(void *cookie); void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule, bool leaf, void *cookie); @@ -84,7 +84,7 @@ struct io_pgtable_cfg { unsigned int ias; unsigned int oas; bool coherent_walk; - const struct iommu_gather_ops *tlb; + const struct iommu_flush_ops *tlb; struct device *iommu_dev; /* Low-level data specific to the table format */ -- cgit v1.2.3-71-gd317 From a7d20dc19d9ea7012227be5144353012ffa3ddc4 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:43:48 +0100 Subject: iommu: Introduce struct iommu_iotlb_gather for batching TLB flushes To permit batching of TLB flushes across multiple calls to the IOMMU driver's ->unmap() implementation, introduce a new structure for tracking the address range to be flushed and the granularity at which the flushing is required. This is hooked into the IOMMU API and its caller are updated to make use of the new structure. Subsequent patches will plumb this into the IOMMU drivers as well, but for now the gathering information is ignored. Signed-off-by: Will Deacon --- drivers/iommu/dma-iommu.c | 9 +++++++-- drivers/iommu/iommu.c | 19 +++++++++++------- drivers/vfio/vfio_iommu_type1.c | 26 ++++++++++++++++--------- include/linux/iommu.h | 43 +++++++++++++++++++++++++++++++++++++---- 4 files changed, 75 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index a7f9c3edbcb2..80beb1f5994a 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -444,13 +444,18 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr, struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iova_domain *iovad = &cookie->iovad; size_t iova_off = iova_offset(iovad, dma_addr); + struct iommu_iotlb_gather iotlb_gather; + size_t unmapped; dma_addr -= iova_off; size = iova_align(iovad, size + iova_off); + iommu_iotlb_gather_init(&iotlb_gather); + + unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather); + WARN_ON(unmapped != size); - WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size); if (!cookie->fq_domain) - iommu_tlb_sync(domain); + iommu_tlb_sync(domain, &iotlb_gather); iommu_dma_free_iova(cookie, dma_addr, size); } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6d7b25fe2474..d67222fdfe44 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1862,7 +1862,7 @@ EXPORT_SYMBOL_GPL(iommu_map); static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size, - bool sync) + struct iommu_iotlb_gather *iotlb_gather) { const struct iommu_ops *ops = domain->ops; size_t unmapped_page, unmapped = 0; @@ -1910,9 +1910,6 @@ static size_t __iommu_unmap(struct iommu_domain *domain, unmapped += unmapped_page; } - if (sync && ops->iotlb_sync) - ops->iotlb_sync(domain); - trace_unmap(orig_iova, size, unmapped); return unmapped; } @@ -1920,14 +1917,22 @@ static size_t __iommu_unmap(struct iommu_domain *domain, size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { - return __iommu_unmap(domain, iova, size, true); + struct iommu_iotlb_gather iotlb_gather; + size_t ret; + + iommu_iotlb_gather_init(&iotlb_gather); + ret = __iommu_unmap(domain, iova, size, &iotlb_gather); + iommu_tlb_sync(domain, &iotlb_gather); + + return ret; } EXPORT_SYMBOL_GPL(iommu_unmap); size_t iommu_unmap_fast(struct iommu_domain *domain, - unsigned long iova, size_t size) + unsigned long iova, size_t size, + struct iommu_iotlb_gather *iotlb_gather) { - return __iommu_unmap(domain, iova, size, false); + return __iommu_unmap(domain, iova, size, iotlb_gather); } EXPORT_SYMBOL_GPL(iommu_unmap_fast); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index fad7fd8c167c..ad830abe1021 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -650,12 +650,13 @@ unpin_exit: } static long vfio_sync_unpin(struct vfio_dma *dma, struct vfio_domain *domain, - struct list_head *regions) + struct list_head *regions, + struct iommu_iotlb_gather *iotlb_gather) { long unlocked = 0; struct vfio_regions *entry, *next; - iommu_tlb_sync(domain->domain); + iommu_tlb_sync(domain->domain, iotlb_gather); list_for_each_entry_safe(entry, next, regions, list) { unlocked += vfio_unpin_pages_remote(dma, @@ -685,13 +686,15 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain, struct vfio_dma *dma, dma_addr_t *iova, size_t len, phys_addr_t phys, long *unlocked, struct list_head *unmapped_list, - int *unmapped_cnt) + int *unmapped_cnt, + struct iommu_iotlb_gather *iotlb_gather) { size_t unmapped = 0; struct vfio_regions *entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry) { - unmapped = iommu_unmap_fast(domain->domain, *iova, len); + unmapped = iommu_unmap_fast(domain->domain, *iova, len, + iotlb_gather); if (!unmapped) { kfree(entry); @@ -711,8 +714,8 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain, * or in case of errors. */ if (*unmapped_cnt >= VFIO_IOMMU_TLB_SYNC_MAX || !unmapped) { - *unlocked += vfio_sync_unpin(dma, domain, - unmapped_list); + *unlocked += vfio_sync_unpin(dma, domain, unmapped_list, + iotlb_gather); *unmapped_cnt = 0; } @@ -743,6 +746,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma, dma_addr_t iova = dma->iova, end = dma->iova + dma->size; struct vfio_domain *domain, *d; LIST_HEAD(unmapped_region_list); + struct iommu_iotlb_gather iotlb_gather; int unmapped_region_cnt = 0; long unlocked = 0; @@ -767,6 +771,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma, cond_resched(); } + iommu_iotlb_gather_init(&iotlb_gather); while (iova < end) { size_t unmapped, len; phys_addr_t phys, next; @@ -795,7 +800,8 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma, */ unmapped = unmap_unpin_fast(domain, dma, &iova, len, phys, &unlocked, &unmapped_region_list, - &unmapped_region_cnt); + &unmapped_region_cnt, + &iotlb_gather); if (!unmapped) { unmapped = unmap_unpin_slow(domain, dma, &iova, len, phys, &unlocked); @@ -806,8 +812,10 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma, dma->iommu_mapped = false; - if (unmapped_region_cnt) - unlocked += vfio_sync_unpin(dma, domain, &unmapped_region_list); + if (unmapped_region_cnt) { + unlocked += vfio_sync_unpin(dma, domain, &unmapped_region_list, + &iotlb_gather); + } if (do_accounting) { vfio_lock_acct(dma, -unlocked, true); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 1e21431262d9..aaf073010a9a 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -191,6 +191,23 @@ struct iommu_sva_ops { #ifdef CONFIG_IOMMU_API +/** + * struct iommu_iotlb_gather - Range information for a pending IOTLB flush + * + * @start: IOVA representing the start of the range to be flushed + * @end: IOVA representing the end of the range to be flushed (exclusive) + * @pgsize: The interval at which to perform the flush + * + * This structure is intended to be updated by multiple calls to the + * ->unmap() function in struct iommu_ops before eventually being passed + * into ->iotlb_sync(). + */ +struct iommu_iotlb_gather { + unsigned long start; + unsigned long end; + size_t pgsize; +}; + /** * struct iommu_ops - iommu ops and capabilities * @capable: check capability @@ -375,6 +392,13 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev) return (struct iommu_device *)dev_get_drvdata(dev); } +static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) +{ + *gather = (struct iommu_iotlb_gather) { + .start = ULONG_MAX, + }; +} + #define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ #define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ #define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ @@ -399,7 +423,8 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova, extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, - unsigned long iova, size_t size); + unsigned long iova, size_t size, + struct iommu_iotlb_gather *iotlb_gather); extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg,unsigned int nents, int prot); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); @@ -473,10 +498,13 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain) domain->ops->flush_iotlb_all(domain); } -static inline void iommu_tlb_sync(struct iommu_domain *domain) +static inline void iommu_tlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather) { if (domain->ops->iotlb_sync) domain->ops->iotlb_sync(domain); + + iommu_iotlb_gather_init(iotlb_gather); } /* PCI device grouping function */ @@ -557,6 +585,7 @@ struct iommu_group {}; struct iommu_fwspec {}; struct iommu_device {}; struct iommu_fault_param {}; +struct iommu_iotlb_gather {}; static inline bool iommu_present(struct bus_type *bus) { @@ -611,7 +640,8 @@ static inline size_t iommu_unmap(struct iommu_domain *domain, } static inline size_t iommu_unmap_fast(struct iommu_domain *domain, - unsigned long iova, int gfp_order) + unsigned long iova, int gfp_order, + struct iommu_iotlb_gather *iotlb_gather) { return 0; } @@ -627,7 +657,8 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain) { } -static inline void iommu_tlb_sync(struct iommu_domain *domain) +static inline void iommu_tlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather) { } @@ -812,6 +843,10 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev) return NULL; } +static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) +{ +} + static inline void iommu_device_unregister(struct iommu_device *iommu) { } -- cgit v1.2.3-71-gd317 From 4fcf8544fc677fc8af135f1d86b3ba69c4ad429d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:43:57 +0100 Subject: iommu: Introduce iommu_iotlb_gather_add_page() Introduce a helper function for drivers to use when updating an iommu_iotlb_gather structure in response to an ->unmap() call, rather than having to open-code the logic in every page-table implementation. Signed-off-by: Will Deacon --- include/linux/iommu.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index aaf073010a9a..ad41aee55bc6 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -507,6 +507,31 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain, iommu_iotlb_gather_init(iotlb_gather); } +static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather, + unsigned long iova, size_t size) +{ + unsigned long start = iova, end = start + size; + + /* + * If the new page is disjoint from the current range or is mapped at + * a different granularity, then sync the TLB so that the gather + * structure can be rewritten. + */ + if (gather->pgsize != size || + end < gather->start || start > gather->end) { + if (gather->pgsize) + iommu_tlb_sync(domain, gather); + gather->pgsize = size; + } + + if (gather->end < end) + gather->end = end; + + if (gather->start > start) + gather->start = start; +} + /* PCI device grouping function */ extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ @@ -847,6 +872,12 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) { } +static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather, + unsigned long iova, size_t size) +{ +} + static inline void iommu_device_unregister(struct iommu_device *iommu) { } -- cgit v1.2.3-71-gd317 From 511885d7061eda3eb1faf3f57dcc936ff75863f1 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 24 Jul 2019 08:23:23 -0700 Subject: lib/timerqueue: Rely on rbtree semantics for next timer Simplify the timerqueue code by using cached rbtrees and rely on the tree leftmost node semantics to get the timer with earliest expiration time. This is a drop in conversion, and therefore semantics remain untouched. The runtime overhead of cached rbtrees is be pretty much the same as the current head->next method, noting that when removing the leftmost node, a common operation for the timerqueue, the rb_next(leftmost) is O(1) as well, so the next timer will either be the right node or its parent. Therefore no extra pointer chasing. Finally, the size of the struct timerqueue_head remains the same. Passes several hours of rcutorture. Signed-off-by: Davidlohr Bueso Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20190724152323.bojciei3muvfxalm@linux-r8p5 --- include/linux/timerqueue.h | 13 ++++++------- lib/timerqueue.c | 30 ++++++++++++------------------ 2 files changed, 18 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 78b8cc73f12f..aff122f1062a 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -12,8 +12,7 @@ struct timerqueue_node { }; struct timerqueue_head { - struct rb_root head; - struct timerqueue_node *next; + struct rb_root_cached rb_root; }; @@ -29,13 +28,14 @@ extern struct timerqueue_node *timerqueue_iterate_next( * * @head: head of timerqueue * - * Returns a pointer to the timer node that has the - * earliest expiration time. + * Returns a pointer to the timer node that has the earliest expiration time. */ static inline struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) { - return head->next; + struct rb_node *leftmost = rb_first_cached(&head->rb_root); + + return rb_entry(leftmost, struct timerqueue_node, node); } static inline void timerqueue_init(struct timerqueue_node *node) @@ -45,7 +45,6 @@ static inline void timerqueue_init(struct timerqueue_node *node) static inline void timerqueue_init_head(struct timerqueue_head *head) { - head->head = RB_ROOT; - head->next = NULL; + head->rb_root = RB_ROOT_CACHED; } #endif /* _LINUX_TIMERQUEUE_H */ diff --git a/lib/timerqueue.c b/lib/timerqueue.c index bc7e64df27df..c52710964593 100644 --- a/lib/timerqueue.c +++ b/lib/timerqueue.c @@ -26,9 +26,10 @@ */ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) { - struct rb_node **p = &head->head.rb_node; + struct rb_node **p = &head->rb_root.rb_root.rb_node; struct rb_node *parent = NULL; - struct timerqueue_node *ptr; + struct timerqueue_node *ptr; + bool leftmost = true; /* Make sure we don't add nodes that are already added */ WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); @@ -36,19 +37,17 @@ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) while (*p) { parent = *p; ptr = rb_entry(parent, struct timerqueue_node, node); - if (node->expires < ptr->expires) + if (node->expires < ptr->expires) { p = &(*p)->rb_left; - else + } else { p = &(*p)->rb_right; + leftmost = false; + } } rb_link_node(&node->node, parent, p); - rb_insert_color(&node->node, &head->head); + rb_insert_color_cached(&node->node, &head->rb_root, leftmost); - if (!head->next || node->expires < head->next->expires) { - head->next = node; - return true; - } - return false; + return leftmost; } EXPORT_SYMBOL_GPL(timerqueue_add); @@ -65,15 +64,10 @@ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) { WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); - /* update next pointer */ - if (head->next == node) { - struct rb_node *rbn = rb_next(&node->node); - - head->next = rb_entry_safe(rbn, struct timerqueue_node, node); - } - rb_erase(&node->node, &head->head); + rb_erase_cached(&node->node, &head->rb_root); RB_CLEAR_NODE(&node->node); - return head->next != NULL; + + return !RB_EMPTY_ROOT(&head->rb_root.rb_root); } EXPORT_SYMBOL_GPL(timerqueue_del); -- cgit v1.2.3-71-gd317 From 71d8e94dabee7fceac473d87445a03e848469a71 Mon Sep 17 00:00:00 2001 From: Moritz Fischer Date: Wed, 26 Jun 2019 17:33:09 -0700 Subject: fpga: altera-pr-ip: Make alt_pr_unregister function void Make alt_pr_unregister function void, since it always returns 0, and nothing would act on the value anyways. Signed-off-by: Moritz Fischer --- drivers/fpga/altera-pr-ip-core-plat.c | 4 +++- drivers/fpga/altera-pr-ip-core.c | 4 +--- include/linux/fpga/altera-pr-ip-core.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/fpga/altera-pr-ip-core-plat.c b/drivers/fpga/altera-pr-ip-core-plat.c index b293d83143f1..99b9cc0e70f0 100644 --- a/drivers/fpga/altera-pr-ip-core-plat.c +++ b/drivers/fpga/altera-pr-ip-core-plat.c @@ -32,7 +32,9 @@ static int alt_pr_platform_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; - return alt_pr_unregister(dev); + alt_pr_unregister(dev); + + return 0; } static const struct of_device_id alt_pr_of_match[] = { diff --git a/drivers/fpga/altera-pr-ip-core.c b/drivers/fpga/altera-pr-ip-core.c index a7a3bf0b5202..2cf25fd5e897 100644 --- a/drivers/fpga/altera-pr-ip-core.c +++ b/drivers/fpga/altera-pr-ip-core.c @@ -201,15 +201,13 @@ int alt_pr_register(struct device *dev, void __iomem *reg_base) } EXPORT_SYMBOL_GPL(alt_pr_register); -int alt_pr_unregister(struct device *dev) +void alt_pr_unregister(struct device *dev) { struct fpga_manager *mgr = dev_get_drvdata(dev); dev_dbg(dev, "%s\n", __func__); fpga_mgr_unregister(mgr); - - return 0; } EXPORT_SYMBOL_GPL(alt_pr_unregister); diff --git a/include/linux/fpga/altera-pr-ip-core.h b/include/linux/fpga/altera-pr-ip-core.h index 7d4664730d60..0b08ac20ab16 100644 --- a/include/linux/fpga/altera-pr-ip-core.h +++ b/include/linux/fpga/altera-pr-ip-core.h @@ -13,6 +13,6 @@ #include int alt_pr_register(struct device *dev, void __iomem *reg_base); -int alt_pr_unregister(struct device *dev); +void alt_pr_unregister(struct device *dev); #endif /* _ALT_PR_IP_CORE_H */ -- cgit v1.2.3-71-gd317 From 110f87a6a5f65e825852632b9557f463e65251d7 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 21 Jul 2019 23:49:08 +0900 Subject: usb: host: oxu210hp-hcd: remove include/linux/oxu210hp.h struct oxu210hp_platform_data is defined, but not used at all. $ git grep oxu210hp_platform_data include/linux/oxu210hp.h:struct oxu210hp_platform_data { include/linux/oxu210hp.h exists just for defining an unused structure, so it can go away. Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20190721144909.5295-1-yamada.masahiro@socionext.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/oxu210hp.h | 2 -- include/linux/oxu210hp.h | 8 -------- 2 files changed, 10 deletions(-) delete mode 100644 include/linux/oxu210hp.h (limited to 'include/linux') diff --git a/drivers/usb/host/oxu210hp.h b/drivers/usb/host/oxu210hp.h index 437044147862..67ebea4993b6 100644 --- a/drivers/usb/host/oxu210hp.h +++ b/drivers/usb/host/oxu210hp.h @@ -444,5 +444,3 @@ enum ehci_timer_action { TIMER_ASYNC_SHRINK, TIMER_ASYNC_OFF, }; - -#include diff --git a/include/linux/oxu210hp.h b/include/linux/oxu210hp.h deleted file mode 100644 index 94cd25165c08..000000000000 --- a/include/linux/oxu210hp.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* platform data for the OXU210HP HCD */ - -struct oxu210hp_platform_data { - unsigned int bus16:1; - unsigned int use_hcd_otg:1; - unsigned int use_hcd_sph:1; -}; -- cgit v1.2.3-71-gd317 From 615c164da0eb42cbfb1688cb429cc4d5039db5d8 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 5 Jul 2019 17:14:21 +0300 Subject: intel_th: msu: Introduce buffer interface Introduces a concept of external buffers, which is a mechanism for creating trace sinks that would receive trace data from MSC buffers and transfer it elsewhere. A external buffer can implement its own window allocation/deallocation if it has to. It must provide a callback that's used to notify it when a window fills up, so that it can then start a DMA transaction from that window 'elsewhere'. This window remains in a 'locked' state and won't be used for storing new trace data until the buffer 'unlocks' it with a provided API call, at which point the window can be used again for storing trace data. This relies on a functional "last block" interrupt, so not all versions of Trace Hub can use this feature, which does not reflect on existing users. Signed-off-by: Alexander Shishkin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20190705141425.19894-2-alexander.shishkin@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-bus-intel_th-devices-msc | 3 +- MAINTAINERS | 1 + drivers/hwtracing/intel_th/msu.c | 388 +++++++++++++++++++-- drivers/hwtracing/intel_th/msu.h | 20 +- include/linux/intel_th.h | 79 +++++ 5 files changed, 461 insertions(+), 30 deletions(-) create mode 100644 include/linux/intel_th.h (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc index f54ae244f3f1..456cb62b384c 100644 --- a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc +++ b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc @@ -12,7 +12,8 @@ Description: (RW) Configure MSC operating mode: - "single", for contiguous buffer mode (high-order alloc); - "multi", for multiblock mode; - "ExI", for DCI handler mode; - - "debug", for debug mode. + - "debug", for debug mode; + - any of the currently loaded buffer sinks. If operating mode changes, existing buffer is deallocated, provided there are no active users and tracing is not enabled, otherwise the write will fail. diff --git a/MAINTAINERS b/MAINTAINERS index 783569e3c4b4..c8c506b8423b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8360,6 +8360,7 @@ M: Alexander Shishkin S: Supported F: Documentation/trace/intel_th.rst F: drivers/hwtracing/intel_th/ +F: include/linux/intel_th.h INTEL(R) TRUSTED EXECUTION TECHNOLOGY (TXT) M: Ning Sun diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 8ab28e5fb366..08413e6a075f 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -17,21 +17,48 @@ #include #include #include +#include #include #ifdef CONFIG_X86 #include #endif +#include #include "intel_th.h" #include "msu.h" #define msc_dev(x) (&(x)->thdev->dev) +/* + * Lockout state transitions: + * READY -> INUSE -+-> LOCKED -+-> READY -> etc. + * \-----------/ + * WIN_READY: window can be used by HW + * WIN_INUSE: window is in use + * WIN_LOCKED: window is filled up and is being processed by the buffer + * handling code + * + * All state transitions happen automatically, except for the LOCKED->READY, + * which needs to be signalled by the buffer code by calling + * intel_th_msc_window_unlock(). + * + * When the interrupt handler has to switch to the next window, it checks + * whether it's READY, and if it is, it performs the switch and tracing + * continues. If it's LOCKED, it stops the trace. + */ +enum lockout_state { + WIN_READY = 0, + WIN_INUSE, + WIN_LOCKED +}; + /** * struct msc_window - multiblock mode window descriptor * @entry: window list linkage (msc::win_list) * @pgoff: page offset into the buffer that this window starts at + * @lockout: lockout state, see comment below + * @lo_lock: lockout state serialization * @nr_blocks: number of blocks (pages) in this window * @nr_segs: number of segments in this window (<= @nr_blocks) * @_sgt: array of block descriptors @@ -40,6 +67,8 @@ struct msc_window { struct list_head entry; unsigned long pgoff; + enum lockout_state lockout; + spinlock_t lo_lock; unsigned int nr_blocks; unsigned int nr_segs; struct msc *msc; @@ -77,6 +106,8 @@ struct msc_iter { * struct msc - MSC device representation * @reg_base: register window base address * @thdev: intel_th_device pointer + * @mbuf: MSU buffer, if assigned + * @mbuf_priv MSU buffer's private data, if @mbuf * @win_list: list of windows in multiblock mode * @single_sgt: single mode buffer * @cur_win: current window @@ -100,6 +131,10 @@ struct msc { void __iomem *msu_base; struct intel_th_device *thdev; + const struct msu_buffer *mbuf; + void *mbuf_priv; + + struct work_struct work; struct list_head win_list; struct sg_table single_sgt; struct msc_window *cur_win; @@ -126,6 +161,101 @@ struct msc { unsigned int index; }; +static LIST_HEAD(msu_buffer_list); +static struct mutex msu_buffer_mutex; + +/** + * struct msu_buffer_entry - internal MSU buffer bookkeeping + * @entry: link to msu_buffer_list + * @mbuf: MSU buffer object + * @owner: module that provides this MSU buffer + */ +struct msu_buffer_entry { + struct list_head entry; + const struct msu_buffer *mbuf; + struct module *owner; +}; + +static struct msu_buffer_entry *__msu_buffer_entry_find(const char *name) +{ + struct msu_buffer_entry *mbe; + + lockdep_assert_held(&msu_buffer_mutex); + + list_for_each_entry(mbe, &msu_buffer_list, entry) { + if (!strcmp(mbe->mbuf->name, name)) + return mbe; + } + + return NULL; +} + +static const struct msu_buffer * +msu_buffer_get(const char *name) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(name); + if (mbe && !try_module_get(mbe->owner)) + mbe = NULL; + mutex_unlock(&msu_buffer_mutex); + + return mbe ? mbe->mbuf : NULL; +} + +static void msu_buffer_put(const struct msu_buffer *mbuf) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(mbuf->name); + if (mbe) + module_put(mbe->owner); + mutex_unlock(&msu_buffer_mutex); +} + +int intel_th_msu_buffer_register(const struct msu_buffer *mbuf, + struct module *owner) +{ + struct msu_buffer_entry *mbe; + int ret = 0; + + mbe = kzalloc(sizeof(*mbe), GFP_KERNEL); + if (!mbe) + return -ENOMEM; + + mutex_lock(&msu_buffer_mutex); + if (__msu_buffer_entry_find(mbuf->name)) { + ret = -EEXIST; + kfree(mbe); + goto unlock; + } + + mbe->mbuf = mbuf; + mbe->owner = owner; + list_add_tail(&mbe->entry, &msu_buffer_list); +unlock: + mutex_unlock(&msu_buffer_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(intel_th_msu_buffer_register); + +void intel_th_msu_buffer_unregister(const struct msu_buffer *mbuf) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(mbuf->name); + if (mbe) { + list_del(&mbe->entry); + kfree(mbe); + } + mutex_unlock(&msu_buffer_mutex); +} +EXPORT_SYMBOL_GPL(intel_th_msu_buffer_unregister); + static inline bool msc_block_is_empty(struct msc_block_desc *bdesc) { /* header hasn't been written */ @@ -188,6 +318,25 @@ static struct msc_window *msc_next_window(struct msc_window *win) return list_next_entry(win, entry); } +static size_t msc_win_total_sz(struct msc_window *win) +{ + unsigned int blk; + size_t size = 0; + + for (blk = 0; blk < win->nr_segs; blk++) { + struct msc_block_desc *bdesc = msc_win_block(win, blk); + + if (msc_block_wrapped(bdesc)) + return win->nr_blocks << PAGE_SHIFT; + + size += msc_total_sz(bdesc); + if (msc_block_last_written(bdesc)) + break; + } + + return size; +} + /** * msc_find_window() - find a window matching a given sg_table * @msc: MSC device @@ -527,6 +676,9 @@ static int intel_th_msu_init(struct msc *msc) if (!msc->do_irq) return 0; + if (!msc->mbuf) + return 0; + mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL); mintctl |= msc->index ? M1BLIE : M0BLIE; iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); @@ -554,6 +706,44 @@ static void intel_th_msu_deinit(struct msc *msc) iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); } +static int msc_win_set_lockout(struct msc_window *win, + enum lockout_state expect, + enum lockout_state new) +{ + enum lockout_state old; + unsigned long flags; + int ret = 0; + + if (!win->msc->mbuf) + return 0; + + spin_lock_irqsave(&win->lo_lock, flags); + old = win->lockout; + + if (old != expect) { + ret = -EINVAL; + dev_warn_ratelimited(msc_dev(win->msc), + "expected lockout state %d, got %d\n", + expect, old); + goto unlock; + } + + win->lockout = new; + +unlock: + spin_unlock_irqrestore(&win->lo_lock, flags); + + if (ret) { + if (expect == WIN_READY && old == WIN_LOCKED) + return -EBUSY; + + /* from intel_th_msc_window_unlock(), don't warn if not locked */ + if (expect == WIN_LOCKED && old == new) + return 0; + } + + return ret; +} /** * msc_configure() - set up MSC hardware * @msc: the MSC device to configure @@ -571,8 +761,12 @@ static int msc_configure(struct msc *msc) if (msc->mode > MSC_MODE_MULTI) return -ENOTSUPP; - if (msc->mode == MSC_MODE_MULTI) + if (msc->mode == MSC_MODE_MULTI) { + if (msc_win_set_lockout(msc->cur_win, WIN_READY, WIN_INUSE)) + return -EBUSY; + msc_buffer_clear_hw_header(msc); + } reg = msc->base_addr >> PAGE_SHIFT; iowrite32(reg, msc->reg_base + REG_MSU_MSC0BAR); @@ -594,10 +788,14 @@ static int msc_configure(struct msc *msc) iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL); + intel_th_msu_init(msc); + msc->thdev->output.multiblock = msc->mode == MSC_MODE_MULTI; intel_th_trace_enable(msc->thdev); msc->enabled = 1; + if (msc->mbuf && msc->mbuf->activate) + msc->mbuf->activate(msc->mbuf_priv); return 0; } @@ -611,10 +809,17 @@ static int msc_configure(struct msc *msc) */ static void msc_disable(struct msc *msc) { + struct msc_window *win = msc->cur_win; u32 reg; lockdep_assert_held(&msc->buf_mutex); + if (msc->mode == MSC_MODE_MULTI) + msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED); + + if (msc->mbuf && msc->mbuf->deactivate) + msc->mbuf->deactivate(msc->mbuf_priv); + intel_th_msu_deinit(msc); intel_th_trace_disable(msc->thdev); if (msc->mode == MSC_MODE_SINGLE) { @@ -630,6 +835,11 @@ static void msc_disable(struct msc *msc) reg = ioread32(msc->reg_base + REG_MSU_MSC0CTL); reg &= ~MSC_EN; iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL); + + if (msc->mbuf && msc->mbuf->ready) + msc->mbuf->ready(msc->mbuf_priv, win->sgt, + msc_win_total_sz(win)); + msc->enabled = 0; iowrite32(0, msc->reg_base + REG_MSU_MSC0BAR); @@ -640,6 +850,10 @@ static void msc_disable(struct msc *msc) reg = ioread32(msc->reg_base + REG_MSU_MSC0STS); dev_dbg(msc_dev(msc), "MSCnSTS: %08x\n", reg); + + reg = ioread32(msc->reg_base + REG_MSU_MSUSTS); + reg &= msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST; + iowrite32(reg, msc->reg_base + REG_MSU_MSUSTS); } static int intel_th_msc_activate(struct intel_th_device *thdev) @@ -856,6 +1070,8 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) win->msc = msc; win->sgt = &win->_sgt; + win->lockout = WIN_READY; + spin_lock_init(&win->lo_lock); if (!list_empty(&msc->win_list)) { struct msc_window *prev = list_last_entry(&msc->win_list, @@ -865,8 +1081,13 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) win->pgoff = prev->pgoff + prev->nr_blocks; } - ret = __msc_buffer_win_alloc(win, nr_blocks); - if (ret < 0) + if (msc->mbuf && msc->mbuf->alloc_window) + ret = msc->mbuf->alloc_window(msc->mbuf_priv, &win->sgt, + nr_blocks << PAGE_SHIFT); + else + ret = __msc_buffer_win_alloc(win, nr_blocks); + + if (ret <= 0) goto err_nomem; msc_buffer_set_uc(win, ret); @@ -925,7 +1146,10 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win) msc_buffer_set_wb(win); - __msc_buffer_win_free(msc, win); + if (msc->mbuf && msc->mbuf->free_window) + msc->mbuf->free_window(msc->mbuf_priv, win->sgt); + else + __msc_buffer_win_free(msc, win); kfree(win); } @@ -1462,18 +1686,77 @@ static void msc_win_switch(struct msc *msc) intel_th_trace_switch(msc->thdev); } +/** + * intel_th_msc_window_unlock - put the window back in rotation + * @dev: MSC device to which this relates + * @sgt: buffer's sg_table for the window, does nothing if NULL + */ +void intel_th_msc_window_unlock(struct device *dev, struct sg_table *sgt) +{ + struct msc *msc = dev_get_drvdata(dev); + struct msc_window *win; + + if (!sgt) + return; + + win = msc_find_window(msc, sgt, false); + if (!win) + return; + + msc_win_set_lockout(win, WIN_LOCKED, WIN_READY); +} +EXPORT_SYMBOL_GPL(intel_th_msc_window_unlock); + +static void msc_work(struct work_struct *work) +{ + struct msc *msc = container_of(work, struct msc, work); + + intel_th_msc_deactivate(msc->thdev); +} + static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev) { struct msc *msc = dev_get_drvdata(&thdev->dev); u32 msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS); u32 mask = msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST; + struct msc_window *win, *next_win; - if (!(msusts & mask)) { - if (msc->enabled) - return IRQ_HANDLED; + if (!msc->do_irq || !msc->mbuf) return IRQ_NONE; + + msusts &= mask; + + if (!msusts) + return msc->enabled ? IRQ_HANDLED : IRQ_NONE; + + iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS); + + if (!msc->enabled) + return IRQ_NONE; + + /* grab the window before we do the switch */ + win = msc->cur_win; + if (!win) + return IRQ_HANDLED; + next_win = msc_next_window(win); + if (!next_win) + return IRQ_HANDLED; + + /* next window: if READY, proceed, if LOCKED, stop the trace */ + if (msc_win_set_lockout(next_win, WIN_READY, WIN_INUSE)) { + schedule_work(&msc->work); + return IRQ_HANDLED; } + /* current window: INUSE -> LOCKED */ + msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED); + + msc_win_switch(msc); + + if (msc->mbuf && msc->mbuf->ready) + msc->mbuf->ready(msc->mbuf_priv, win->sgt, + msc_win_total_sz(win)); + return IRQ_HANDLED; } @@ -1511,21 +1794,43 @@ wrap_store(struct device *dev, struct device_attribute *attr, const char *buf, static DEVICE_ATTR_RW(wrap); +static void msc_buffer_unassign(struct msc *msc) +{ + lockdep_assert_held(&msc->buf_mutex); + + if (!msc->mbuf) + return; + + msc->mbuf->unassign(msc->mbuf_priv); + msu_buffer_put(msc->mbuf); + msc->mbuf_priv = NULL; + msc->mbuf = NULL; +} + static ssize_t mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct msc *msc = dev_get_drvdata(dev); + const char *mode = msc_mode[msc->mode]; + ssize_t ret; + + mutex_lock(&msc->buf_mutex); + if (msc->mbuf) + mode = msc->mbuf->name; + ret = scnprintf(buf, PAGE_SIZE, "%s\n", mode); + mutex_unlock(&msc->buf_mutex); - return scnprintf(buf, PAGE_SIZE, "%s\n", msc_mode[msc->mode]); + return ret; } static ssize_t mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + const struct msu_buffer *mbuf = NULL; struct msc *msc = dev_get_drvdata(dev); size_t len = size; - char *cp; + char *cp, *mode; int i, ret; if (!capable(CAP_SYS_RAWIO)) @@ -1535,17 +1840,59 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf, if (cp) len = cp - buf; - for (i = 0; i < ARRAY_SIZE(msc_mode); i++) - if (!strncmp(msc_mode[i], buf, len)) - goto found; + mode = kstrndup(buf, len, GFP_KERNEL); + i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode); + if (i >= 0) + goto found; + + /* Buffer sinks only work with a usable IRQ */ + if (!msc->do_irq) { + kfree(mode); + return -EINVAL; + } + + mbuf = msu_buffer_get(mode); + kfree(mode); + if (mbuf) + goto found; return -EINVAL; found: mutex_lock(&msc->buf_mutex); + ret = 0; + + /* Same buffer: do nothing */ + if (mbuf && mbuf == msc->mbuf) { + /* put the extra reference we just got */ + msu_buffer_put(mbuf); + goto unlock; + } + ret = msc_buffer_unlocked_free_unless_used(msc); - if (!ret) - msc->mode = i; + if (ret) + goto unlock; + + if (mbuf) { + void *mbuf_priv = mbuf->assign(dev, &i); + + if (!mbuf_priv) { + ret = -ENOMEM; + goto unlock; + } + + msc_buffer_unassign(msc); + msc->mbuf_priv = mbuf_priv; + msc->mbuf = mbuf; + } else { + msc_buffer_unassign(msc); + } + + msc->mode = i; + +unlock: + if (ret && mbuf) + msu_buffer_put(mbuf); mutex_unlock(&msc->buf_mutex); return ret ? ret : size; @@ -1667,7 +2014,12 @@ win_switch_store(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&msc->buf_mutex); - if (msc->mode != MSC_MODE_MULTI) + /* + * Window switch can only happen in the "multi" mode. + * If a external buffer is engaged, they have the full + * control over window switching. + */ + if (msc->mode != MSC_MODE_MULTI || msc->mbuf) ret = -ENOTSUPP; else msc_win_switch(msc); @@ -1720,10 +2072,7 @@ static int intel_th_msc_probe(struct intel_th_device *thdev) msc->reg_base = base + msc->index * 0x100; msc->msu_base = base; - err = intel_th_msu_init(msc); - if (err) - return err; - + INIT_WORK(&msc->work, msc_work); err = intel_th_msc_init(msc); if (err) return err; @@ -1739,7 +2088,6 @@ static void intel_th_msc_remove(struct intel_th_device *thdev) int ret; intel_th_msc_deactivate(thdev); - intel_th_msu_deinit(msc); /* * Buffers should not be used at this point except if the diff --git a/drivers/hwtracing/intel_th/msu.h b/drivers/hwtracing/intel_th/msu.h index 574c16004cb2..3f527dd4d727 100644 --- a/drivers/hwtracing/intel_th/msu.h +++ b/drivers/hwtracing/intel_th/msu.h @@ -44,14 +44,6 @@ enum { #define M0BLIE BIT(16) #define M1BLIE BIT(24) -/* MSC operating modes (MSC_MODE) */ -enum { - MSC_MODE_SINGLE = 0, - MSC_MODE_MULTI, - MSC_MODE_EXI, - MSC_MODE_DEBUG, -}; - /* MSCnSTS bits */ #define MSCSTS_WRAPSTAT BIT(1) /* Wrap occurred */ #define MSCSTS_PLE BIT(2) /* Pipeline Empty */ @@ -93,6 +85,16 @@ static inline unsigned long msc_data_sz(struct msc_block_desc *bdesc) return bdesc->valid_dw * 4 - MSC_BDESC; } +static inline unsigned long msc_total_sz(struct msc_block_desc *bdesc) +{ + return bdesc->valid_dw * 4; +} + +static inline unsigned long msc_block_sz(struct msc_block_desc *bdesc) +{ + return bdesc->block_sz * 64 - MSC_BDESC; +} + static inline bool msc_block_wrapped(struct msc_block_desc *bdesc) { if (bdesc->hw_tag & (MSC_HW_TAG_BLOCKWRAP | MSC_HW_TAG_WINWRAP)) @@ -104,7 +106,7 @@ static inline bool msc_block_wrapped(struct msc_block_desc *bdesc) static inline bool msc_block_last_written(struct msc_block_desc *bdesc) { if ((bdesc->hw_tag & MSC_HW_TAG_ENDBIT) || - (msc_data_sz(bdesc) != DATA_IN_PAGE)) + (msc_data_sz(bdesc) != msc_block_sz(bdesc))) return true; return false; diff --git a/include/linux/intel_th.h b/include/linux/intel_th.h new file mode 100644 index 000000000000..9b7f4c22499c --- /dev/null +++ b/include/linux/intel_th.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel(R) Trace Hub data structures for implementing buffer sinks. + * + * Copyright (C) 2019 Intel Corporation. + */ + +#ifndef _INTEL_TH_H_ +#define _INTEL_TH_H_ + +#include + +/* MSC operating modes (MSC_MODE) */ +enum { + MSC_MODE_SINGLE = 0, + MSC_MODE_MULTI, + MSC_MODE_EXI, + MSC_MODE_DEBUG, +}; + +struct msu_buffer { + const char *name; + /* + * ->assign() called when buffer 'mode' is set to this driver + * (aka mode_store()) + * @device: struct device * of the msc + * @mode: allows the driver to set HW mode (see the enum above) + * Returns: a pointer to a private structure associated with this + * msc or NULL in case of error. This private structure + * will then be passed into all other callbacks. + */ + void *(*assign)(struct device *dev, int *mode); + /* ->unassign(): some other mode is selected, clean up */ + void (*unassign)(void *priv); + /* + * ->alloc_window(): allocate memory for the window of a given + * size + * @sgt: pointer to sg_table, can be overridden by the buffer + * driver, or kept intact + * Returns: number of sg table entries <= number of pages; + * 0 is treated as an allocation failure. + */ + int (*alloc_window)(void *priv, struct sg_table **sgt, + size_t size); + void (*free_window)(void *priv, struct sg_table *sgt); + /* ->activate(): trace has started */ + void (*activate)(void *priv); + /* ->deactivate(): trace is about to stop */ + void (*deactivate)(void *priv); + /* + * ->ready(): window @sgt is filled up to the last block OR + * tracing is stopped by the user; this window contains + * @bytes data. The window in question transitions into + * the "LOCKED" state, indicating that it can't be used + * by hardware. To clear this state and make the window + * available to the hardware again, call + * intel_th_msc_window_unlock(). + */ + int (*ready)(void *priv, struct sg_table *sgt, size_t bytes); +}; + +int intel_th_msu_buffer_register(const struct msu_buffer *mbuf, + struct module *owner); +void intel_th_msu_buffer_unregister(const struct msu_buffer *mbuf); +void intel_th_msc_window_unlock(struct device *dev, struct sg_table *sgt); + +#define module_intel_th_msu_buffer(__buffer) \ +static int __init __buffer##_init(void) \ +{ \ + return intel_th_msu_buffer_register(&(__buffer), THIS_MODULE); \ +} \ +module_init(__buffer##_init); \ +static void __exit __buffer##_exit(void) \ +{ \ + intel_th_msu_buffer_unregister(&(__buffer)); \ +} \ +module_exit(__buffer##_exit); + +#endif /* _INTEL_TH_H_ */ -- cgit v1.2.3-71-gd317 From 515db266a9dace92b0cbaed9a6044dd5304b8ca9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 16 Jul 2019 17:21:06 +0200 Subject: driver core: Remove device link creation limitation If device_link_add() is called for a consumer/supplier pair with an existing device link between them and the existing link's type is not in agreement with the flags passed to that function by its caller, NULL will be returned. That is seriously inconvenient, because it forces the callers of device_link_add() to worry about what others may or may not do even if that is not relevant to them for any other reasons. It turns out, however, that this limitation can be made go away relatively easily. The underlying observation is that if DL_FLAG_STATELESS has been passed to device_link_add() in flags for the given consumer/supplier pair at least once, calling either device_link_del() or device_link_remove() to release the link returned by it should work, but there are no other requirements associated with that flag. In turn, if at least one of the callers of device_link_add() for the given consumer/supplier pair has not passed DL_FLAG_STATELESS to it in flags, the driver core should track the status of the link and act on it as appropriate (ie. the link should be treated as "managed"). This means that DL_FLAG_STATELESS needs to be set for managed device links and it should be valid to call device_link_del() or device_link_remove() to drop references to them in certain sutiations. To allow that to happen, introduce a new (internal) device link flag called DL_FLAG_MANAGED and make device_link_add() set it automatically whenever DL_FLAG_STATELESS is not passed to it. Also make it take additional references to existing device links that were previously stateless (that is, with DL_FLAG_STATELESS set and DL_FLAG_MANAGED unset) and will need to be managed going forward and initialize their status (which has been DL_STATE_NONE so far). Accordingly, when a managed device link is dropped automatically by the driver core, make it clear DL_FLAG_MANAGED, reset the link's status back to DL_STATE_NONE and drop the reference to it associated with DL_FLAG_MANAGED instead of just deleting it right away (to allow it to stay around in case it still needs to be released explicitly by someone). With that, since setting DL_FLAG_STATELESS doesn't mean that the device link in question is not managed any more, replace all of the status-tracking checks against DL_FLAG_STATELESS with analogous checks against DL_FLAG_MANAGED and update the documentation to reflect these changes. While at it, make device_link_add() reject flags that it does not recognize, including DL_FLAG_MANAGED. Signed-off-by: Rafael J. Wysocki Reviewed-by: Saravana Kannan Tested-by: Marek Szyprowski Review-by: Saravana Kannan Link: https://lore.kernel.org/r/2305283.AStDPdUUnE@kreacher Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/device_link.rst | 4 +- drivers/base/core.c | 176 +++++++++++++++++-------------- drivers/base/power/runtime.c | 4 +- include/linux/device.h | 4 +- 4 files changed, 106 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst index ae1e3d0394b0..1b5020ec6517 100644 --- a/Documentation/driver-api/device_link.rst +++ b/Documentation/driver-api/device_link.rst @@ -78,8 +78,8 @@ typically deleted in its ``->remove`` callback for symmetry. That way, if the driver is compiled as a module, the device link is added on module load and orderly deleted on unload. The same restrictions that apply to device link addition (e.g. exclusion of a parallel suspend/resume transition) apply equally -to deletion. Device links with ``DL_FLAG_STATELESS`` unset (i.e. managed -device links) are deleted automatically by the driver core. +to deletion. Device links managed by the driver core are deleted automatically +by it. Several flags may be specified on device link addition, two of which have already been mentioned above: ``DL_FLAG_STATELESS`` to express that no diff --git a/drivers/base/core.c b/drivers/base/core.c index da84a73f2ba6..21cd08162219 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -124,6 +124,50 @@ static int device_is_dependent(struct device *dev, void *target) return ret; } +static void device_link_init_status(struct device_link *link, + struct device *consumer, + struct device *supplier) +{ + switch (supplier->links.status) { + case DL_DEV_PROBING: + switch (consumer->links.status) { + case DL_DEV_PROBING: + /* + * A consumer driver can create a link to a supplier + * that has not completed its probing yet as long as it + * knows that the supplier is already functional (for + * example, it has just acquired some resources from the + * supplier). + */ + link->status = DL_STATE_CONSUMER_PROBE; + break; + default: + link->status = DL_STATE_DORMANT; + break; + } + break; + case DL_DEV_DRIVER_BOUND: + switch (consumer->links.status) { + case DL_DEV_PROBING: + link->status = DL_STATE_CONSUMER_PROBE; + break; + case DL_DEV_DRIVER_BOUND: + link->status = DL_STATE_ACTIVE; + break; + default: + link->status = DL_STATE_AVAILABLE; + break; + } + break; + case DL_DEV_UNBINDING: + link->status = DL_STATE_SUPPLIER_UNBIND; + break; + default: + link->status = DL_STATE_DORMANT; + break; + } +} + static int device_reorder_to_tail(struct device *dev, void *not_used) { struct device_link *link; @@ -165,6 +209,10 @@ void device_pm_move_to_tail(struct device *dev) device_links_read_unlock(idx); } +#define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \ + DL_FLAG_AUTOREMOVE_SUPPLIER | \ + DL_FLAG_AUTOPROBE_CONSUMER) + /** * device_link_add - Create a link between two devices. * @consumer: Consumer end of the link. @@ -179,9 +227,9 @@ void device_pm_move_to_tail(struct device *dev) * of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be * ignored. * - * If DL_FLAG_STATELESS is set in @flags, the link is not going to be managed by - * the driver core and, in particular, the caller of this function is expected - * to drop the reference to the link acquired by it directly. + * If DL_FLAG_STATELESS is set in @flags, the caller of this function is + * expected to release the link returned by it directly with the help of either + * device_link_del() or device_link_remove(). * * If that flag is not set, however, the caller of this function is handing the * management of the link over to the driver core entirely and its return value @@ -201,9 +249,16 @@ void device_pm_move_to_tail(struct device *dev) * be used to request the driver core to automaticall probe for a consmer * driver after successfully binding a driver to the supplier device. * - * The combination of DL_FLAG_STATELESS and either DL_FLAG_AUTOREMOVE_CONSUMER - * or DL_FLAG_AUTOREMOVE_SUPPLIER set in @flags at the same time is invalid and - * will cause NULL to be returned upfront. + * The combination of DL_FLAG_STATELESS and one of DL_FLAG_AUTOREMOVE_CONSUMER, + * DL_FLAG_AUTOREMOVE_SUPPLIER, or DL_FLAG_AUTOPROBE_CONSUMER set in @flags at + * the same time is invalid and will cause NULL to be returned upfront. + * However, if a device link between the given @consumer and @supplier pair + * exists already when this function is called for them, the existing link will + * be returned regardless of its current type and status (the link's flags may + * be modified then). The caller of this function is then expected to treat + * the link as though it has just been created, so (in particular) if + * DL_FLAG_STATELESS was passed in @flags, the link needs to be released + * explicitly when not needed any more (as stated above). * * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending @@ -220,10 +275,8 @@ struct device_link *device_link_add(struct device *consumer, struct device_link *link; if (!consumer || !supplier || - (flags & DL_FLAG_STATELESS && - flags & (DL_FLAG_AUTOREMOVE_CONSUMER | - DL_FLAG_AUTOREMOVE_SUPPLIER | - DL_FLAG_AUTOPROBE_CONSUMER)) || + (flags & ~(DL_FLAG_STATELESS | DL_MANAGED_LINK_FLAGS)) || + (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) || (flags & DL_FLAG_AUTOPROBE_CONSUMER && flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) @@ -236,6 +289,9 @@ struct device_link *device_link_add(struct device *consumer, } } + if (!(flags & DL_FLAG_STATELESS)) + flags |= DL_FLAG_MANAGED; + device_links_write_lock(); device_pm_lock(); @@ -262,15 +318,6 @@ struct device_link *device_link_add(struct device *consumer, if (link->consumer != consumer) continue; - /* - * Don't return a stateless link if the caller wants a stateful - * one and vice versa. - */ - if (WARN_ON((flags & DL_FLAG_STATELESS) != (link->flags & DL_FLAG_STATELESS))) { - link = NULL; - goto out; - } - if (flags & DL_FLAG_PM_RUNTIME) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) { pm_runtime_new_link(consumer); @@ -281,6 +328,7 @@ struct device_link *device_link_add(struct device *consumer, } if (flags & DL_FLAG_STATELESS) { + link->flags |= DL_FLAG_STATELESS; kref_get(&link->kref); goto out; } @@ -299,6 +347,11 @@ struct device_link *device_link_add(struct device *consumer, link->flags &= ~(DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER); } + if (!(link->flags & DL_FLAG_MANAGED)) { + kref_get(&link->kref); + link->flags |= DL_FLAG_MANAGED; + device_link_init_status(link, consumer, supplier); + } goto out; } @@ -325,48 +378,10 @@ struct device_link *device_link_add(struct device *consumer, kref_init(&link->kref); /* Determine the initial link state. */ - if (flags & DL_FLAG_STATELESS) { + if (flags & DL_FLAG_STATELESS) link->status = DL_STATE_NONE; - } else { - switch (supplier->links.status) { - case DL_DEV_PROBING: - switch (consumer->links.status) { - case DL_DEV_PROBING: - /* - * A consumer driver can create a link to a - * supplier that has not completed its probing - * yet as long as it knows that the supplier is - * already functional (for example, it has just - * acquired some resources from the supplier). - */ - link->status = DL_STATE_CONSUMER_PROBE; - break; - default: - link->status = DL_STATE_DORMANT; - break; - } - break; - case DL_DEV_DRIVER_BOUND: - switch (consumer->links.status) { - case DL_DEV_PROBING: - link->status = DL_STATE_CONSUMER_PROBE; - break; - case DL_DEV_DRIVER_BOUND: - link->status = DL_STATE_ACTIVE; - break; - default: - link->status = DL_STATE_AVAILABLE; - break; - } - break; - case DL_DEV_UNBINDING: - link->status = DL_STATE_SUPPLIER_UNBIND; - break; - default: - link->status = DL_STATE_DORMANT; - break; - } - } + else + device_link_init_status(link, consumer, supplier); /* * Some callers expect the link creation during consumer driver probe to @@ -528,7 +543,7 @@ static void device_links_missing_supplier(struct device *dev) * mark the link as "consumer probe in progress" to make the supplier removal * wait for us to complete (or bad things may happen). * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links without the DL_FLAG_MANAGED flag set are ignored. */ int device_links_check_suppliers(struct device *dev) { @@ -538,7 +553,7 @@ int device_links_check_suppliers(struct device *dev) device_links_write_lock(); list_for_each_entry(link, &dev->links.suppliers, c_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_AVAILABLE) { @@ -563,7 +578,7 @@ int device_links_check_suppliers(struct device *dev) * * Also change the status of @dev's links to suppliers to "active". * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_bound(struct device *dev) { @@ -572,7 +587,7 @@ void device_links_driver_bound(struct device *dev) device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; /* @@ -593,7 +608,7 @@ void device_links_driver_bound(struct device *dev) } list_for_each_entry(link, &dev->links.suppliers, c_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; WARN_ON(link->status != DL_STATE_CONSUMER_PROBE); @@ -605,6 +620,13 @@ void device_links_driver_bound(struct device *dev) device_links_write_unlock(); } +static void device_link_drop_managed(struct device_link *link) +{ + link->flags &= ~DL_FLAG_MANAGED; + WRITE_ONCE(link->status, DL_STATE_NONE); + kref_put(&link->kref, __device_link_del); +} + /** * __device_links_no_driver - Update links of a device without a driver. * @dev: Device without a drvier. @@ -615,18 +637,18 @@ void device_links_driver_bound(struct device *dev) * unless they already are in the "supplier unbind in progress" state in which * case they need not be updated. * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links without the DL_FLAG_MANAGED flag set are ignored. */ static void __device_links_no_driver(struct device *dev) { struct device_link *link, *ln; list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) - __device_link_del(&link->kref); + device_link_drop_managed(link); else if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) WRITE_ONCE(link->status, DL_STATE_AVAILABLE); @@ -643,7 +665,7 @@ static void __device_links_no_driver(struct device *dev) * %__device_links_no_driver() to update links to suppliers for it as * appropriate. * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_no_driver(struct device *dev) { @@ -652,7 +674,7 @@ void device_links_no_driver(struct device *dev) device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; /* @@ -680,7 +702,7 @@ void device_links_no_driver(struct device *dev) * invoke %__device_links_no_driver() to update links to suppliers for it as * appropriate. * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_cleanup(struct device *dev) { @@ -689,7 +711,7 @@ void device_links_driver_cleanup(struct device *dev) device_links_write_lock(); list_for_each_entry_safe(link, ln, &dev->links.consumers, s_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER); @@ -702,7 +724,7 @@ void device_links_driver_cleanup(struct device *dev) */ if (link->status == DL_STATE_SUPPLIER_UNBIND && link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) - __device_link_del(&link->kref); + device_link_drop_managed(link); WRITE_ONCE(link->status, DL_STATE_DORMANT); } @@ -724,7 +746,7 @@ void device_links_driver_cleanup(struct device *dev) * * Return 'false' if there are no probing or active consumers. * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links without the DL_FLAG_MANAGED flag set are ignored. */ bool device_links_busy(struct device *dev) { @@ -734,7 +756,7 @@ bool device_links_busy(struct device *dev) device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status == DL_STATE_CONSUMER_PROBE @@ -764,7 +786,7 @@ bool device_links_busy(struct device *dev) * driver to unbind and start over (the consumer will not re-probe as we have * changed the state of the link already). * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_unbind_consumers(struct device *dev) { @@ -776,7 +798,7 @@ void device_links_unbind_consumers(struct device *dev) list_for_each_entry(link, &dev->links.consumers, s_node) { enum device_link_state status; - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; status = link->status; diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index b75335508d2c..45a8fbe6987a 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1624,7 +1624,7 @@ void pm_runtime_remove(struct device *dev) * runtime PM references to the device, drop the usage counter of the device * (as many times as needed). * - * Links with the DL_FLAG_STATELESS flag set are ignored. + * Links with the DL_FLAG_MANAGED flag unset are ignored. * * Since the device is guaranteed to be runtime-active at the point this is * called, nothing else needs to be done here. @@ -1641,7 +1641,7 @@ void pm_runtime_clean_up_links(struct device *dev) idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.consumers, s_node) { - if (link->flags & DL_FLAG_STATELESS) + if (!(link->flags & DL_FLAG_MANAGED)) continue; while (refcount_dec_not_one(&link->rpm_active)) diff --git a/include/linux/device.h b/include/linux/device.h index c330b75c6c57..c1c489921e4c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -833,12 +833,13 @@ enum device_link_state { /* * Device link flags. * - * STATELESS: The core won't track the presence of supplier/consumer drivers. + * STATELESS: The core will not remove this link automatically. * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. + * MANAGED: The core tracks presence of supplier/consumer drivers (internal). */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) @@ -846,6 +847,7 @@ enum device_link_state { #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) +#define DL_FLAG_MANAGED BIT(6) /** * struct device_link - Device link representation. -- cgit v1.2.3-71-gd317 From 364f6afc4f5537b79cf454eb35cae92920676075 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 22 Jul 2019 11:24:40 -0700 Subject: locking/lockdep: Make it clear that what lock_class::key points at is not modified This patch does not change the behavior of the lockdep code. Signed-off-by: Bart Van Assche Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Link: https://lkml.kernel.org/r/20190722182443.216015-2-bvanassche@acm.org Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 2 +- kernel/locking/lockdep.c | 2 +- kernel/locking/lockdep_internals.h | 3 ++- kernel/locking/lockdep_proc.c | 2 +- 4 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 0b0d7259276d..cdb3c2f06092 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -97,7 +97,7 @@ struct lock_class { */ struct list_head locks_after, locks_before; - struct lockdep_subclass_key *key; + const struct lockdep_subclass_key *key; unsigned int subclass; unsigned int dep_gen_id; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4861cf8e274b..af6627866191 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -511,7 +511,7 @@ static const char *usage_str[] = }; #endif -const char * __get_key_name(struct lockdep_subclass_key *key, char *str) +const char *__get_key_name(const struct lockdep_subclass_key *key, char *str) { return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str); } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index cc83568d5012..2e518369add4 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -116,7 +116,8 @@ extern struct lock_chain lock_chains[]; extern void get_usage_chars(struct lock_class *class, char usage[LOCK_USAGE_CHARS]); -extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str); +extern const char *__get_key_name(const struct lockdep_subclass_key *key, + char *str); struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index bda006f8a88b..ed9842425cac 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -399,7 +399,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt) static void seq_stats(struct seq_file *m, struct lock_stat_data *data) { - struct lockdep_subclass_key *ckey; + const struct lockdep_subclass_key *ckey; struct lock_class_stats *stats; struct lock_class *class; const char *cname; -- cgit v1.2.3-71-gd317 From a2970421640bd9b6a78f2685d7750a791abdfd4e Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 22 Jul 2019 11:24:41 -0700 Subject: stacktrace: Constify 'entries' arguments Make it clear to humans and to the compiler that the stack trace ('entries') arguments are not modified. Signed-off-by: Bart Van Assche Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Link: https://lkml.kernel.org/r/20190722182443.216015-3-bvanassche@acm.org Signed-off-by: Ingo Molnar --- include/linux/stacktrace.h | 4 ++-- kernel/stacktrace.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index f0cfd12cb45e..83bd8cb475d7 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -9,9 +9,9 @@ struct task_struct; struct pt_regs; #ifdef CONFIG_STACKTRACE -void stack_trace_print(unsigned long *trace, unsigned int nr_entries, +void stack_trace_print(const unsigned long *trace, unsigned int nr_entries, int spaces); -int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, +int stack_trace_snprint(char *buf, size_t size, const unsigned long *entries, unsigned int nr_entries, int spaces); unsigned int stack_trace_save(unsigned long *store, unsigned int size, unsigned int skipnr); diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index f5440abb7532..6d1f68b7e528 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -20,7 +20,7 @@ * @nr_entries: Number of entries in the storage array * @spaces: Number of leading spaces to print */ -void stack_trace_print(unsigned long *entries, unsigned int nr_entries, +void stack_trace_print(const unsigned long *entries, unsigned int nr_entries, int spaces) { unsigned int i; @@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(stack_trace_print); * * Return: Number of bytes printed. */ -int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, +int stack_trace_snprint(char *buf, size_t size, const unsigned long *entries, unsigned int nr_entries, int spaces) { unsigned int generated, i, total = 0; -- cgit v1.2.3-71-gd317 From 12593b7467f9130b64a6d4b6a26ed4ec217b6784 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 22 Jul 2019 11:24:42 -0700 Subject: locking/lockdep: Reduce space occupied by stack traces Although commit 669de8bda87b ("kernel/workqueue: Use dynamic lockdep keys for workqueues") unregisters dynamic lockdep keys when a workqueue is destroyed, a side effect of that commit is that all stack traces associated with the lockdep key are leaked when a workqueue is destroyed. Fix this by storing each unique stack trace once. Other changes in this patch are: - Use NULL instead of { .nr_entries = 0 } to represent 'no trace'. - Store a pointer to a stack trace in struct lock_class and struct lock_list instead of storing 'nr_entries' and 'offset'. This patch avoids that the following program triggers the "BUG: MAX_STACK_TRACE_ENTRIES too low!" complaint: #include #include int main() { for (;;) { int fd = open("/dev/infiniband/rdma_cm", O_RDWR); close(fd); } } Suggested-by: Peter Zijlstra Reported-by: Eric Biggers Signed-off-by: Bart Van Assche Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Cc: Yuyang Du Link: https://lkml.kernel.org/r/20190722182443.216015-4-bvanassche@acm.org Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 9 +-- kernel/locking/lockdep.c | 128 ++++++++++++++++++++++++++----------- kernel/locking/lockdep_internals.h | 2 + 3 files changed, 95 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index cdb3c2f06092..b8a835fd611b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -66,10 +66,7 @@ struct lock_class_key { extern struct lock_class_key __lockdep_no_validate__; -struct lock_trace { - unsigned int nr_entries; - unsigned int offset; -}; +struct lock_trace; #define LOCKSTAT_POINTS 4 @@ -105,7 +102,7 @@ struct lock_class { * IRQ/softirq usage tracking bits: */ unsigned long usage_mask; - struct lock_trace usage_traces[XXX_LOCK_USAGE_STATES]; + const struct lock_trace *usage_traces[XXX_LOCK_USAGE_STATES]; /* * Generation counter, when doing certain classes of graph walking, @@ -193,7 +190,7 @@ struct lock_list { struct list_head entry; struct lock_class *class; struct lock_class *links_to; - struct lock_trace trace; + const struct lock_trace *trace; int distance; /* diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index af6627866191..1a96869cb2f0 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -449,33 +449,72 @@ static void print_lockdep_off(const char *bug_msg) unsigned long nr_stack_trace_entries; #ifdef CONFIG_PROVE_LOCKING +/** + * struct lock_trace - single stack backtrace + * @hash_entry: Entry in a stack_trace_hash[] list. + * @hash: jhash() of @entries. + * @nr_entries: Number of entries in @entries. + * @entries: Actual stack backtrace. + */ +struct lock_trace { + struct hlist_node hash_entry; + u32 hash; + u32 nr_entries; + unsigned long entries[0] __aligned(sizeof(unsigned long)); +}; +#define LOCK_TRACE_SIZE_IN_LONGS \ + (sizeof(struct lock_trace) / sizeof(unsigned long)) /* - * Stack-trace: tightly packed array of stack backtrace - * addresses. Protected by the graph_lock. + * Stack-trace: sequence of lock_trace structures. Protected by the graph_lock. */ static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES]; +static struct hlist_head stack_trace_hash[STACK_TRACE_HASH_SIZE]; + +static bool traces_identical(struct lock_trace *t1, struct lock_trace *t2) +{ + return t1->hash == t2->hash && t1->nr_entries == t2->nr_entries && + memcmp(t1->entries, t2->entries, + t1->nr_entries * sizeof(t1->entries[0])) == 0; +} -static int save_trace(struct lock_trace *trace) +static struct lock_trace *save_trace(void) { - unsigned long *entries = stack_trace + nr_stack_trace_entries; + struct lock_trace *trace, *t2; + struct hlist_head *hash_head; + u32 hash; unsigned int max_entries; - trace->offset = nr_stack_trace_entries; - max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; - trace->nr_entries = stack_trace_save(entries, max_entries, 3); - nr_stack_trace_entries += trace->nr_entries; + BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE); + BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES); + + trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries); + max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries - + LOCK_TRACE_SIZE_IN_LONGS; + trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); - if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) { + if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES - + LOCK_TRACE_SIZE_IN_LONGS - 1) { if (!debug_locks_off_graph_unlock()) - return 0; + return NULL; print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!"); dump_stack(); - return 0; + return NULL; } - return 1; + hash = jhash(trace->entries, trace->nr_entries * + sizeof(trace->entries[0]), 0); + trace->hash = hash; + hash_head = stack_trace_hash + (hash & (STACK_TRACE_HASH_SIZE - 1)); + hlist_for_each_entry(t2, hash_head, hash_entry) { + if (traces_identical(trace, t2)) + return t2; + } + nr_stack_trace_entries += LOCK_TRACE_SIZE_IN_LONGS + trace->nr_entries; + hlist_add_head(&trace->hash_entry, hash_head); + + return trace; } #endif @@ -1235,7 +1274,7 @@ static struct lock_list *alloc_list_entry(void) static int add_lock_to_list(struct lock_class *this, struct lock_class *links_to, struct list_head *head, unsigned long ip, int distance, - struct lock_trace *trace) + const struct lock_trace *trace) { struct lock_list *entry; /* @@ -1249,7 +1288,7 @@ static int add_lock_to_list(struct lock_class *this, entry->class = this; entry->links_to = links_to; entry->distance = distance; - entry->trace = *trace; + entry->trace = trace; /* * Both allocation and removal are done under the graph lock; but * iteration is under RCU-sched; see look_up_lock_class() and @@ -1470,11 +1509,10 @@ static inline int __bfs_backwards(struct lock_list *src_entry, } -static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +static void print_lock_trace(const struct lock_trace *trace, + unsigned int spaces) { - unsigned long *entries = stack_trace + trace->offset; - - stack_trace_print(entries, trace->nr_entries, spaces); + stack_trace_print(trace->entries, trace->nr_entries, spaces); } /* @@ -1489,7 +1527,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) printk("\n-> #%u", depth); print_lock_name(target->class); printk(KERN_CONT ":\n"); - print_lock_trace(&target->trace, 6); + print_lock_trace(target->trace, 6); } static void @@ -1592,7 +1630,8 @@ static noinline void print_circular_bug(struct lock_list *this, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return; - if (!save_trace(&this->trace)) + this->trace = save_trace(); + if (!this->trace) return; depth = get_lock_depth(target); @@ -1715,7 +1754,7 @@ check_path(struct lock_class *target, struct lock_list *src_entry, */ static noinline int check_noncircular(struct held_lock *src, struct held_lock *target, - struct lock_trace *trace) + struct lock_trace **const trace) { int ret; struct lock_list *uninitialized_var(target_entry); @@ -1729,13 +1768,13 @@ check_noncircular(struct held_lock *src, struct held_lock *target, ret = check_path(hlock_class(target), &src_entry, &target_entry); if (unlikely(!ret)) { - if (!trace->nr_entries) { + if (!*trace) { /* * If save_trace fails here, the printing might * trigger a WARN but because of the !nr_entries it * should not do bad things. */ - save_trace(trace); + *trace = save_trace(); } print_circular_bug(&src_entry, target_entry, src, target); @@ -1859,7 +1898,7 @@ static void print_lock_class_header(struct lock_class *class, int depth) len += printk("%*s %s", depth, "", usage_str[bit]); len += printk(KERN_CONT " at:\n"); - print_lock_trace(class->usage_traces + bit, len); + print_lock_trace(class->usage_traces[bit], len); } } printk("%*s }\n", depth, ""); @@ -1884,7 +1923,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf, do { print_lock_class_header(entry->class, depth); printk("%*s ... acquired at:\n", depth, ""); - print_lock_trace(&entry->trace, 2); + print_lock_trace(entry->trace, 2); printk("\n"); if (depth == 0 && (entry != root)) { @@ -1995,14 +2034,14 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock_name(backwards_entry->class); pr_warn("\n... which became %s-irq-safe at:\n", irqclass); - print_lock_trace(backwards_entry->class->usage_traces + bit1, 1); + print_lock_trace(backwards_entry->class->usage_traces[bit1], 1); pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass); print_lock_name(forwards_entry->class); pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass); pr_warn("..."); - print_lock_trace(forwards_entry->class->usage_traces + bit2, 1); + print_lock_trace(forwards_entry->class->usage_traces[bit2], 1); pr_warn("\nother info that might help us debug this:\n\n"); print_irq_lock_scenario(backwards_entry, forwards_entry, @@ -2011,13 +2050,15 @@ print_bad_irq_dependency(struct task_struct *curr, lockdep_print_held_locks(curr); pr_warn("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); - if (!save_trace(&prev_root->trace)) + prev_root->trace = save_trace(); + if (!prev_root->trace) return; print_shortest_lock_dependencies(backwards_entry, prev_root); pr_warn("\nthe dependencies between the lock to be acquired"); pr_warn(" and %s-irq-unsafe lock:\n", irqclass); - if (!save_trace(&next_root->trace)) + next_root->trace = save_trace(); + if (!next_root->trace) return; print_shortest_lock_dependencies(forwards_entry, next_root); @@ -2369,7 +2410,8 @@ check_deadlock(struct task_struct *curr, struct held_lock *next) */ static int check_prev_add(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, int distance, struct lock_trace *trace) + struct held_lock *next, int distance, + struct lock_trace **const trace) { struct lock_list *entry; int ret; @@ -2444,8 +2486,11 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return ret; #endif - if (!trace->nr_entries && !save_trace(trace)) - return 0; + if (!*trace) { + *trace = save_trace(); + if (!*trace) + return 0; + } /* * Ok, all validations passed, add the new lock @@ -2453,14 +2498,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, */ ret = add_lock_to_list(hlock_class(next), hlock_class(prev), &hlock_class(prev)->locks_after, - next->acquire_ip, distance, trace); + next->acquire_ip, distance, *trace); if (!ret) return 0; ret = add_lock_to_list(hlock_class(prev), hlock_class(next), &hlock_class(next)->locks_before, - next->acquire_ip, distance, trace); + next->acquire_ip, distance, *trace); if (!ret) return 0; @@ -2476,7 +2521,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, static int check_prevs_add(struct task_struct *curr, struct held_lock *next) { - struct lock_trace trace = { .nr_entries = 0 }; + struct lock_trace *trace = NULL; int depth = curr->lockdep_depth; struct held_lock *hlock; @@ -3015,7 +3060,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, print_lock(this); pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]); - print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1); + print_lock_trace(hlock_class(this)->usage_traces[prev_bit], 1); print_irqtrace_events(curr); pr_warn("\nother info that might help us debug this:\n"); @@ -3096,7 +3141,8 @@ print_irq_inversion_bug(struct task_struct *curr, lockdep_print_held_locks(curr); pr_warn("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); - if (!save_trace(&root->trace)) + root->trace = save_trace(); + if (!root->trace) return; print_shortest_lock_dependencies(other, root); @@ -3580,7 +3626,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, hlock_class(this)->usage_mask |= new_mask; - if (!save_trace(hlock_class(this)->usage_traces + new_bit)) + if (!(hlock_class(this)->usage_traces[new_bit] = save_trace())) return 0; switch (new_bit) { @@ -5157,6 +5203,12 @@ void __init lockdep_init(void) ) / 1024 ); +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) + printk(" memory used for stack traces: %zu kB\n", + (sizeof(stack_trace) + sizeof(stack_trace_hash)) / 1024 + ); +#endif + printk(" per task-struct memory footprint: %zu bytes\n", sizeof(((struct task_struct *)NULL)->held_locks)); } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 2e518369add4..93a008bf77db 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -92,6 +92,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define MAX_LOCKDEP_ENTRIES 16384UL #define MAX_LOCKDEP_CHAINS_BITS 15 #define MAX_STACK_TRACE_ENTRIES 262144UL +#define STACK_TRACE_HASH_SIZE 8192 #else #define MAX_LOCKDEP_ENTRIES 32768UL @@ -102,6 +103,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = * addresses. Protected by the hash_lock. */ #define MAX_STACK_TRACE_ENTRIES 524288UL +#define STACK_TRACE_HASH_SIZE 16384 #endif #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) -- cgit v1.2.3-71-gd317 From e797bda3fd29137f6c151dfa10ea6a61c17895ce Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 22 Jul 2019 20:47:16 +0200 Subject: smp/hotplug: Track booted once CPUs in a cpumask The booted once information which is required to deal with the MCE broadcast issue on X86 correctly is stored in the per cpu hotplug state, which is perfectly fine for the intended purpose. X86 needs that information for supporting NMI broadcasting via shortcuts, but retrieving it from per cpu data is cumbersome. Move it to a cpumask so the information can be checked against the cpu_present_mask quickly. No functional change intended. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20190722105219.818822855@linutronix.de --- include/linux/cpumask.h | 2 ++ kernel/cpu.c | 11 +++++++---- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 21755471b1c3..693124900f0a 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -115,6 +115,8 @@ extern struct cpumask __cpu_active_mask; #define cpu_active(cpu) ((cpu) == 0) #endif +extern cpumask_t cpus_booted_once_mask; + static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS diff --git a/kernel/cpu.c b/kernel/cpu.c index e84c0873559e..05778e32674a 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -62,7 +62,6 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; - bool booted_once; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; @@ -76,6 +75,10 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; +#ifdef CONFIG_SMP +cpumask_t cpus_booted_once_mask; +#endif + #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); @@ -433,7 +436,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu) * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ - return !per_cpu(cpuhp_state, cpu).booted_once; + return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } #else static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } @@ -1066,7 +1069,7 @@ void notify_cpu_starting(unsigned int cpu) int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ - st->booted_once = true; + cpumask_set_cpu(cpu, &cpus_booted_once_mask); while (st->state < target) { st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); @@ -2334,7 +2337,7 @@ void __init boot_cpu_init(void) void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP - this_cpu_write(cpuhp_state.booted_once, true); + cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } -- cgit v1.2.3-71-gd317 From b9fa6442f7043e2cdd247905d4f3b80f2e9605cb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 22 Jul 2019 20:47:24 +0200 Subject: cpumask: Implement cpumask_or_equal() The IPI code of x86 needs to evaluate whether the target cpumask is equal to the cpu_online_mask or equal except for the calling CPU. To replace the current implementation which requires the usage of a temporary cpumask, which might involve allocations, add a new function which compares a cpumask to the result of two other cpumasks which are or'ed together before comparison. This allows to make the required decision in one go and the calling code then can check for the calling CPU being set in the target mask with cpumask_test_cpu(). Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20190722105220.585449120@linutronix.de --- include/linux/bitmap.h | 23 +++++++++++++++++++++++ include/linux/cpumask.h | 14 ++++++++++++++ lib/bitmap.c | 20 ++++++++++++++++++++ 3 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index f58e97446abc..90528f12bdfa 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -120,6 +120,10 @@ extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); +extern bool __pure __bitmap_or_equal(const unsigned long *src1, + const unsigned long *src2, + const unsigned long *src3, + unsigned int nbits); extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits); extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, @@ -321,6 +325,25 @@ static inline int bitmap_equal(const unsigned long *src1, return __bitmap_equal(src1, src2, nbits); } +/** + * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third + * @src1: Pointer to bitmap 1 + * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 + * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 + * + * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise + */ +static inline bool bitmap_or_equal(const unsigned long *src1, + const unsigned long *src2, + const unsigned long *src3, + unsigned int nbits) +{ + if (!small_const_nbits(nbits)) + return __bitmap_or_equal(src1, src2, src3, nbits); + + return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); +} + static inline int bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 693124900f0a..0c7db5efe66c 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -475,6 +475,20 @@ static inline bool cpumask_equal(const struct cpumask *src1p, nr_cpumask_bits); } +/** + * cpumask_or_equal - *src1p | *src2p == *src3p + * @src1p: the first input + * @src2p: the second input + * @src3p: the third input + */ +static inline bool cpumask_or_equal(const struct cpumask *src1p, + const struct cpumask *src2p, + const struct cpumask *src3p) +{ + return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), + cpumask_bits(src3p), nr_cpumask_bits); +} + /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input diff --git a/lib/bitmap.c b/lib/bitmap.c index bbe2589e8497..f9e834841e94 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -59,6 +59,26 @@ int __bitmap_equal(const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_equal); +bool __bitmap_or_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, + const unsigned long *bitmap3, + unsigned int bits) +{ + unsigned int k, lim = bits / BITS_PER_LONG; + unsigned long tmp; + + for (k = 0; k < lim; ++k) { + if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) + return false; + } + + if (!(bits % BITS_PER_LONG)) + return true; + + tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; + return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; +} + void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); -- cgit v1.2.3-71-gd317 From 0c09ab96fc820109d63097a2adcbbd20836b655f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 9 Jul 2019 16:23:40 +0200 Subject: cpu/hotplug: Cache number of online CPUs Re-evaluating the bitmap wheight of the online cpus bitmap in every invocation of num_online_cpus() over and over is a pretty useless exercise. Especially when num_online_cpus() is used in code paths like the IPI delivery of x86 or the membarrier code. Cache the number of online CPUs in the core and just return the cached variable. The accessor function provides only a snapshot when used without protection against concurrent CPU hotplug. The storage needs to use an atomic_t because the kexec and reboot code (ab)use set_cpu_online() in their 'shutdown' handlers without any form of serialization as pointed out by Mathieu. Regular CPU hotplug usage is properly serialized. Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1907091622590.1634@nanos.tec.linutronix.de --- include/linux/cpumask.h | 25 ++++++++++++++++--------- kernel/cpu.c | 24 ++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 0c7db5efe66c..b5a5a1ed9efd 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -10,6 +10,7 @@ #include #include #include +#include #include /* Don't assign or return these: may not be this big! */ @@ -95,8 +96,21 @@ extern struct cpumask __cpu_active_mask; #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) +extern atomic_t __num_online_cpus; + #if NR_CPUS > 1 -#define num_online_cpus() cpumask_weight(cpu_online_mask) +/** + * num_online_cpus() - Read the number of online CPUs + * + * Despite the fact that __num_online_cpus is of type atomic_t, this + * interface gives only a momentary snapshot and is not protected against + * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held + * region. + */ +static inline unsigned int num_online_cpus(void) +{ + return atomic_read(&__num_online_cpus); +} #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) @@ -821,14 +835,7 @@ set_cpu_present(unsigned int cpu, bool present) cpumask_clear_cpu(cpu, &__cpu_present_mask); } -static inline void -set_cpu_online(unsigned int cpu, bool online) -{ - if (online) - cpumask_set_cpu(cpu, &__cpu_online_mask); - else - cpumask_clear_cpu(cpu, &__cpu_online_mask); -} +void set_cpu_online(unsigned int cpu, bool online); static inline void set_cpu_active(unsigned int cpu, bool active) diff --git a/kernel/cpu.c b/kernel/cpu.c index 05778e32674a..e1967e9eddc2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2298,6 +2298,9 @@ EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); +atomic_t __num_online_cpus __read_mostly; +EXPORT_SYMBOL(__num_online_cpus); + void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); @@ -2313,6 +2316,27 @@ void init_cpu_online(const struct cpumask *src) cpumask_copy(&__cpu_online_mask, src); } +void set_cpu_online(unsigned int cpu, bool online) +{ + /* + * atomic_inc/dec() is required to handle the horrid abuse of this + * function by the reboot and kexec code which invoke it from + * IPI/NMI broadcasts when shutting down CPUs. Invocation from + * regular CPU hotplug is properly serialized. + * + * Note, that the fact that __num_online_cpus is of type atomic_t + * does not protect readers which are not serialized against + * concurrent hotplug operations. + */ + if (online) { + if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) + atomic_inc(&__num_online_cpus); + } else { + if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) + atomic_dec(&__num_online_cpus); + } +} + /* * Activate the first processor. */ -- cgit v1.2.3-71-gd317 From 7b3c92b85a65c2db1f542265bc98e1f9e3056eba Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 4 Jul 2019 15:13:23 -0700 Subject: sched/core: Convert get_task_struct() to return the task Returning the pointer that was passed in allows us to write slightly more idiomatic code. Convert a few users. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190704221323.24290-1-willy@infradead.org Signed-off-by: Ingo Molnar --- include/linux/sched/task.h | 6 +++++- kernel/events/core.c | 9 +++------ kernel/irq/manage.c | 3 +-- kernel/locking/rtmutex.c | 6 ++---- kernel/trace/trace_sched_wakeup.c | 3 +-- 5 files changed, 12 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 0497091e40c1..3d90ed8f75f0 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -105,7 +105,11 @@ extern void sched_exec(void); #define sched_exec() {} #endif -#define get_task_struct(tsk) do { refcount_inc(&(tsk)->usage); } while(0) +static inline struct task_struct *get_task_struct(struct task_struct *t) +{ + refcount_inc(&t->usage); + return t; +} extern void __put_task_struct(struct task_struct *t); diff --git a/kernel/events/core.c b/kernel/events/core.c index 026a14541a38..ea5e8139fe62 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4089,10 +4089,8 @@ alloc_perf_context(struct pmu *pmu, struct task_struct *task) return NULL; __perf_event_init_context(ctx); - if (task) { - ctx->task = task; - get_task_struct(task); - } + if (task) + ctx->task = get_task_struct(task); ctx->pmu = pmu; return ctx; @@ -10355,8 +10353,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, * and we cannot use the ctx information because we need the * pmu before we get a ctx. */ - get_task_struct(task); - event->hw.target = task; + event->hw.target = get_task_struct(task); } event->clock = &local_clock; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e8f7f179bf77..9d50fbe5531a 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1255,8 +1255,7 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) * the thread dies to avoid that the interrupt code * references an already freed task_struct. */ - get_task_struct(t); - new->thread = t; + new->thread = get_task_struct(t); /* * Tell the thread to set its affinity. This is * important for shared interrupt handlers as we do diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index fa83d36e30c6..2874bf556162 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -628,8 +628,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } /* [10] Grab the next task, i.e. owner of @lock */ - task = rt_mutex_owner(lock); - get_task_struct(task); + task = get_task_struct(rt_mutex_owner(lock)); raw_spin_lock(&task->pi_lock); /* @@ -709,8 +708,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } /* [10] Grab the next task, i.e. the owner of @lock */ - task = rt_mutex_owner(lock); - get_task_struct(task); + task = get_task_struct(rt_mutex_owner(lock)); raw_spin_lock(&task->pi_lock); /* [11] requeue the pi waiters if necessary */ diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 743b2b520d34..5e43b9664eca 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -579,8 +579,7 @@ probe_wakeup(void *ignore, struct task_struct *p) else tracing_dl = 0; - wakeup_task = p; - get_task_struct(wakeup_task); + wakeup_task = get_task_struct(p); local_save_flags(flags); -- cgit v1.2.3-71-gd317 From c22645f4c8f021fb1c5e7189eb1f968132cc0844 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Fri, 19 Jul 2019 15:59:53 +0200 Subject: sched/topology: Add partition_sched_domains_locked() Introduce the partition_sched_domains_locked() function by taking the mutex locking code out of the original function. That way the work done by partition_sched_domains_locked() can be reused without dropping the mutex lock. No change of functionality is introduced by this patch. Tested-by: Dietmar Eggemann Signed-off-by: Mathieu Poirier Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bristot@redhat.com Cc: claudio@evidence.eu.com Cc: lizefan@huawei.com Cc: longman@redhat.com Cc: luca.abeni@santannapisa.it Cc: rostedt@goodmis.org Cc: tommaso.cucinotta@santannapisa.it Link: https://lkml.kernel.org/r/20190719140000.31694-2-juri.lelli@redhat.com Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 10 ++++++++++ kernel/sched/topology.c | 17 +++++++++++++---- 2 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7863bb62d2ab..f341163fedc9 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -150,6 +150,10 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd) return to_cpumask(sd->span); } +extern void partition_sched_domains_locked(int ndoms_new, + cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new); + extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new); @@ -194,6 +198,12 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl); struct sched_domain_attr; +static inline void +partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ +} + static inline void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 4eea2c9bc732..5a174ae6ecf3 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2169,16 +2169,16 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * ndoms_new == 0 is a special case for destroying existing domains, * and it will not create the default domain. * - * Call with hotplug lock held + * Call with hotplug lock and sched_domains_mutex held */ -void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) +void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) { bool __maybe_unused has_eas = false; int i, j, n; int new_topology; - mutex_lock(&sched_domains_mutex); + lockdep_assert_held(&sched_domains_mutex); /* Always unregister in case we don't destroy any domains: */ unregister_sched_domain_sysctl(); @@ -2261,6 +2261,15 @@ match3: ndoms_cur = ndoms_new; register_sched_domain_sysctl(); +} +/* + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + mutex_lock(&sched_domains_mutex); + partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); mutex_unlock(&sched_domains_mutex); } -- cgit v1.2.3-71-gd317 From f9a25f776d780bfa3279f0b6e5f5cf3224997976 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Fri, 19 Jul 2019 15:59:55 +0200 Subject: cpusets: Rebuild root domain deadline accounting information When the topology of root domains is modified by CPUset or CPUhotplug operations information about the current deadline bandwidth held in the root domain is lost. This patch addresses the issue by recalculating the lost deadline bandwidth information by circling through the deadline tasks held in CPUsets and adding their current load to the root domain they are associated with. Tested-by: Dietmar Eggemann Signed-off-by: Mathieu Poirier Signed-off-by: Juri Lelli [ Various additional modifications. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bristot@redhat.com Cc: claudio@evidence.eu.com Cc: lizefan@huawei.com Cc: longman@redhat.com Cc: luca.abeni@santannapisa.it Cc: rostedt@goodmis.org Cc: tj@kernel.org Cc: tommaso.cucinotta@santannapisa.it Link: https://lkml.kernel.org/r/20190719140000.31694-4-juri.lelli@redhat.com Signed-off-by: Ingo Molnar --- include/linux/cgroup.h | 1 + include/linux/sched.h | 5 ++++ include/linux/sched/deadline.h | 8 ++++++ kernel/cgroup/cgroup.c | 2 +- kernel/cgroup/cpuset.c | 64 +++++++++++++++++++++++++++++++++++++++++- kernel/sched/deadline.c | 30 ++++++++++++++++++++ kernel/sched/sched.h | 3 -- kernel/sched/topology.c | 13 ++++++++- 8 files changed, 120 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f6b048902d6c..3ba3e6da13a6 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -150,6 +150,7 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); +void cgroup_enable_task_cg_lists(void); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); diff --git a/include/linux/sched.h b/include/linux/sched.h index 9f51932bd543..b94ad92dfbe6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -295,6 +295,11 @@ enum uclamp_id { UCLAMP_CNT }; +#ifdef CONFIG_SMP +extern struct root_domain def_root_domain; +extern struct mutex sched_domains_mutex; +#endif + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 0cb034331cbb..1aff00b65f3c 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -24,3 +24,11 @@ static inline bool dl_time_before(u64 a, u64 b) { return (s64)(a - b) < 0; } + +#ifdef CONFIG_SMP + +struct root_domain; +extern void dl_add_task_root_domain(struct task_struct *p); +extern void dl_clear_root_domain(struct root_domain *rd); + +#endif /* CONFIG_SMP */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 753afbca549f..4b5bc452176c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1891,7 +1891,7 @@ static int cgroup_reconfigure(struct fs_context *fc) */ static bool use_task_css_set_links __read_mostly; -static void cgroup_enable_task_cg_lists(void) +void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5aa37531ce76..846cbdb68566 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include #include @@ -894,6 +895,67 @@ done: return ndoms; } +static void update_tasks_root_domain(struct cpuset *cs) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&cs->css, 0, &it); + + while ((task = css_task_iter_next(&it))) + dl_add_task_root_domain(task); + + css_task_iter_end(&it); +} + +static void rebuild_root_domains(void) +{ + struct cpuset *cs = NULL; + struct cgroup_subsys_state *pos_css; + + lockdep_assert_held(&cpuset_mutex); + lockdep_assert_cpus_held(); + lockdep_assert_held(&sched_domains_mutex); + + cgroup_enable_task_cg_lists(); + + rcu_read_lock(); + + /* + * Clear default root domain DL accounting, it will be computed again + * if a task belongs to it. + */ + dl_clear_root_domain(&def_root_domain); + + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { + + if (cpumask_empty(cs->effective_cpus)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + css_get(&cs->css); + + rcu_read_unlock(); + + update_tasks_root_domain(cs); + + rcu_read_lock(); + css_put(&cs->css); + } + rcu_read_unlock(); +} + +static void +partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + mutex_lock(&sched_domains_mutex); + partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); + rebuild_root_domains(); + mutex_unlock(&sched_domains_mutex); +} + /* * Rebuild scheduler domains. * @@ -931,7 +993,7 @@ static void rebuild_sched_domains_locked(void) ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ - partition_sched_domains(ndoms, doms, attr); + partition_and_rebuild_sched_domains(ndoms, doms, attr); out: put_online_cpus(); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index ef5b9f6b1d42..0f9d2180be23 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2283,6 +2283,36 @@ void __init init_sched_dl_class(void) GFP_KERNEL, cpu_to_node(i)); } +void dl_add_task_root_domain(struct task_struct *p) +{ + struct rq_flags rf; + struct rq *rq; + struct dl_bw *dl_b; + + rq = task_rq_lock(p, &rf); + if (!dl_task(p)) + goto unlock; + + dl_b = &rq->rd->dl_bw; + raw_spin_lock(&dl_b->lock); + + __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span)); + + raw_spin_unlock(&dl_b->lock); + +unlock: + task_rq_unlock(rq, p, &rf); +} + +void dl_clear_root_domain(struct root_domain *rd) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rd->dl_bw.lock, flags); + rd->dl_bw.total_bw = 0; + raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags); +} + #endif /* CONFIG_SMP */ static void switched_from_dl(struct rq *rq, struct task_struct *p) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 16126efd14ed..7583faddba33 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -778,9 +778,6 @@ struct root_domain { struct perf_domain __rcu *pd; }; -extern struct root_domain def_root_domain; -extern struct mutex sched_domains_mutex; - extern void init_defrootdomain(void); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 5a174ae6ecf3..8f83e8e3ea9a 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2203,8 +2203,19 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { if (cpumask_equal(doms_cur[i], doms_new[j]) && - dattrs_equal(dattr_cur, i, dattr_new, j)) + dattrs_equal(dattr_cur, i, dattr_new, j)) { + struct root_domain *rd; + + /* + * This domain won't be destroyed and as such + * its dl_bw->total_bw needs to be cleared. It + * will be recomputed in function + * update_tasks_root_domain(). + */ + rd = cpu_rq(cpumask_any(doms_cur[i]))->rd; + dl_clear_root_domain(rd); goto match1; + } } /* No match - a current sched domain not in new doms_new[] */ detach_destroy_domains(doms_cur[i]); -- cgit v1.2.3-71-gd317 From d74b27d63a8bebe2fe634944e4ebdc7b10db7a39 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Fri, 19 Jul 2019 15:59:58 +0200 Subject: cgroup/cpuset: Change cpuset_rwsem and hotplug lock order cpuset_rwsem is going to be acquired from sched_setscheduler() with a following patch. There are however paths (e.g., spawn_ksoftirqd) in which sched_scheduler() is eventually called while holding hotplug lock; this creates a dependecy between hotplug lock (to be always acquired first) and cpuset_rwsem (to be always acquired after hotplug lock). Fix paths which currently take the two locks in the wrong order (after a following patch is applied). Tested-by: Dietmar Eggemann Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bristot@redhat.com Cc: claudio@evidence.eu.com Cc: lizefan@huawei.com Cc: longman@redhat.com Cc: luca.abeni@santannapisa.it Cc: mathieu.poirier@linaro.org Cc: rostedt@goodmis.org Cc: tj@kernel.org Cc: tommaso.cucinotta@santannapisa.it Link: https://lkml.kernel.org/r/20190719140000.31694-7-juri.lelli@redhat.com Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 8 ++++---- kernel/cgroup/cpuset.c | 22 +++++++++++++++++----- 2 files changed, 21 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 934633a05d20..7f1478c26a33 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -40,14 +40,14 @@ static inline bool cpusets_enabled(void) static inline void cpuset_inc(void) { - static_branch_inc(&cpusets_pre_enable_key); - static_branch_inc(&cpusets_enabled_key); + static_branch_inc_cpuslocked(&cpusets_pre_enable_key); + static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { - static_branch_dec(&cpusets_enabled_key); - static_branch_dec(&cpusets_pre_enable_key); + static_branch_dec_cpuslocked(&cpusets_enabled_key); + static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } extern int cpuset_init(void); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e1a8d168c5e9..5c5014caa23c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -973,8 +973,8 @@ static void rebuild_sched_domains_locked(void) cpumask_var_t *doms; int ndoms; + lockdep_assert_cpus_held(); percpu_rwsem_assert_held(&cpuset_rwsem); - get_online_cpus(); /* * We have raced with CPU hotplug. Don't do anything to avoid @@ -983,19 +983,17 @@ static void rebuild_sched_domains_locked(void) */ if (!top_cpuset.nr_subparts_cpus && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) - goto out; + return; if (top_cpuset.nr_subparts_cpus && !cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask)) - goto out; + return; /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); -out: - put_online_cpus(); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) @@ -1005,9 +1003,11 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { + get_online_cpus(); percpu_down_write(&cpuset_rwsem); rebuild_sched_domains_locked(); percpu_up_write(&cpuset_rwsem); + put_online_cpus(); } /** @@ -2245,6 +2245,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = 0; + get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) { retval = -ENODEV; @@ -2282,6 +2283,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: percpu_up_write(&cpuset_rwsem); + put_online_cpus(); return retval; } @@ -2292,6 +2294,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = -ENODEV; + get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2306,6 +2309,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: percpu_up_write(&cpuset_rwsem); + put_online_cpus(); return retval; } @@ -2344,6 +2348,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); + get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2369,6 +2374,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: percpu_up_write(&cpuset_rwsem); + put_online_cpus(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); @@ -2499,6 +2505,7 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, return -EINVAL; css_get(&cs->css); + get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2506,6 +2513,7 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, retval = update_prstate(cs, val); out_unlock: percpu_up_write(&cpuset_rwsem); + put_online_cpus(); css_put(&cs->css); return retval ?: nbytes; } @@ -2711,6 +2719,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (!parent) return 0; + get_online_cpus(); percpu_down_write(&cpuset_rwsem); set_bit(CS_ONLINE, &cs->flags); @@ -2763,6 +2772,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) spin_unlock_irq(&callback_lock); out_unlock: percpu_up_write(&cpuset_rwsem); + put_online_cpus(); return 0; } @@ -2781,6 +2791,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); + get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (is_partition_root(cs)) @@ -2801,6 +2812,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) clear_bit(CS_ONLINE, &cs->flags); percpu_up_write(&cpuset_rwsem); + put_online_cpus(); } static void cpuset_css_free(struct cgroup_subsys_state *css) -- cgit v1.2.3-71-gd317 From 710da3c8ea7dfbd327920afd3831d8c82c42789d Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Fri, 19 Jul 2019 16:00:00 +0200 Subject: sched/core: Prevent race condition between cpuset and __sched_setscheduler() No synchronisation mechanism exists between the cpuset subsystem and calls to function __sched_setscheduler(). As such, it is possible that new root domains are created on the cpuset side while a deadline acceptance test is carried out in __sched_setscheduler(), leading to a potential oversell of CPU bandwidth. Grab cpuset_rwsem read lock from core scheduler, so to prevent situations such as the one described above from happening. The only exception is normalize_rt_tasks() which needs to work under tasklist_lock and can't therefore grab cpuset_rwsem. We are fine with this, as this function is only called by sysrq and, if that gets triggered, DEADLINE guarantees are already gone out of the window anyway. Tested-by: Dietmar Eggemann Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bristot@redhat.com Cc: claudio@evidence.eu.com Cc: lizefan@huawei.com Cc: longman@redhat.com Cc: luca.abeni@santannapisa.it Cc: mathieu.poirier@linaro.org Cc: rostedt@goodmis.org Cc: tj@kernel.org Cc: tommaso.cucinotta@santannapisa.it Link: https://lkml.kernel.org/r/20190719140000.31694-9-juri.lelli@redhat.com Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 5 +++++ kernel/cgroup/cpuset.c | 11 +++++++++++ kernel/sched/core.c | 20 +++++++++++++++++--- 3 files changed, 33 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 7f1478c26a33..04c20de66afc 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -55,6 +55,8 @@ extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); +extern void cpuset_read_lock(void); +extern void cpuset_read_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -176,6 +178,9 @@ static inline void cpuset_update_active_cpus(void) static inline void cpuset_wait_for_hotplug(void) { } +static inline void cpuset_read_lock(void) { } +static inline void cpuset_read_unlock(void) { } + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5c5014caa23c..c52bc91f882b 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -334,6 +334,17 @@ static struct cpuset top_cpuset = { */ DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem); + +void cpuset_read_lock(void) +{ + percpu_down_read(&cpuset_rwsem); +} + +void cpuset_read_unlock(void) +{ + percpu_up_read(&cpuset_rwsem); +} + static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1af3d2dc6b29..1bceb22dac18 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4698,6 +4698,9 @@ recheck: return retval; } + if (pi) + cpuset_read_lock(); + /* * Make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: @@ -4772,6 +4775,8 @@ change: if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); + if (pi) + cpuset_read_unlock(); goto recheck; } @@ -4832,8 +4837,10 @@ change: preempt_disable(); task_rq_unlock(rq, p, &rf); - if (pi) + if (pi) { + cpuset_read_unlock(); rt_mutex_adjust_pi(p); + } /* Run balance callbacks after we've adjusted the PI chain: */ balance_callback(rq); @@ -4843,6 +4850,8 @@ change: unlock: task_rq_unlock(rq, p, &rf); + if (pi) + cpuset_read_unlock(); return retval; } @@ -4927,10 +4936,15 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); - if (p != NULL) - retval = sched_setscheduler(p, policy, &lparam); + if (likely(p)) + get_task_struct(p); rcu_read_unlock(); + if (likely(p)) { + retval = sched_setscheduler(p, policy, &lparam); + put_task_struct(p); + } + return retval; } -- cgit v1.2.3-71-gd317 From 0058eb589881056b49a4ba15dfa3f1b8db53991c Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Tue, 9 Jul 2019 17:17:33 +0300 Subject: qed*: Change dpi_addr to be denoted with __iomem Several casts were required around dpi_addr parameter in qed_rdma_if.h This is an address on the doorbell bar and should therefore be marked with __iomem. Link: https://lore.kernel.org/r/20190709141735.19193-5-michal.kalderon@marvell.com Reported-by: Jason Gunthorpe Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/qedr/main.c | 2 +- drivers/infiniband/hw/qedr/qedr.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_rdma.c | 5 ++--- include/linux/qed/qed_rdma_if.h | 2 +- 4 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 533157a2a3be..ca5f6f65c929 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -820,7 +820,7 @@ static int qedr_init_hw(struct qedr_dev *dev) if (rc) goto out; - dev->db_addr = (void __iomem *)(uintptr_t)out_params.dpi_addr; + dev->db_addr = out_params.dpi_addr; dev->db_phys_addr = out_params.dpi_phys_addr; dev->db_size = out_params.dpi_size; dev->dpi = out_params.dpi; diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index a92ca22e5de1..0cfd849b13d6 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -229,7 +229,7 @@ struct qedr_ucontext { struct ib_ucontext ibucontext; struct qedr_dev *dev; struct qedr_pd *pd; - u64 dpi_addr; + void __iomem *dpi_addr; u64 dpi_phys_addr; u32 dpi_size; u16 dpi; diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index f900fde448db..95eba277f6e2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -799,9 +799,8 @@ static int qed_rdma_add_user(void *rdma_cxt, /* Calculate the corresponding DPI address */ dpi_start_offset = p_hwfn->dpi_start_offset; - out_params->dpi_addr = (u64)((u8 __iomem *)p_hwfn->doorbells + - dpi_start_offset + - ((out_params->dpi) * p_hwfn->dpi_size)); + out_params->dpi_addr = p_hwfn->doorbells + dpi_start_offset + + out_params->dpi * p_hwfn->dpi_size; out_params->dpi_phys_addr = p_hwfn->db_phys_addr + dpi_start_offset + diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 898f595ea3d6..74efca15fde7 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -225,7 +225,7 @@ struct qed_rdma_start_in_params { struct qed_rdma_add_user_out_params { u16 dpi; - u64 dpi_addr; + void __iomem *dpi_addr; u64 dpi_phys_addr; u32 dpi_size; u16 wid_count; -- cgit v1.2.3-71-gd317 From b2b998c0f944993c9ef435569651e407d607af41 Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Sun, 9 Jun 2019 20:19:03 +0200 Subject: leds: class: Improve LED and LED flash class registration API Replace of_led_classdev_register() with led_classdev_register_ext(), which accepts easily extendable struct led_init_data, instead of the fixed struct device_node argument. The latter can be now passed in an fwnode property of the struct led_init_data. The modification is driven by the need for passing additional arguments required for the forthcoming generic mechanism for composing LED names. Currently the LED name is conveyed in the "name" char pointer property of the struct led_classdev. This is redundant since LED class device name is accessible throughout the whole LED class device life time via associated struct device's kobj->name property. The change will not break any existing clients since the patch alters also existing led_classdev{_flash}_register() macro wrappers, that pass NULL in place of init_data, which leads to using legacy name initialization path basing on the struct led_classdev's "name" property. Three existing users of devm_of_led_classdev_registers() are modified to use devm_led_classdev_register(), which will not impact their operation since they in fact didn't need to pass struct device_node on registration from the beginning. Signed-off-by: Jacek Anaszewski Cc: Baolin Wang Cc: Dan Murphy Cc: Daniel Mack Cc: Linus Walleij Cc: Oleh Kravchenko Cc: Sakari Ailus Cc: Simon Shields Acked-by: Pavel Machek --- drivers/leds/led-class-flash.c | 9 +++++---- drivers/leds/led-class.c | 29 +++++++++++++++++------------ drivers/leds/leds-cr0014114.c | 3 +-- drivers/leds/leds-gpio.c | 2 +- drivers/leds/leds-max77650.c | 2 +- drivers/leds/leds-pwm.c | 3 +-- include/linux/led-class-flash.h | 15 ++++++++++----- include/linux/leds.h | 34 ++++++++++++++++++++++++---------- 8 files changed, 60 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/leds/led-class-flash.c b/drivers/leds/led-class-flash.c index 94980c654d89..60c3de5c6b9f 100644 --- a/drivers/leds/led-class-flash.c +++ b/drivers/leds/led-class-flash.c @@ -282,8 +282,9 @@ static void led_flash_init_sysfs_groups(struct led_classdev_flash *fled_cdev) led_cdev->groups = flash_groups; } -int led_classdev_flash_register(struct device *parent, - struct led_classdev_flash *fled_cdev) +int led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) { struct led_classdev *led_cdev; const struct led_flash_ops *ops; @@ -309,13 +310,13 @@ int led_classdev_flash_register(struct device *parent, } /* Register led class device */ - ret = led_classdev_register(parent, led_cdev); + ret = led_classdev_register_ext(parent, led_cdev, init_data); if (ret < 0) return ret; return 0; } -EXPORT_SYMBOL_GPL(led_classdev_flash_register); +EXPORT_SYMBOL_GPL(led_classdev_flash_register_ext); void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev) { diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 4793e77808e2..242122f49333 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -242,14 +243,16 @@ static int led_classdev_next_name(const char *init_name, char *name, } /** - * of_led_classdev_register - register a new object of led_classdev class. + * led_classdev_register_ext - register a new object of led_classdev class + * with init data. * * @parent: parent of LED device * @led_cdev: the led_classdev structure for this device. - * @np: DT node describing this LED + * @init_data: LED class device initialization data */ -int of_led_classdev_register(struct device *parent, struct device_node *np, - struct led_classdev *led_cdev) +int led_classdev_register_ext(struct device *parent, + struct led_classdev *led_cdev, + struct led_init_data *init_data) { char name[LED_MAX_NAME_SIZE]; int ret; @@ -266,7 +269,8 @@ int of_led_classdev_register(struct device *parent, struct device_node *np, mutex_unlock(&led_cdev->led_access); return PTR_ERR(led_cdev->dev); } - led_cdev->dev->of_node = np; + if (init_data && init_data->fwnode) + led_cdev->dev->of_node = to_of_node(init_data->fwnode); if (ret) dev_warn(parent, "Led %s renamed to %s due to name collision", @@ -311,7 +315,7 @@ int of_led_classdev_register(struct device *parent, struct device_node *np, return 0; } -EXPORT_SYMBOL_GPL(of_led_classdev_register); +EXPORT_SYMBOL_GPL(led_classdev_register_ext); /** * led_classdev_unregister - unregisters a object of led_properties class. @@ -356,14 +360,15 @@ static void devm_led_classdev_release(struct device *dev, void *res) } /** - * devm_of_led_classdev_register - resource managed led_classdev_register() + * devm_led_classdev_register_ext - resource managed led_classdev_register_ext() * * @parent: parent of LED device * @led_cdev: the led_classdev structure for this device. + * @init_data: LED class device initialization data */ -int devm_of_led_classdev_register(struct device *parent, - struct device_node *np, - struct led_classdev *led_cdev) +int devm_led_classdev_register_ext(struct device *parent, + struct led_classdev *led_cdev, + struct led_init_data *init_data) { struct led_classdev **dr; int rc; @@ -372,7 +377,7 @@ int devm_of_led_classdev_register(struct device *parent, if (!dr) return -ENOMEM; - rc = of_led_classdev_register(parent, np, led_cdev); + rc = led_classdev_register_ext(parent, led_cdev, init_data); if (rc) { devres_free(dr); return rc; @@ -383,7 +388,7 @@ int devm_of_led_classdev_register(struct device *parent, return 0; } -EXPORT_SYMBOL_GPL(devm_of_led_classdev_register); +EXPORT_SYMBOL_GPL(devm_led_classdev_register_ext); static int devm_led_classdev_match(struct device *dev, void *res, void *data) { diff --git a/drivers/leds/leds-cr0014114.c b/drivers/leds/leds-cr0014114.c index 0e4262462cb9..1c82152764d2 100644 --- a/drivers/leds/leds-cr0014114.c +++ b/drivers/leds/leds-cr0014114.c @@ -207,8 +207,7 @@ static int cr0014114_probe_dt(struct cr0014114 *priv) led->ldev.max_brightness = CR_MAX_BRIGHTNESS; led->ldev.brightness_set_blocking = cr0014114_set_sync; - ret = devm_of_led_classdev_register(priv->dev, np, - &led->ldev); + ret = devm_led_classdev_register(priv->dev, &led->ldev); if (ret) { dev_err(priv->dev, "failed to register LED device %s, err %d", diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c index bdc98ddca1dc..8f463c912db8 100644 --- a/drivers/leds/leds-gpio.c +++ b/drivers/leds/leds-gpio.c @@ -108,7 +108,7 @@ static int create_gpio_led(const struct gpio_led *template, if (ret < 0) return ret; - return devm_of_led_classdev_register(parent, np, &led_dat->cdev); + return devm_led_classdev_register(parent, &led_dat->cdev); } struct gpio_leds_priv { diff --git a/drivers/leds/leds-max77650.c b/drivers/leds/leds-max77650.c index 04738324b3e6..5a14f9775b0e 100644 --- a/drivers/leds/leds-max77650.c +++ b/drivers/leds/leds-max77650.c @@ -118,7 +118,7 @@ static int max77650_led_probe(struct platform_device *pdev) of_property_read_string(child, "linux,default-trigger", &led->cdev.default_trigger); - rv = devm_of_led_classdev_register(dev, child, &led->cdev); + rv = devm_led_classdev_register(dev, &led->cdev); if (rv) goto err_node_put; diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c index 48d068f80f11..d0e1f2710351 100644 --- a/drivers/leds/leds-pwm.c +++ b/drivers/leds/leds-pwm.c @@ -111,8 +111,7 @@ static int led_pwm_add(struct device *dev, struct led_pwm_priv *priv, if (!led_data->period && (led->pwm_period_ns > 0)) led_data->period = led->pwm_period_ns; - ret = devm_of_led_classdev_register(dev, to_of_node(fwnode), - &led_data->cdev); + ret = devm_led_classdev_register(dev, &led_data->cdev); if (ret == 0) { priv->num_leds++; led_pwm_set(&led_data->cdev, led_data->cdev.brightness); diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index f52713f0a269..1e824963af17 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -86,15 +86,20 @@ static inline struct led_classdev_flash *lcdev_to_flcdev( } /** - * led_classdev_flash_register - register a new object of led_classdev class - * with support for flash LEDs - * @parent: the flash LED to register + * led_classdev_flash_register_ext - register a new object of LED class with + * init data and with support for flash LEDs + * @parent: LED flash controller device this flash LED is driven by * @fled_cdev: the led_classdev_flash structure for this device + * @init_data: the LED class flash device initialization data * * Returns: 0 on success or negative error value on failure */ -extern int led_classdev_flash_register(struct device *parent, - struct led_classdev_flash *fled_cdev); +extern int led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data); + +#define led_classdev_flash_register(parent, fled_cdev) \ + led_classdev_flash_register_ext(parent, fled_cdev, NULL) /** * led_classdev_flash_unregister - unregisters an object of led_classdev class diff --git a/include/linux/leds.h b/include/linux/leds.h index 9b2bf574a17a..2bbe8a38fe39 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -30,6 +30,11 @@ enum led_brightness { LED_FULL = 255, }; +struct led_init_data { + /* device fwnode handle */ + struct fwnode_handle *fwnode; +}; + struct led_classdev { const char *name; enum led_brightness brightness; @@ -125,16 +130,25 @@ struct led_classdev { struct mutex led_access; }; -extern int of_led_classdev_register(struct device *parent, - struct device_node *np, - struct led_classdev *led_cdev); -#define led_classdev_register(parent, led_cdev) \ - of_led_classdev_register(parent, NULL, led_cdev) -extern int devm_of_led_classdev_register(struct device *parent, - struct device_node *np, - struct led_classdev *led_cdev); -#define devm_led_classdev_register(parent, led_cdev) \ - devm_of_led_classdev_register(parent, NULL, led_cdev) +/** + * led_classdev_register_ext - register a new object of LED class with + * init data + * @parent: LED controller device this LED is driven by + * @led_cdev: the led_classdev structure for this device + * @init_data: the LED class device initialization data + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_classdev_register_ext(struct device *parent, + struct led_classdev *led_cdev, + struct led_init_data *init_data); +#define led_classdev_register(parent, led_cdev) \ + led_classdev_register_ext(parent, led_cdev, NULL) +extern int devm_led_classdev_register_ext(struct device *parent, + struct led_classdev *led_cdev, + struct led_init_data *init_data); +#define devm_led_classdev_register(parent, led_cdev) \ + devm_led_classdev_register_ext(parent, led_cdev, NULL) extern void led_classdev_unregister(struct led_classdev *led_cdev); extern void devm_led_classdev_unregister(struct device *parent, struct led_classdev *led_cdev); -- cgit v1.2.3-71-gd317 From bb4e9af0348dfeafd66c7e7f82e8a0983fe5390c Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Sun, 9 Jun 2019 20:19:04 +0200 Subject: leds: core: Add support for composing LED class device names Add generic support for composing LED class device name. The newly introduced led_compose_name() function composes device name according to either or pattern, depending on the configuration of initialization data. Backward compatibility with in-driver hard-coded LED class device names is assured thanks to the default_label and devicename properties of newly introduced struct led_init_data. In case none of the aforementioned properties was found, then, for OF nodes, the node name is adopted for LED class device name. At the occassion of amending the Documentation/leds/leds-class.txt unify spelling: colour -> color. Alongside these changes added is a new tool - tools/leds/get_led_device_info.sh. The tool allows retrieving details of a LED class device's parent device, which proves that using vendor or product name for devicename part of LED name doesn't convey any added value since that information had been already available in sysfs. The script performs also basic validation of a LED class device name. Signed-off-by: Jacek Anaszewski Cc: Baolin Wang Cc: Dan Murphy Cc: Daniel Mack Cc: Linus Walleij Cc: Oleh Kravchenko Cc: Sakari Ailus Cc: Simon Shields Reviewed-by: Linus Walleij Acked-by: Pavel Machek --- Documentation/leds/leds-class.rst | 70 ++++++++++++- drivers/leds/led-class.c | 20 +++- drivers/leds/led-core.c | 127 ++++++++++++++++++++++++ drivers/leds/leds.h | 1 + include/linux/leds.h | 45 +++++++++ tools/leds/get_led_device_info.sh | 201 ++++++++++++++++++++++++++++++++++++++ 6 files changed, 458 insertions(+), 6 deletions(-) create mode 100755 tools/leds/get_led_device_info.sh (limited to 'include/linux') diff --git a/Documentation/leds/leds-class.rst b/Documentation/leds/leds-class.rst index df0120a1ee3c..a0708d3f3d0b 100644 --- a/Documentation/leds/leds-class.rst +++ b/Documentation/leds/leds-class.rst @@ -43,9 +43,73 @@ LED Device Naming Is currently of the form: - "devicename:colour:function" - -There have been calls for LED properties such as colour to be exported as + "devicename:color:function" + +- devicename: + it should refer to a unique identifier created by the kernel, + like e.g. phyN for network devices or inputN for input devices, rather + than to the hardware; the information related to the product and the bus + to which given device is hooked is available in sysfs and can be + retrieved using get_led_device_info.sh script from tools/leds; generally + this section is expected mostly for LEDs that are somehow associated with + other devices. + +- color: + one of LED_COLOR_ID_* definitions from the header + include/dt-bindings/leds/common.h. + +- function: + one of LED_FUNCTION_* definitions from the header + include/dt-bindings/leds/common.h. + +If required color or function is missing, please submit a patch +to linux-leds@vger.kernel.org. + +It is possible that more than one LED with the same color and function will +be required for given platform, differing only with an ordinal number. +In this case it is preferable to just concatenate the predefined LED_FUNCTION_* +name with required "-N" suffix in the driver. fwnode based drivers can use +function-enumerator property for that and then the concatenation will be handled +automatically by the LED core upon LED class device registration. + +LED subsystem has also a protection against name clash, that may occur +when LED class device is created by a driver of hot-pluggable device and +it doesn't provide unique devicename section. In this case numerical +suffix (e.g. "_1", "_2", "_3" etc.) is added to the requested LED class +device name. + +There might be still LED class drivers around using vendor or product name +for devicename, but this approach is now deprecated as it doesn't convey +any added value. Product information can be found in other places in sysfs +(see tools/leds/get_led_device_info.sh). + +Examples of proper LED names: + + - "red:disk" + - "white:flash" + - "red:indicator" + - "phy1:green:wlan" + - "phy3::wlan" + - ":kbd_backlight" + - "input5::kbd_backlight" + - "input3::numlock" + - "input3::scrolllock" + - "input3::capslock" + - "mmc1::status" + - "white:status" + +get_led_device_info.sh script can be used for verifying if the LED name +meets the requirements pointed out here. It performs validation of the LED class +devicename sections and gives hints on expected value for a section in case +the validation fails for it. So far the script supports validation +of associations between LEDs and following types of devices: + + - input devices + - ieee80211 compliant USB devices + +The script is open to extensions. + +There have been calls for LED properties such as color to be exported as individual led class attributes. As a solution which doesn't incur as much overhead, I suggest these become part of the device name. The naming scheme above leaves scope for further attributes should they be needed. If sections diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 242122f49333..508d6477d0b8 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -254,17 +254,31 @@ int led_classdev_register_ext(struct device *parent, struct led_classdev *led_cdev, struct led_init_data *init_data) { - char name[LED_MAX_NAME_SIZE]; + char composed_name[LED_MAX_NAME_SIZE]; + char final_name[LED_MAX_NAME_SIZE]; + const char *proposed_name = composed_name; int ret; - ret = led_classdev_next_name(led_cdev->name, name, sizeof(name)); + if (init_data) { + if (init_data->devname_mandatory && !init_data->devicename) { + dev_err(parent, "Mandatory device name is missing"); + return -EINVAL; + } + ret = led_compose_name(parent, init_data, composed_name); + if (ret < 0) + return ret; + } else { + proposed_name = led_cdev->name; + } + + ret = led_classdev_next_name(proposed_name, final_name, sizeof(final_name)); if (ret < 0) return ret; mutex_init(&led_cdev->led_access); mutex_lock(&led_cdev->led_access); led_cdev->dev = device_create_with_groups(leds_class, parent, 0, - led_cdev, led_cdev->groups, "%s", name); + led_cdev, led_cdev->groups, "%s", final_name); if (IS_ERR(led_cdev->dev)) { mutex_unlock(&led_cdev->led_access); return PTR_ERR(led_cdev->dev); diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index 7107cd7e87cf..f0c1c403f678 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -13,8 +13,10 @@ #include #include #include +#include #include #include +#include #include "leds.h" DECLARE_RWSEM(leds_list_lock); @@ -23,6 +25,18 @@ EXPORT_SYMBOL_GPL(leds_list_lock); LIST_HEAD(leds_list); EXPORT_SYMBOL_GPL(leds_list); +const char * const led_colors[LED_COLOR_ID_MAX] = { + [LED_COLOR_ID_WHITE] = "white", + [LED_COLOR_ID_RED] = "red", + [LED_COLOR_ID_GREEN] = "green", + [LED_COLOR_ID_BLUE] = "blue", + [LED_COLOR_ID_AMBER] = "amber", + [LED_COLOR_ID_VIOLET] = "violet", + [LED_COLOR_ID_YELLOW] = "yellow", + [LED_COLOR_ID_IR] = "ir", +}; +EXPORT_SYMBOL_GPL(led_colors); + static int __led_set_brightness(struct led_classdev *led_cdev, enum led_brightness value) { @@ -353,3 +367,116 @@ void led_sysfs_enable(struct led_classdev *led_cdev) led_cdev->flags &= ~LED_SYSFS_DISABLE; } EXPORT_SYMBOL_GPL(led_sysfs_enable); + +static void led_parse_fwnode_props(struct device *dev, + struct fwnode_handle *fwnode, + struct led_properties *props) +{ + int ret; + + if (!fwnode) + return; + + if (fwnode_property_present(fwnode, "label")) { + ret = fwnode_property_read_string(fwnode, "label", &props->label); + if (ret) + dev_err(dev, "Error parsing 'label' property (%d)\n", ret); + return; + } + + if (fwnode_property_present(fwnode, "color")) { + ret = fwnode_property_read_u32(fwnode, "color", &props->color); + if (ret) + dev_err(dev, "Error parsing 'color' property (%d)\n", ret); + else if (props->color >= LED_COLOR_ID_MAX) + dev_err(dev, "LED color identifier out of range\n"); + else + props->color_present = true; + } + + + if (!fwnode_property_present(fwnode, "function")) + return; + + ret = fwnode_property_read_string(fwnode, "function", &props->function); + if (ret) { + dev_err(dev, + "Error parsing 'function' property (%d)\n", + ret); + } + + if (!fwnode_property_present(fwnode, "function-enumerator")) + return; + + ret = fwnode_property_read_u32(fwnode, "function-enumerator", + &props->func_enum); + if (ret) { + dev_err(dev, + "Error parsing 'function-enumerator' property (%d)\n", + ret); + } else { + props->func_enum_present = true; + } +} + +int led_compose_name(struct device *dev, struct led_init_data *init_data, + char *led_classdev_name) +{ + struct led_properties props = {}; + struct fwnode_handle *fwnode = init_data->fwnode; + const char *devicename = init_data->devicename; + + if (!led_classdev_name) + return -EINVAL; + + led_parse_fwnode_props(dev, fwnode, &props); + + if (props.label) { + /* + * If init_data.devicename is NULL, then it indicates that + * DT label should be used as-is for LED class device name. + * Otherwise the label is prepended with devicename to compose + * the final LED class device name. + */ + if (!devicename) { + strscpy(led_classdev_name, props.label, + LED_MAX_NAME_SIZE); + } else { + snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s", + devicename, props.label); + } + } else if (props.function || props.color_present) { + char tmp_buf[LED_MAX_NAME_SIZE]; + + if (props.func_enum_present) { + snprintf(tmp_buf, LED_MAX_NAME_SIZE, "%s:%s-%d", + props.color_present ? led_colors[props.color] : "", + props.function ?: "", props.func_enum); + } else { + snprintf(tmp_buf, LED_MAX_NAME_SIZE, "%s:%s", + props.color_present ? led_colors[props.color] : "", + props.function ?: ""); + } + if (init_data->devname_mandatory) { + snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s", + devicename, tmp_buf); + } else { + strscpy(led_classdev_name, tmp_buf, LED_MAX_NAME_SIZE); + + } + } else if (init_data->default_label) { + if (!devicename) { + dev_err(dev, "Legacy LED naming requires devicename segment"); + return -EINVAL; + } + snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s", + devicename, init_data->default_label); + } else if (is_of_node(fwnode)) { + strscpy(led_classdev_name, to_of_node(fwnode)->name, + LED_MAX_NAME_SIZE); + } else + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_GPL(led_compose_name); diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h index 47b229469069..0b577cece8f7 100644 --- a/drivers/leds/leds.h +++ b/drivers/leds/leds.h @@ -27,5 +27,6 @@ void led_set_brightness_nosleep(struct led_classdev *led_cdev, extern struct rw_semaphore leds_list_lock; extern struct list_head leds_list; extern struct list_head trigger_list; +extern const char * const led_colors[LED_COLOR_ID_MAX]; #endif /* __LEDS_H_INCLUDED */ diff --git a/include/linux/leds.h b/include/linux/leds.h index 2bbe8a38fe39..d101fd13e18e 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -8,6 +8,7 @@ #ifndef __LINUX_LEDS_H_INCLUDED #define __LINUX_LEDS_H_INCLUDED +#include #include #include #include @@ -33,6 +34,25 @@ enum led_brightness { struct led_init_data { /* device fwnode handle */ struct fwnode_handle *fwnode; + /* + * default tuple, for backward compatibility + * with in-driver hard-coded LED names used as a fallback when + * DT "label" property is absent; it should be set to NULL + * in new LED class drivers. + */ + const char *default_label; + /* + * string to be used for devicename section of LED class device + * either for label based LED name composition path or for fwnode + * based when devname_mandatory is true + */ + const char *devicename; + /* + * indicates if LED name should always comprise devicename section; + * only LEDs exposed by drivers of hot-pluggable devices should + * set it to true + */ + bool devname_mandatory; }; struct led_classdev { @@ -257,6 +277,22 @@ extern void led_sysfs_disable(struct led_classdev *led_cdev); */ extern void led_sysfs_enable(struct led_classdev *led_cdev); +/** + * led_compose_name - compose LED class device name + * @dev: LED controller device object + * @child: child fwnode_handle describing a LED or a group of synchronized LEDs; + * it must be provided only for fwnode based LEDs + * @led_classdev_name: composed LED class device name + * + * Create LED class device name basing on the provided init_data argument. + * The name can have or . + * form, depending on the init_data configuration. + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_compose_name(struct device *dev, struct led_init_data *init_data, + char *led_classdev_name); + /** * led_sysfs_is_disabled - check if LED sysfs interface is disabled * @led_cdev: the LED to query @@ -434,6 +470,15 @@ struct led_platform_data { struct led_info *leds; }; +struct led_properties { + u32 color; + bool color_present; + const char *function; + u32 func_enum; + bool func_enum_present; + const char *label; +}; + struct gpio_desc; typedef int (*gpio_blink_set_t)(struct gpio_desc *desc, int state, unsigned long *delay_on, diff --git a/tools/leds/get_led_device_info.sh b/tools/leds/get_led_device_info.sh new file mode 100755 index 000000000000..ccfa442db5fe --- /dev/null +++ b/tools/leds/get_led_device_info.sh @@ -0,0 +1,201 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +led_common_defs_path="include/dt-bindings/leds/common.h" + +num_args=$# +if [ $num_args -eq 1 ]; then + linux_top=$(dirname `realpath $0` | awk -F/ \ + '{ \ + i=1; \ + while (i <= NF - 2) { \ + printf $i"/"; \ + i++; \ + }; \ + }') + led_defs_path=$linux_top/$led_common_defs_path +elif [ $num_args -eq 2 ]; then + led_defs_path=`realpath $2` +else + echo "Usage: get_led_device_info.sh LED_CDEV_PATH [LED_COMMON_DEFS_PATH]" + exit 1 +fi + +if [ ! -f $led_defs_path ]; then + echo "$led_defs_path doesn't exist" + exit 1 +fi + +led_cdev_path=`echo $1 | sed s'/\/$//'` + +ls "$led_cdev_path/brightness" > /dev/null 2>&1 +if [ $? -ne 0 ]; then + echo "Device \"$led_cdev_path\" does not exist." + exit 1 +fi + +bus=`readlink $led_cdev_path/device/subsystem | sed s'/.*\///'` +usb_subdev=`readlink $led_cdev_path | grep usb | sed s'/\(.*usb[0-9]*\/[0-9]*-[0-9]*\)\/.*/\1/'` +ls "$led_cdev_path/device/of_node/compatible" > /dev/null 2>&1 +of_node_missing=$? + +if [ "$bus" = "input" ]; then + input_node=`readlink $led_cdev_path/device | sed s'/.*\///'` + if [ ! -z "$usb_subdev" ]; then + bus="usb" + fi +fi + +if [ "$bus" = "usb" ]; then + usb_interface=`readlink $led_cdev_path | sed s'/.*\(usb[0-9]*\)/\1/' | cut -d\/ -f3` + cd $led_cdev_path/../$usb_subdev + driver=`readlink $usb_interface/driver | sed s'/.*\///'` + if [ -d "$usb_interface/ieee80211" ]; then + wifi_phy=`ls -l $usb_interface/ieee80211 | grep phy | awk '{print $9}'` + fi + idVendor=`cat idVendor` + idProduct=`cat idProduct` + manufacturer=`cat manufacturer` + product=`cat product` +elif [ "$bus" = "input" ]; then + cd $led_cdev_path + product=`cat device/name` + driver=`cat device/device/driver/description` +elif [ $of_node_missing -eq 0 ]; then + cd $led_cdev_path + compatible=`cat device/of_node/compatible` + if [ "$compatible" = "gpio-leds" ]; then + driver="leds-gpio" + elif [ "$compatible" = "pwm-leds" ]; then + driver="leds-pwm" + else + manufacturer=`echo $compatible | awk -F, '{print $1}'` + product=`echo $compatible | awk -F, '{print $2}'` + fi +else + echo "Unknown device type." + exit 1 +fi + +printf "\n#####################################\n" +printf "# LED class device hardware details #\n" +printf "#####################################\n\n" + +printf "bus:\t\t\t$bus\n" + +if [ ! -z "$idVendor" ]; then + printf "idVendor:\t\t$idVendor\n" +fi + +if [ ! -z "$idProduct" ]; then + printf "idProduct:\t\t$idProduct\n" +fi + +if [ ! -z "$manufacturer" ]; then + printf "manufacturer:\t\t$manufacturer\n" +fi + +if [ ! -z "$product" ]; then + printf "product:\t\t$product\n" +fi + +if [ ! -z "$driver" ]; then + printf "driver:\t\t\t$driver\n" +fi + +if [ ! -z "$input_node" ]; then + printf "associated input node:\t$input_node\n" +fi + +printf "\n####################################\n" +printf "# LED class device name validation #\n" +printf "####################################\n\n" + +led_name=`echo $led_cdev_path | sed s'/.*\///'` + +num_sections=`echo $led_name | awk -F: '{print NF}'` + +if [ $num_sections -eq 1 ]; then + printf "\":\" delimiter not detected.\t[ FAILED ]\n" + exit 1 +elif [ $num_sections -eq 2 ]; then + color=`echo $led_name | cut -d: -f1` + function=`echo $led_name | cut -d: -f2` +elif [ $num_sections -eq 3 ]; then + devicename=`echo $led_name | cut -d: -f1` + color=`echo $led_name | cut -d: -f2` + function=`echo $led_name | cut -d: -f3` +else + printf "Detected %d sections in the LED class device name - should the script be updated?\n" $num_sections + exit 1 +fi + +S_DEV="devicename" +S_CLR="color " +S_FUN="function " +status_tab=20 + +print_msg_ok() +{ + local section_name="$1" + local section_val="$2" + local msg="$3" + printf "$section_name :\t%-${status_tab}.${status_tab}s %s %s\n" "$section_val" "[ OK ] " "$msg" +} + +print_msg_failed() +{ + local section_name="$1" + local section_val="$2" + local msg="$3" + printf "$section_name :\t%-${status_tab}.${status_tab}s %s %s\n" "$section_val" "[ FAILED ]" "$msg" +} + +if [ ! -z "$input_node" ]; then + expected_devname=$input_node +elif [ ! -z "$wifi_phy" ]; then + expected_devname=$wifi_phy +fi + +if [ ! -z "$devicename" ]; then + if [ ! -z "$expected_devname" ]; then + if [ "$devicename" = "$expected_devname" ]; then + print_msg_ok "$S_DEV" "$devicename" + else + print_msg_failed "$S_DEV" "$devicename" "Expected: $expected_devname" + fi + else + if [ "$devicename" = "$manufacturer" ]; then + print_msg_failed "$S_DEV" "$devicename" "Redundant: use of vendor name is discouraged" + elif [ "$devicename" = "$product" ]; then + print_msg_failed "$S_DEV" "$devicename" "Redundant: use of product name is discouraged" + else + print_msg_failed "$S_DEV" "$devicename" "Unknown devicename - should the script be updated?" + fi + fi +elif [ ! -z "$expected_devname" ]; then + print_msg_failed "$S_DEV" "blank" "Expected: $expected_devname" +fi + +if [ ! -z "$color" ]; then + color_upper=`echo $color | tr [:lower:] [:upper:]` + color_id_definition=$(cat $led_defs_path | grep "_$color_upper\s" | awk '{print $2}') + if [ ! -z "$color_id_definition" ]; then + print_msg_ok "$S_CLR" "$color" "Matching definition: $color_id_definition" + else + print_msg_failed "$S_CLR" "$color" "Definition not found in $led_defs_path" + fi + +fi + +if [ ! -z "$function" ]; then + # strip optional enumerator + function=`echo $function | sed s'/\(.*\)-[0-9]*$/\1/'` + fun_definition=$(cat $led_defs_path | grep "\"$function\"" | awk '{print $2}') + if [ ! -z "$fun_definition" ]; then + print_msg_ok "$S_FUN" "$function" "Matching definition: $fun_definition" + else + print_msg_failed "$S_FUN" "$function" "Definition not found in $led_defs_path" + fi + +fi -- cgit v1.2.3-71-gd317 From f32471e2cf87112b8f5dc10469b27c39c1a41722 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Jul 2019 08:52:57 +0200 Subject: mm/hmm: remove the legacy hmm_pfn_* APIs Switch the one remaining user in nouveau over to its replacement, and remove all the wrappers. Link: https://lore.kernel.org/r/20190724065258.16603-7-hch@lst.de Tested-by: Ralph Campbell Signed-off-by: Christoph Hellwig Reviewed-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- include/linux/hmm.h | 34 ---------------------------------- 2 files changed, 1 insertion(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 1333220787a1..345c63cb752a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -845,7 +845,7 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, struct page *page; uint64_t addr; - page = hmm_pfn_to_page(range, range->pfns[i]); + page = hmm_device_entry_to_page(range, range->pfns[i]); if (page == NULL) continue; diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 7ef56dc18050..9f32586684c9 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -290,40 +290,6 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, range->flags[HMM_PFN_VALID]; } -/* - * Old API: - * hmm_pfn_to_page() - * hmm_pfn_to_pfn() - * hmm_pfn_from_page() - * hmm_pfn_from_pfn() - * - * This are the OLD API please use new API, it is here to avoid cross-tree - * merge painfullness ie we convert things to new API in stages. - */ -static inline struct page *hmm_pfn_to_page(const struct hmm_range *range, - uint64_t pfn) -{ - return hmm_device_entry_to_page(range, pfn); -} - -static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range, - uint64_t pfn) -{ - return hmm_device_entry_to_pfn(range, pfn); -} - -static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range, - struct page *page) -{ - return hmm_device_entry_from_page(range, page); -} - -static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, - unsigned long pfn) -{ - return hmm_device_entry_from_pfn(range, pfn); -} - /* * Mirroring: how to synchronize device page table with CPU page table. * -- cgit v1.2.3-71-gd317 From 086f95682114fd2d1790bd3226e76cbae9a2d192 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 25 Jul 2019 15:52:25 -0700 Subject: bpf/flow_dissector: pass input flags to BPF flow dissector program C flow dissector supports input flags that tell it to customize parsing by either stopping early or trying to parse as deep as possible. Pass those flags to the BPF flow dissector so it can make the same decisions. In the next commits I'll add support for those flags to our reference bpf_flow.c v3: * Export copy of flow dissector flags instead of moving (Alexei Starovoitov) Acked-by: Petar Penkov Acked-by: Willem de Bruijn Acked-by: Song Liu Cc: Song Liu Cc: Willem de Bruijn Cc: Petar Penkov Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 2 +- include/uapi/linux/bpf.h | 5 +++++ net/bpf/test_run.c | 2 +- net/core/flow_dissector.c | 12 ++++++++++-- 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 718742b1c505..9b7a8038beec 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1271,7 +1271,7 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen); + __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fa1c753dcdbc..88b9d743036f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3507,6 +3507,10 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + struct bpf_flow_keys { __u16 nhoff; __u16 thoff; @@ -3528,6 +3532,7 @@ struct bpf_flow_keys { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; }; + __u32 flags; }; struct bpf_func_info { diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 80e6f3a6864d..4e41d15a1098 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -419,7 +419,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, - size); + size, 0); if (signal_pending(current)) { preempt_enable(); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3e6fedb57bc1..50ed1a688709 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -784,7 +784,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, } bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen) + __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; @@ -795,6 +795,14 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != + (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != + (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != + (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); + flow_keys->flags = flags; + preempt_disable(); result = BPF_PROG_RUN(prog, ctx); preempt_enable(); @@ -914,7 +922,7 @@ bool __skb_flow_dissect(const struct net *net, } ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, - hlen); + hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); -- cgit v1.2.3-71-gd317 From 9552389c465ed1ded39edf4a5642a861b53c2955 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Tue, 2 Jul 2019 14:39:20 +0300 Subject: crypto: fips - add FIPS test failure notification chain Crypto test failures in FIPS mode cause an immediate panic, but on some system the cryptographic boundary extends beyond just the Linux controlled domain. Add a simple atomic notification chain to allow interested parties to register to receive notification prior to us kicking the bucket. Signed-off-by: Gilad Ben-Yossef Signed-off-by: Herbert Xu --- crypto/fips.c | 11 +++++++++++ crypto/testmgr.c | 4 +++- include/linux/fips.h | 7 +++++++ 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/crypto/fips.c b/crypto/fips.c index c0b3a3c3452d..7b1d8caee669 100644 --- a/crypto/fips.c +++ b/crypto/fips.c @@ -11,10 +11,14 @@ #include #include #include +#include int fips_enabled; EXPORT_SYMBOL_GPL(fips_enabled); +ATOMIC_NOTIFIER_HEAD(fips_fail_notif_chain); +EXPORT_SYMBOL_GPL(fips_fail_notif_chain); + /* Process kernel command-line parameter at boot time. fips=0 or fips=1 */ static int fips_enable(char *str) { @@ -58,6 +62,13 @@ static void crypto_proc_fips_exit(void) unregister_sysctl_table(crypto_sysctls); } +void fips_fail_notify(void) +{ + if (fips_enabled) + atomic_notifier_call_chain(&fips_fail_notif_chain, 0, NULL); +} +EXPORT_SYMBOL_GPL(fips_fail_notify); + static int __init fips_init(void) { crypto_proc_fips_init(); diff --git a/crypto/testmgr.c b/crypto/testmgr.c index d0b5b33806a6..8ba1e75cd973 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -5240,9 +5240,11 @@ int alg_test(const char *driver, const char *alg, u32 type, u32 mask) type, mask); test_done: - if (rc && (fips_enabled || panic_on_fail)) + if (rc && (fips_enabled || panic_on_fail)) { + fips_fail_notify(); panic("alg: self-tests for %s (%s) failed in %s mode!\n", driver, alg, fips_enabled ? "fips" : "panic_on_fail"); + } if (fips_enabled && !rc) pr_info("alg: self-tests for %s (%s) passed\n", driver, alg); diff --git a/include/linux/fips.h b/include/linux/fips.h index afeeece92302..c6961e932fef 100644 --- a/include/linux/fips.h +++ b/include/linux/fips.h @@ -4,8 +4,15 @@ #ifdef CONFIG_CRYPTO_FIPS extern int fips_enabled; +extern struct atomic_notifier_head fips_fail_notif_chain; + +void fips_fail_notify(void); + #else #define fips_enabled 0 + +static inline void fips_fail_notify(void) {} + #endif #endif -- cgit v1.2.3-71-gd317 From 17a8f868ae3e85a173843b1ac65e744e8585bc5a Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 8 Jul 2019 11:24:56 +0530 Subject: opp: Return genpd virtual devices from dev_pm_opp_attach_genpd() The cpufreq drivers don't need to do runtime PM operations on the virtual devices returned by dev_pm_domain_attach_by_name() and so the virtual devices weren't shared with the callers of dev_pm_opp_attach_genpd() earlier. But the IO device drivers would want to do that. This patch updates the prototype of dev_pm_opp_attach_genpd() to accept another argument to return the pointer to the array of genpd virtual devices. Reported-by: Rajendra Nayak Tested-by: Rajendra Nayak Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 6 +++++- include/linux/pm_opp.h | 4 ++-- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 08b830f84d8c..bdb435822401 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1771,6 +1771,7 @@ static void _opp_detach_genpd(struct opp_table *opp_table) * dev_pm_opp_attach_genpd - Attach genpd(s) for the device and save virtual device pointer * @dev: Consumer device for which the genpd is getting attached. * @names: Null terminated array of pointers containing names of genpd to attach. + * @virt_devs: Pointer to return the array of virtual devices. * * Multiple generic power domains for a device are supported with the help of * virtual genpd devices, which are created for each consumer device - genpd @@ -1788,7 +1789,8 @@ static void _opp_detach_genpd(struct opp_table *opp_table) * The order of entries in the names array must match the order in which * "required-opps" are added in DT. */ -struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names) +struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, + const char **names, struct device ***virt_devs) { struct opp_table *opp_table; struct device *virt_dev; @@ -1842,6 +1844,8 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names name++; } + if (virt_devs) + *virt_devs = opp_table->genpd_virt_devs; mutex_unlock(&opp_table->genpd_virt_dev_lock); return opp_table; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index af5021f27cb7..5bdceca5125d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -128,7 +128,7 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); -struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names); +struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); @@ -292,7 +292,7 @@ static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} -static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names) +static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs) { return ERR_PTR(-ENOTSUPP); } -- cgit v1.2.3-71-gd317 From 71419d84c216cee8da3b19fb843b4242f112cde4 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 25 Jul 2019 12:41:29 +0200 Subject: opp: Add dev_pm_opp_find_level_exact() Since the performance states in the OPP table are unique, implement a dev_pm_opp_find_level_exact() in order to be able to fetch a specific OPP. Signed-off-by: Niklas Cassel [ Viresh: Updated commit log ] Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_opp.h | 8 ++++++++ 2 files changed, 56 insertions(+) (limited to 'include/linux') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index bdb435822401..0ee8c0133d3e 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -401,6 +401,54 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact); +/** + * dev_pm_opp_find_level_exact() - search for an exact level + * @dev: device for which we do this operation + * @level: level to search for + * + * Return: Searches for exact match in the opp table and returns pointer to the + * matching opp if found, else returns ERR_PTR in case of error and should + * be handled using IS_ERR. Error return values can be: + * EINVAL: for bad pointer + * ERANGE: no match found for search + * ENODEV: if device not found in list of registered devices + * + * The callers are required to call dev_pm_opp_put() for the returned OPP after + * use. + */ +struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, + unsigned int level) +{ + struct opp_table *opp_table; + struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + int r = PTR_ERR(opp_table); + + dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r); + return ERR_PTR(r); + } + + mutex_lock(&opp_table->lock); + + list_for_each_entry(temp_opp, &opp_table->opp_list, node) { + if (temp_opp->level == level) { + opp = temp_opp; + + /* Increment the reference count of OPP */ + dev_pm_opp_get(opp); + break; + } + } + + mutex_unlock(&opp_table->lock); + dev_pm_opp_put_opp_table(opp_table); + + return opp; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_exact); + static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table, unsigned long *freq) { diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 5bdceca5125d..b8197ab014f2 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -96,6 +96,8 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available); +struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, + unsigned int level); struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq); @@ -200,6 +202,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, return ERR_PTR(-ENOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, + unsigned int level) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { -- cgit v1.2.3-71-gd317 From 2aa485e1148557215337731b2c79f5569edcbbab Mon Sep 17 00:00:00 2001 From: John Crispin Date: Sat, 13 Jul 2019 18:36:41 +0200 Subject: mac80211: add support for parsing ADDBA_EXT IEs ADDBA_EXT IEs can be used to negotiate the BA fragmentation level. Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20190713163642.18491-2-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 8 ++++++++ net/mac80211/ieee80211_i.h | 1 + net/mac80211/util.c | 7 +++++++ 3 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8511fadc0935..f36144eda5d6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -881,6 +881,14 @@ struct ieee80211_tpc_report_ie { u8 link_margin; } __packed; +#define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) +#define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 +#define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) + +struct ieee80211_addba_ext_ie { + u8 data; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 004e2e3adb88..c67da3575e74 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1506,6 +1506,7 @@ struct ieee802_11_elems { u8 max_bssid_indicator; u8 dtim_count; u8 dtim_period; + const struct ieee80211_addba_ext_ie *addba_ext_ie; /* length of them, respectively */ u8 ext_capab_len; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1b224fa27367..3441558ef2d2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1200,6 +1200,13 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; + case WLAN_EID_ADDBA_EXT: + if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + elem_parse_failed = true; + break; + } + elems->addba_ext_ie = (void *)pos; + break; case WLAN_EID_TIMEOUT_INTERVAL: if (elen >= sizeof(struct ieee80211_timeout_interval_ie)) elems->timeout_int = (void *)pos; -- cgit v1.2.3-71-gd317 From 1f961807925032daa90267d8a23ff730e7ede07a Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Thu, 25 Jul 2019 17:56:44 -0700 Subject: mm/hmm: replace hmm_update with mmu_notifier_range The hmm_mirror_ops callback function sync_cpu_device_pagetables() passes a struct hmm_update which is a simplified version of struct mmu_notifier_range. This is unnecessary so replace hmm_update with mmu_notifier_range directly. Link: https://lore.kernel.org/r/20190726005650.2566-2-rcampbell@nvidia.com Signed-off-by: Ralph Campbell Reviewed: Christoph Hellwig Reviewed-by: Jason Gunthorpe [jgg: white space tuning] Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 14 ++++++++------ drivers/gpu/drm/nouveau/nouveau_svm.c | 4 ++-- include/linux/hmm.h | 34 ++++++---------------------------- mm/hmm.c | 13 ++++--------- 4 files changed, 20 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 3971c201f320..b698b423b25d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -195,13 +195,14 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node, * Block for operations on BOs to finish and mark pages as accessed and * potentially dirty. */ -static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, - const struct hmm_update *update) +static int +amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, + const struct mmu_notifier_range *update) { struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror); unsigned long start = update->start; unsigned long end = update->end; - bool blockable = update->blockable; + bool blockable = mmu_notifier_range_blockable(update); struct interval_tree_node *it; /* notification is exclusive, but interval is inclusive */ @@ -243,13 +244,14 @@ static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, * necessitates evicting all user-mode queues of the process. The BOs * are restorted in amdgpu_mn_invalidate_range_end_hsa. */ -static int amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror, - const struct hmm_update *update) +static int +amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror, + const struct mmu_notifier_range *update) { struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror); unsigned long start = update->start; unsigned long end = update->end; - bool blockable = update->blockable; + bool blockable = mmu_notifier_range_blockable(update); struct interval_tree_node *it; /* notification is exclusive, but interval is inclusive */ diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 545100f7c594..79b29c918717 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -252,13 +252,13 @@ nouveau_svmm_invalidate(struct nouveau_svmm *svmm, u64 start, u64 limit) static int nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror, - const struct hmm_update *update) + const struct mmu_notifier_range *update) { struct nouveau_svmm *svmm = container_of(mirror, typeof(*svmm), mirror); unsigned long start = update->start; unsigned long limit = update->end; - if (!update->blockable) + if (!mmu_notifier_range_blockable(update)) return -EAGAIN; SVMM_DBG(svmm, "invalidate %016lx-%016lx", start, limit); diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 9f32586684c9..4f870f7017cb 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -340,29 +340,6 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, struct hmm_mirror; -/* - * enum hmm_update_event - type of update - * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) - */ -enum hmm_update_event { - HMM_UPDATE_INVALIDATE, -}; - -/* - * struct hmm_update - HMM update information for callback - * - * @start: virtual start address of the range to update - * @end: virtual end address of the range to update - * @event: event triggering the update (what is happening) - * @blockable: can the callback block/sleep ? - */ -struct hmm_update { - unsigned long start; - unsigned long end; - enum hmm_update_event event; - bool blockable; -}; - /* * struct hmm_mirror_ops - HMM mirror device operations callback * @@ -383,9 +360,9 @@ struct hmm_mirror_ops { /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror - * @update: update information (see struct hmm_update) - * Return: -EAGAIN if update.blockable false and callback need to - * block, 0 otherwise. + * @update: update information (see struct mmu_notifier_range) + * Return: -EAGAIN if mmu_notifier_range_blockable(update) is false + * and callback needs to block, 0 otherwise. * * This callback ultimately originates from mmu_notifiers when the CPU * page table is updated. The device driver must update its page table @@ -396,8 +373,9 @@ struct hmm_mirror_ops { * page tables are completely updated (TLBs flushed, etc); this is a * synchronous call. */ - int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - const struct hmm_update *update); + int (*sync_cpu_device_pagetables)( + struct hmm_mirror *mirror, + const struct mmu_notifier_range *update); }; /* diff --git a/mm/hmm.c b/mm/hmm.c index 54b3a4162ae9..4040b4427635 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -165,7 +165,6 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn, { struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); struct hmm_mirror *mirror; - struct hmm_update update; struct hmm_range *range; unsigned long flags; int ret = 0; @@ -173,15 +172,10 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn, if (!kref_get_unless_zero(&hmm->kref)) return 0; - update.start = nrange->start; - update.end = nrange->end; - update.event = HMM_UPDATE_INVALIDATE; - update.blockable = mmu_notifier_range_blockable(nrange); - spin_lock_irqsave(&hmm->ranges_lock, flags); hmm->notifiers++; list_for_each_entry(range, &hmm->ranges, list) { - if (update.end < range->start || update.start >= range->end) + if (nrange->end < range->start || nrange->start >= range->end) continue; range->valid = false; @@ -198,9 +192,10 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn, list_for_each_entry(mirror, &hmm->mirrors, list) { int rc; - rc = mirror->ops->sync_cpu_device_pagetables(mirror, &update); + rc = mirror->ops->sync_cpu_device_pagetables(mirror, nrange); if (rc) { - if (WARN_ON(update.blockable || rc != -EAGAIN)) + if (WARN_ON(mmu_notifier_range_blockable(nrange) || + rc != -EAGAIN)) continue; ret = -EAGAIN; break; -- cgit v1.2.3-71-gd317 From 9a4903e49e495bfd2650862dfae4178bebe4db9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 25 Jul 2019 17:56:46 -0700 Subject: mm/hmm: replace the block argument to hmm_range_fault with a flags value This allows easier expansion to other flags, and also makes the callers a little easier to read. Link: https://lore.kernel.org/r/20190726005650.2566-4-rcampbell@nvidia.com Signed-off-by: Christoph Hellwig Signed-off-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/nouveau/nouveau_svm.c | 2 +- include/linux/hmm.h | 11 ++++- mm/hmm.c | 74 ++++++++++++++++----------------- 4 files changed, 48 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index e51b48ac48eb..12a59ac83f72 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -832,7 +832,7 @@ retry: down_read(&mm->mmap_sem); - r = hmm_range_fault(range, true); + r = hmm_range_fault(range, 0); if (unlikely(r < 0)) { if (likely(r == -EAGAIN)) { /* diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 79b29c918717..49b520c60fc5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -505,7 +505,7 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) return -EBUSY; } - ret = hmm_range_fault(range, true); + ret = hmm_range_fault(range, 0); if (ret <= 0) { if (ret == 0) ret = -EBUSY; diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 4f870f7017cb..89a141060e5b 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -407,12 +407,19 @@ int hmm_range_register(struct hmm_range *range, unsigned long end, unsigned page_shift); void hmm_range_unregister(struct hmm_range *range); + +/* + * Retry fault if non-blocking, drop mmap_sem and return -EAGAIN in that case. + */ +#define HMM_FAULT_ALLOW_RETRY (1 << 0) + long hmm_range_snapshot(struct hmm_range *range); -long hmm_range_fault(struct hmm_range *range, bool block); +long hmm_range_fault(struct hmm_range *range, unsigned int flags); + long hmm_range_dma_map(struct hmm_range *range, struct device *device, dma_addr_t *daddrs, - bool block); + unsigned int flags); long hmm_range_dma_unmap(struct hmm_range *range, struct vm_area_struct *vma, struct device *device, diff --git a/mm/hmm.c b/mm/hmm.c index 362944b0fbca..84f2791d3510 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -281,7 +281,7 @@ struct hmm_vma_walk { struct dev_pagemap *pgmap; unsigned long last; bool fault; - bool block; + unsigned int flags; }; static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr, @@ -293,8 +293,11 @@ static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr, struct vm_area_struct *vma = walk->vma; vm_fault_t ret; - flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY; - flags |= write_fault ? FAULT_FLAG_WRITE : 0; + if (hmm_vma_walk->flags & HMM_FAULT_ALLOW_RETRY) + flags |= FAULT_FLAG_ALLOW_RETRY; + if (write_fault) + flags |= FAULT_FLAG_WRITE; + ret = handle_mm_fault(vma, addr, flags); if (ret & VM_FAULT_RETRY) { /* Note, handle_mm_fault did up_read(&mm->mmap_sem)) */ @@ -1012,26 +1015,26 @@ long hmm_range_snapshot(struct hmm_range *range) } EXPORT_SYMBOL(hmm_range_snapshot); -/* - * hmm_range_fault() - try to fault some address in a virtual address range - * @range: range being faulted - * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem) - * Return: number of valid pages in range->pfns[] (from range start - * address). This may be zero. If the return value is negative, - * then one of the following values may be returned: +/** + * hmm_range_fault - try to fault some address in a virtual address range + * @range: range being faulted + * @flags: HMM_FAULT_* flags * - * -EINVAL invalid arguments or mm or virtual address are in an - * invalid vma (for instance device file vma). - * -ENOMEM: Out of memory. - * -EPERM: Invalid permission (for instance asking for write and - * range is read only). - * -EAGAIN: If you need to retry and mmap_sem was drop. This can only - * happens if block argument is false. - * -EBUSY: If the the range is being invalidated and you should wait - * for invalidation to finish. - * -EFAULT: Invalid (ie either no valid vma or it is illegal to access - * that range), number of valid pages in range->pfns[] (from - * range start address). + * Return: the number of valid pages in range->pfns[] (from range start + * address), which may be zero. On error one of the following status codes + * can be returned: + * + * -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma + * (e.g., device file vma). + * -ENOMEM: Out of memory. + * -EPERM: Invalid permission (e.g., asking for write and range is read + * only). + * -EAGAIN: A page fault needs to be retried and mmap_sem was dropped. + * -EBUSY: The range has been invalidated and the caller needs to wait for + * the invalidation to finish. + * -EFAULT: Invalid (i.e., either no valid vma or it is illegal to access + * that range) number of valid pages in range->pfns[] (from + * range start address). * * This is similar to a regular CPU page fault except that it will not trigger * any memory migration if the memory being faulted is not accessible by CPUs @@ -1040,7 +1043,7 @@ EXPORT_SYMBOL(hmm_range_snapshot); * On error, for one virtual address in the range, the function will mark the * corresponding HMM pfn entry with an error flag. */ -long hmm_range_fault(struct hmm_range *range, bool block) +long hmm_range_fault(struct hmm_range *range, unsigned int flags) { const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP; unsigned long start = range->start, end; @@ -1086,7 +1089,7 @@ long hmm_range_fault(struct hmm_range *range, bool block) hmm_vma_walk.pgmap = NULL; hmm_vma_walk.last = start; hmm_vma_walk.fault = true; - hmm_vma_walk.block = block; + hmm_vma_walk.flags = flags; hmm_vma_walk.range = range; mm_walk.private = &hmm_vma_walk; end = min(range->end, vma->vm_end); @@ -1125,25 +1128,22 @@ long hmm_range_fault(struct hmm_range *range, bool block) EXPORT_SYMBOL(hmm_range_fault); /** - * hmm_range_dma_map() - hmm_range_fault() and dma map page all in one. - * @range: range being faulted - * @device: device against to dma map page to - * @daddrs: dma address of mapped pages - * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem) - * Return: number of pages mapped on success, -EAGAIN if mmap_sem have been - * drop and you need to try again, some other error value otherwise + * hmm_range_dma_map - hmm_range_fault() and dma map page all in one. + * @range: range being faulted + * @device: device to map page to + * @daddrs: array of dma addresses for the mapped pages + * @flags: HMM_FAULT_* * - * Note same usage pattern as hmm_range_fault(). + * Return: the number of pages mapped on success (including zero), or any + * status return from hmm_range_fault() otherwise. */ -long hmm_range_dma_map(struct hmm_range *range, - struct device *device, - dma_addr_t *daddrs, - bool block) +long hmm_range_dma_map(struct hmm_range *range, struct device *device, + dma_addr_t *daddrs, unsigned int flags) { unsigned long i, npages, mapped; long ret; - ret = hmm_range_fault(range, block); + ret = hmm_range_fault(range, flags); if (ret <= 0) return ret ? ret : -EBUSY; -- cgit v1.2.3-71-gd317 From d45d464b118f428229d91769c8a3cc1e2e0bb4d5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 25 Jul 2019 17:56:47 -0700 Subject: mm/hmm: merge hmm_range_snapshot into hmm_range_fault Add a HMM_FAULT_SNAPSHOT flag so that hmm_range_snapshot can be merged into the almost identical hmm_range_fault function. Link: https://lore.kernel.org/r/20190726005650.2566-5-rcampbell@nvidia.com Signed-off-by: Christoph Hellwig Signed-off-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- Documentation/vm/hmm.rst | 17 +++++----- include/linux/hmm.h | 4 ++- mm/hmm.c | 85 ++---------------------------------------------- 3 files changed, 13 insertions(+), 93 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index 710ce1c701bf..ddcb5ca8b296 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -192,15 +192,14 @@ read only, or fully unmap, etc.). The device must complete the update before the driver callback returns. When the device driver wants to populate a range of virtual addresses, it can -use either:: +use:: - long hmm_range_snapshot(struct hmm_range *range); - long hmm_range_fault(struct hmm_range *range, bool block); + long hmm_range_fault(struct hmm_range *range, unsigned int flags); -The first one (hmm_range_snapshot()) will only fetch present CPU page table +With the HMM_RANGE_SNAPSHOT flag, it will only fetch present CPU page table entries and will not trigger a page fault on missing or non-present entries. -The second one does trigger a page fault on missing or read-only entries if -write access is requested (see below). Page faults use the generic mm page +Without that flag, it does trigger a page fault on missing or read-only entries +if write access is requested (see below). Page faults use the generic mm page fault code path just like a CPU page fault. Both functions copy CPU page table entries into their pfns array argument. Each @@ -227,20 +226,20 @@ The usage pattern is:: /* * Just wait for range to be valid, safe to ignore return value as we - * will use the return value of hmm_range_snapshot() below under the + * will use the return value of hmm_range_fault() below under the * mmap_sem to ascertain the validity of the range. */ hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC); again: down_read(&mm->mmap_sem); - ret = hmm_range_snapshot(&range); + ret = hmm_range_fault(&range, HMM_RANGE_SNAPSHOT); if (ret) { up_read(&mm->mmap_sem); if (ret == -EBUSY) { /* * No need to check hmm_range_wait_until_valid() return value - * on retry we will get proper error with hmm_range_snapshot() + * on retry we will get proper error with hmm_range_fault() */ hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC); goto again; diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 89a141060e5b..90dc5944b1bc 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -413,7 +413,9 @@ void hmm_range_unregister(struct hmm_range *range); */ #define HMM_FAULT_ALLOW_RETRY (1 << 0) -long hmm_range_snapshot(struct hmm_range *range); +/* Don't fault in missing PTEs, just snapshot the current state. */ +#define HMM_FAULT_SNAPSHOT (1 << 1) + long hmm_range_fault(struct hmm_range *range, unsigned int flags); long hmm_range_dma_map(struct hmm_range *range, diff --git a/mm/hmm.c b/mm/hmm.c index 84f2791d3510..1bc014cddd78 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -280,7 +280,6 @@ struct hmm_vma_walk { struct hmm_range *range; struct dev_pagemap *pgmap; unsigned long last; - bool fault; unsigned int flags; }; @@ -373,7 +372,7 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk, { struct hmm_range *range = hmm_vma_walk->range; - if (!hmm_vma_walk->fault) + if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) return; /* @@ -418,7 +417,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, { unsigned long i; - if (!hmm_vma_walk->fault) { + if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) { *fault = *write_fault = false; return; } @@ -936,85 +935,6 @@ void hmm_range_unregister(struct hmm_range *range) } EXPORT_SYMBOL(hmm_range_unregister); -/* - * hmm_range_snapshot() - snapshot CPU page table for a range - * @range: range - * Return: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid - * permission (for instance asking for write and range is read only), - * -EBUSY if you need to retry, -EFAULT invalid (ie either no valid - * vma or it is illegal to access that range), number of valid pages - * in range->pfns[] (from range start address). - * - * This snapshots the CPU page table for a range of virtual addresses. Snapshot - * validity is tracked by range struct. See in include/linux/hmm.h for example - * on how to use. - */ -long hmm_range_snapshot(struct hmm_range *range) -{ - const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP; - unsigned long start = range->start, end; - struct hmm_vma_walk hmm_vma_walk; - struct hmm *hmm = range->hmm; - struct vm_area_struct *vma; - struct mm_walk mm_walk; - - lockdep_assert_held(&hmm->mm->mmap_sem); - do { - /* If range is no longer valid force retry. */ - if (!range->valid) - return -EBUSY; - - vma = find_vma(hmm->mm, start); - if (vma == NULL || (vma->vm_flags & device_vma)) - return -EFAULT; - - if (is_vm_hugetlb_page(vma)) { - if (huge_page_shift(hstate_vma(vma)) != - range->page_shift && - range->page_shift != PAGE_SHIFT) - return -EINVAL; - } else { - if (range->page_shift != PAGE_SHIFT) - return -EINVAL; - } - - if (!(vma->vm_flags & VM_READ)) { - /* - * If vma do not allow read access, then assume that it - * does not allow write access, either. HMM does not - * support architecture that allow write without read. - */ - hmm_pfns_clear(range, range->pfns, - range->start, range->end); - return -EPERM; - } - - range->vma = vma; - hmm_vma_walk.pgmap = NULL; - hmm_vma_walk.last = start; - hmm_vma_walk.fault = false; - hmm_vma_walk.range = range; - mm_walk.private = &hmm_vma_walk; - end = min(range->end, vma->vm_end); - - mm_walk.vma = vma; - mm_walk.mm = vma->vm_mm; - mm_walk.pte_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.hugetlb_entry = NULL; - mm_walk.pud_entry = hmm_vma_walk_pud; - mm_walk.pmd_entry = hmm_vma_walk_pmd; - mm_walk.pte_hole = hmm_vma_walk_hole; - mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry; - - walk_page_range(start, end, &mm_walk); - start = end; - } while (start < range->end); - - return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; -} -EXPORT_SYMBOL(hmm_range_snapshot); - /** * hmm_range_fault - try to fault some address in a virtual address range * @range: range being faulted @@ -1088,7 +1008,6 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) range->vma = vma; hmm_vma_walk.pgmap = NULL; hmm_vma_walk.last = start; - hmm_vma_walk.fault = true; hmm_vma_walk.flags = flags; hmm_vma_walk.range = range; mm_walk.private = &hmm_vma_walk; -- cgit v1.2.3-71-gd317 From ef11a931bd1c57b02fe2603ff95a392a73041f9e Mon Sep 17 00:00:00 2001 From: John Crispin Date: Tue, 18 Jun 2019 08:19:14 +0200 Subject: mac80211: HE: add Spatial Reuse element parsing support Add support to mac80211 for parsing SPR elements as per P802.11ax_D4.0 section 9.4.2.241. Signed-off-by: Shashidhar Lakkavalli Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20190618061915.7102-2-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++ net/mac80211/ieee80211_i.h | 1 + net/mac80211/util.c | 4 ++++ 3 files changed, 54 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f36144eda5d6..a656f31262f1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1633,6 +1633,18 @@ struct ieee80211_he_operation { u8 optional[0]; } __packed; +/** + * struct ieee80211_he_spr - HE spatial reuse element + * + * This structure is the "HE spatial reuse element" element as + * described in P802.11ax_D4.0 section 9.4.2.241 + */ +struct ieee80211_he_spr { + u8 he_sr_control; + /* Optional 0 to 19 bytes: depends on @he_sr_control */ + u8 optional[0]; +} __packed; + /** * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field * @@ -2071,6 +2083,42 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) return oper_len; } +/* HE Spatial Reuse defines */ +#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT 0x4 +#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT 0x8 + +/* + * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size + * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the the byte + * after the ext ID byte. It is assumed that he_spr_ie has at least + * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated + * this + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_spr_size(const u8 *he_spr_ie) +{ + struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; + u8 spr_len = sizeof(struct ieee80211_he_spr); + u32 he_spr_params; + + /* Make sure the input is not NULL */ + if (!he_spr_ie) + return 0; + + /* Calc required length */ + he_spr_params = le32_to_cpu(he_spr->he_sr_control); + if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) + spr_len++; + if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) + spr_len += 18; + + /* Add the first byte (extension ID) to the total length */ + spr_len++; + + return spr_len; +} + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -2493,6 +2541,7 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_HE_OPERATION = 36, WLAN_EID_EXT_UORA = 37, WLAN_EID_EXT_HE_MU_EDCA = 38, + WLAN_EID_EXT_HE_SPR = 39, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, WLAN_EID_EXT_NON_INHERITANCE = 56, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 4c80c0ed67a7..472c5a40317d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1480,6 +1480,7 @@ struct ieee802_11_elems { const struct ieee80211_meshconf_ie *mesh_config; const u8 *he_cap; const struct ieee80211_he_operation *he_operation; + const struct ieee80211_he_spr *he_spr; const struct ieee80211_mu_edca_param_set *mu_edca_param_set; const u8 *uora_element; const u8 *mesh_id; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3441558ef2d2..3e2aeb1a75b4 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1240,6 +1240,10 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION && elen == 3) { elems->mbssid_config_ie = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_HE_SPR && + elen >= sizeof(*elems->he_spr) && + elen >= ieee80211_he_spr_size(&pos[1])) { + elems->he_spr = (void *)&pos[1]; } break; default: -- cgit v1.2.3-71-gd317 From cc374377a19d2a49d693997b62dc3a6f5fac6d61 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Thu, 25 Jul 2019 17:56:50 -0700 Subject: mm/hmm: remove hmm_range vma Since hmm_range_fault() doesn't use the struct hmm_range vma field, remove it. Link: https://lore.kernel.org/r/20190726005650.2566-8-rcampbell@nvidia.com Suggested-by: Jason Gunthorpe Signed-off-by: Ralph Campbell Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/nouveau/nouveau_svm.c | 7 +++---- include/linux/hmm.h | 1 - mm/hmm.c | 1 - 3 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 49b520c60fc5..a74530b5a523 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -496,12 +496,12 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) range->start, range->end, PAGE_SHIFT); if (ret) { - up_read(&range->vma->vm_mm->mmap_sem); + up_read(&range->hmm->mm->mmap_sem); return (int)ret; } if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { - up_read(&range->vma->vm_mm->mmap_sem); + up_read(&range->hmm->mm->mmap_sem); return -EBUSY; } @@ -509,7 +509,7 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) if (ret <= 0) { if (ret == 0) ret = -EBUSY; - up_read(&range->vma->vm_mm->mmap_sem); + up_read(&range->hmm->mm->mmap_sem); hmm_range_unregister(range); return ret; } @@ -682,7 +682,6 @@ nouveau_svm_fault(struct nvif_notify *notify) args.i.p.addr + args.i.p.size, fn - fi); /* Have HMM fault pages within the fault window to the GPU. */ - range.vma = vma; range.start = args.i.p.addr; range.end = args.i.p.addr + args.i.p.size; range.pfns = args.phys; diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 90dc5944b1bc..82265118d94a 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -164,7 +164,6 @@ enum hmm_pfn_value_e { */ struct hmm_range { struct hmm *hmm; - struct vm_area_struct *vma; struct list_head list; unsigned long start; unsigned long end; diff --git a/mm/hmm.c b/mm/hmm.c index 6111c0a3c12d..9a908902e4cc 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -1002,7 +1002,6 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) return -EPERM; } - range->vma = vma; hmm_vma_walk.pgmap = NULL; hmm_vma_walk.last = start; hmm_vma_walk.flags = flags; -- cgit v1.2.3-71-gd317 From 934d24a5e1508e73c0001afb54a3916e4270428f Mon Sep 17 00:00:00 2001 From: Vitor Soares Date: Fri, 19 Jul 2019 15:30:54 +0200 Subject: i3c: move i3c_device_match_id to device.c and export it Some I3C device drivers need to know which entry matches the i3c_device object passed to the probe function Let's move i3c_device_match_id() to device.c and export it so it can be used by drivers. Signed-off-by: Vitor Soares Signed-off-by: Boris Brezillon --- drivers/i3c/device.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/i3c/master.c | 45 --------------------------------------- include/linux/i3c/device.h | 4 ++++ 3 files changed, 57 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/drivers/i3c/device.c b/drivers/i3c/device.c index 69cc040c3a1c..9e2e1406f85e 100644 --- a/drivers/i3c/device.c +++ b/drivers/i3c/device.c @@ -200,6 +200,59 @@ struct i3c_device *dev_to_i3cdev(struct device *dev) } EXPORT_SYMBOL_GPL(dev_to_i3cdev); +/** + * i3c_device_match_id() - Returns the i3c_device_id entry matching @i3cdev + * @i3cdev: I3C device + * @id_table: I3C device match table + * + * Return: a pointer to an i3c_device_id object or NULL if there's no match. + */ +const struct i3c_device_id * +i3c_device_match_id(struct i3c_device *i3cdev, + const struct i3c_device_id *id_table) +{ + struct i3c_device_info devinfo; + const struct i3c_device_id *id; + + i3c_device_get_info(i3cdev, &devinfo); + + /* + * The lower 32bits of the provisional ID is just filled with a random + * value, try to match using DCR info. + */ + if (!I3C_PID_RND_LOWER_32BITS(devinfo.pid)) { + u16 manuf = I3C_PID_MANUF_ID(devinfo.pid); + u16 part = I3C_PID_PART_ID(devinfo.pid); + u16 ext_info = I3C_PID_EXTRA_INFO(devinfo.pid); + + /* First try to match by manufacturer/part ID. */ + for (id = id_table; id->match_flags != 0; id++) { + if ((id->match_flags & I3C_MATCH_MANUF_AND_PART) != + I3C_MATCH_MANUF_AND_PART) + continue; + + if (manuf != id->manuf_id || part != id->part_id) + continue; + + if ((id->match_flags & I3C_MATCH_EXTRA_INFO) && + ext_info != id->extra_info) + continue; + + return id; + } + } + + /* Fallback to DCR match. */ + for (id = id_table; id->match_flags != 0; id++) { + if ((id->match_flags & I3C_MATCH_DCR) && + id->dcr == devinfo.dcr) + return id; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(i3c_device_match_id); + /** * i3c_driver_register_with_owner() - register an I3C device driver * diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index d6f8b038a896..c58729081899 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -276,51 +276,6 @@ static const struct device_type i3c_device_type = { .uevent = i3c_device_uevent, }; -static const struct i3c_device_id * -i3c_device_match_id(struct i3c_device *i3cdev, - const struct i3c_device_id *id_table) -{ - struct i3c_device_info devinfo; - const struct i3c_device_id *id; - - i3c_device_get_info(i3cdev, &devinfo); - - /* - * The lower 32bits of the provisional ID is just filled with a random - * value, try to match using DCR info. - */ - if (!I3C_PID_RND_LOWER_32BITS(devinfo.pid)) { - u16 manuf = I3C_PID_MANUF_ID(devinfo.pid); - u16 part = I3C_PID_PART_ID(devinfo.pid); - u16 ext_info = I3C_PID_EXTRA_INFO(devinfo.pid); - - /* First try to match by manufacturer/part ID. */ - for (id = id_table; id->match_flags != 0; id++) { - if ((id->match_flags & I3C_MATCH_MANUF_AND_PART) != - I3C_MATCH_MANUF_AND_PART) - continue; - - if (manuf != id->manuf_id || part != id->part_id) - continue; - - if ((id->match_flags & I3C_MATCH_EXTRA_INFO) && - ext_info != id->extra_info) - continue; - - return id; - } - } - - /* Fallback to DCR match. */ - for (id = id_table; id->match_flags != 0; id++) { - if ((id->match_flags & I3C_MATCH_DCR) && - id->dcr == devinfo.dcr) - return id; - } - - return NULL; -} - static int i3c_device_match(struct device *dev, struct device_driver *drv) { struct i3c_device *i3cdev; diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index 5ecb055fd375..de102e4418ab 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -188,6 +188,10 @@ static inline struct i3c_driver *drv_to_i3cdrv(struct device_driver *drv) struct device *i3cdev_to_dev(struct i3c_device *i3cdev); struct i3c_device *dev_to_i3cdev(struct device *dev); +const struct i3c_device_id * +i3c_device_match_id(struct i3c_device *i3cdev, + const struct i3c_device_id *id_table); + static inline void i3cdev_set_drvdata(struct i3c_device *i3cdev, void *data) { -- cgit v1.2.3-71-gd317 From 6fc4dbcf0276279d488c5fbbfabe94734134f4fa Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 18 Jul 2019 23:01:46 +0800 Subject: padata: Replace delayed timer with immediate workqueue in padata_reorder The function padata_reorder will use a timer when it cannot progress while completed jobs are outstanding (pd->reorder_objects > 0). This is suboptimal as if we do end up using the timer then it would have introduced a gratuitous delay of one second. In fact we can easily distinguish between whether completed jobs are outstanding and whether we can make progress. All we have to do is look at the next pqueue list. This patch does that by replacing pd->processed with pd->cpu so that the next pqueue is more accessible. A work queue is used instead of the original try_again to avoid hogging the CPU. Note that we don't bother removing the work queue in padata_flush_queues because the whole premise is broken. You cannot flush async crypto requests so it makes no sense to even try. A subsequent patch will fix it by replacing it with a ref counting scheme. Signed-off-by: Herbert Xu --- include/linux/padata.h | 13 +++---- kernel/padata.c | 97 ++++++++++---------------------------------------- 2 files changed, 22 insertions(+), 88 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 56f09e36f770..8da673861d99 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -12,7 +12,6 @@ #include #include #include -#include #include #include @@ -73,18 +72,14 @@ struct padata_serial_queue { * @serial: List to wait for serialization after reordering. * @pwork: work struct for parallelization. * @swork: work struct for serialization. - * @pd: Backpointer to the internal control structure. * @work: work struct for parallelization. - * @reorder_work: work struct for reordering. * @num_obj: Number of objects that are processed by this cpu. * @cpu_index: Index of the cpu. */ struct padata_parallel_queue { struct padata_list parallel; struct padata_list reorder; - struct parallel_data *pd; struct work_struct work; - struct work_struct reorder_work; atomic_t num_obj; int cpu_index; }; @@ -110,10 +105,10 @@ struct padata_cpumask { * @reorder_objects: Number of objects waiting in the reorder queues. * @refcnt: Number of objects holding a reference on this parallel_data. * @max_seq_nr: Maximal used sequence number. + * @cpu: Next CPU to be processed. * @cpumask: The cpumasks in use for parallel and serial workers. + * @reorder_work: work struct for reordering. * @lock: Reorder lock. - * @processed: Number of already processed objects. - * @timer: Reorder timer. */ struct parallel_data { struct padata_instance *pinst; @@ -122,10 +117,10 @@ struct parallel_data { atomic_t reorder_objects; atomic_t refcnt; atomic_t seq_nr; + int cpu; struct padata_cpumask cpumask; + struct work_struct reorder_work; spinlock_t lock ____cacheline_aligned; - unsigned int processed; - struct timer_list timer; }; /** diff --git a/kernel/padata.c b/kernel/padata.c index 15a8ad63f4ff..fbafca18597f 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -165,23 +165,12 @@ EXPORT_SYMBOL(padata_do_parallel); */ static struct padata_priv *padata_get_next(struct parallel_data *pd) { - int cpu, num_cpus; - unsigned int next_nr, next_index; struct padata_parallel_queue *next_queue; struct padata_priv *padata; struct padata_list *reorder; + int cpu = pd->cpu; - num_cpus = cpumask_weight(pd->cpumask.pcpu); - - /* - * Calculate the percpu reorder queue and the sequence - * number of the next object. - */ - next_nr = pd->processed; - next_index = next_nr % num_cpus; - cpu = padata_index_to_cpu(pd, next_index); next_queue = per_cpu_ptr(pd->pqueue, cpu); - reorder = &next_queue->reorder; spin_lock(&reorder->lock); @@ -192,7 +181,8 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd) list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); - pd->processed++; + pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, + false); spin_unlock(&reorder->lock); goto out; @@ -215,6 +205,7 @@ static void padata_reorder(struct parallel_data *pd) struct padata_priv *padata; struct padata_serial_queue *squeue; struct padata_instance *pinst = pd->pinst; + struct padata_parallel_queue *next_queue; /* * We need to ensure that only one cpu can work on dequeueing of @@ -246,7 +237,6 @@ static void padata_reorder(struct parallel_data *pd) * so exit immediately. */ if (PTR_ERR(padata) == -ENODATA) { - del_timer(&pd->timer); spin_unlock_bh(&pd->lock); return; } @@ -265,70 +255,29 @@ static void padata_reorder(struct parallel_data *pd) /* * The next object that needs serialization might have arrived to - * the reorder queues in the meantime, we will be called again - * from the timer function if no one else cares for it. + * the reorder queues in the meantime. * - * Ensure reorder_objects is read after pd->lock is dropped so we see - * an increment from another task in padata_do_serial. Pairs with + * Ensure reorder queue is read after pd->lock is dropped so we see + * new objects from another task in padata_do_serial. Pairs with * smp_mb__after_atomic in padata_do_serial. */ smp_mb(); - if (atomic_read(&pd->reorder_objects) - && !(pinst->flags & PADATA_RESET)) - mod_timer(&pd->timer, jiffies + HZ); - else - del_timer(&pd->timer); - return; + next_queue = per_cpu_ptr(pd->pqueue, pd->cpu); + if (!list_empty(&next_queue->reorder.list)) + queue_work(pinst->wq, &pd->reorder_work); } static void invoke_padata_reorder(struct work_struct *work) { - struct padata_parallel_queue *pqueue; struct parallel_data *pd; local_bh_disable(); - pqueue = container_of(work, struct padata_parallel_queue, reorder_work); - pd = pqueue->pd; + pd = container_of(work, struct parallel_data, reorder_work); padata_reorder(pd); local_bh_enable(); } -static void padata_reorder_timer(struct timer_list *t) -{ - struct parallel_data *pd = from_timer(pd, t, timer); - unsigned int weight; - int target_cpu, cpu; - - cpu = get_cpu(); - - /* We don't lock pd here to not interfere with parallel processing - * padata_reorder() calls on other CPUs. We just need any CPU out of - * the cpumask.pcpu set. It would be nice if it's the right one but - * it doesn't matter if we're off to the next one by using an outdated - * pd->processed value. - */ - weight = cpumask_weight(pd->cpumask.pcpu); - target_cpu = padata_index_to_cpu(pd, pd->processed % weight); - - /* ensure to call the reorder callback on the correct CPU */ - if (cpu != target_cpu) { - struct padata_parallel_queue *pqueue; - struct padata_instance *pinst; - - /* The timer function is serialized wrt itself -- no locking - * needed. - */ - pinst = pd->pinst; - pqueue = per_cpu_ptr(pd->pqueue, target_cpu); - queue_work_on(target_cpu, pinst->wq, &pqueue->reorder_work); - } else { - padata_reorder(pd); - } - - put_cpu(); -} - static void padata_serial_worker(struct work_struct *serial_work) { struct padata_serial_queue *squeue; @@ -376,9 +325,8 @@ void padata_do_serial(struct padata_priv *padata) cpu = get_cpu(); - /* We need to run on the same CPU padata_do_parallel(.., padata, ..) - * was called on -- or, at least, enqueue the padata object into the - * correct per-cpu queue. + /* We need to enqueue the padata object into the correct + * per-cpu queue. */ if (cpu != padata->cpu) { reorder_via_wq = 1; @@ -388,12 +336,12 @@ void padata_do_serial(struct padata_priv *padata) pqueue = per_cpu_ptr(pd->pqueue, cpu); spin_lock(&pqueue->reorder.lock); - atomic_inc(&pd->reorder_objects); list_add_tail(&padata->list, &pqueue->reorder.list); + atomic_inc(&pd->reorder_objects); spin_unlock(&pqueue->reorder.lock); /* - * Ensure the atomic_inc of reorder_objects above is ordered correctly + * Ensure the addition to the reorder list is ordered correctly * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb * in padata_reorder. */ @@ -401,13 +349,7 @@ void padata_do_serial(struct padata_priv *padata) put_cpu(); - /* If we're running on the wrong CPU, call padata_reorder() via a - * kernel worker. - */ - if (reorder_via_wq) - queue_work_on(cpu, pd->pinst->wq, &pqueue->reorder_work); - else - padata_reorder(pd); + padata_reorder(pd); } EXPORT_SYMBOL(padata_do_serial); @@ -463,14 +405,12 @@ static void padata_init_pqueues(struct parallel_data *pd) continue; } - pqueue->pd = pd; pqueue->cpu_index = cpu_index; cpu_index++; __padata_list_init(&pqueue->reorder); __padata_list_init(&pqueue->parallel); INIT_WORK(&pqueue->work, padata_parallel_worker); - INIT_WORK(&pqueue->reorder_work, invoke_padata_reorder); atomic_set(&pqueue->num_obj, 0); } } @@ -498,12 +438,13 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, padata_init_pqueues(pd); padata_init_squeues(pd); - timer_setup(&pd->timer, padata_reorder_timer, 0); atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 0); pd->pinst = pinst; spin_lock_init(&pd->lock); + pd->cpu = cpumask_first(pcpumask); + INIT_WORK(&pd->reorder_work, invoke_padata_reorder); return pd; @@ -538,8 +479,6 @@ static void padata_flush_queues(struct parallel_data *pd) flush_work(&pqueue->work); } - del_timer_sync(&pd->timer); - if (atomic_read(&pd->reorder_objects)) padata_reorder(pd); -- cgit v1.2.3-71-gd317 From ed1f2e85da79274f3dc4092953f1359eb732f0c6 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Thu, 18 Jul 2019 16:28:24 -0700 Subject: iio: cros_ec: Add calibscale for 3d MEMS Add calibration scale support to accel, gyro and magnetometer. Check on eve with current firmware, check reading calibscale returns 1.0, check with newer firmware values are applied. Signed-off-by: Gwendal Grignou Signed-off-by: Jonathan Cameron --- .../iio/common/cros_ec_sensors/cros_ec_sensors.c | 51 +++++++++++++++++++--- .../common/cros_ec_sensors/cros_ec_sensors_core.c | 2 +- drivers/iio/light/cros_ec_light_prox.c | 12 ++--- drivers/iio/pressure/cros_ec_baro.c | 2 - include/linux/iio/common/cros_ec_sensors_core.h | 5 ++- 5 files changed, 57 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index 17af4e0fd5f8..2af09606c438 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -63,10 +63,35 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev, /* Save values */ for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++) - st->core.calib[i] = + st->core.calib[i].offset = st->core.resp->sensor_offset.offset[i]; ret = IIO_VAL_INT; - *val = st->core.calib[idx]; + *val = st->core.calib[idx].offset; + break; + case IIO_CHAN_INFO_CALIBSCALE: + st->core.param.cmd = MOTIONSENSE_CMD_SENSOR_SCALE; + st->core.param.sensor_offset.flags = 0; + + ret = cros_ec_motion_send_host_cmd(&st->core, 0); + if (ret == -EPROTO) { + /* Reading calibscale is not supported on older EC. */ + *val = 1; + *val2 = 0; + ret = IIO_VAL_INT_PLUS_MICRO; + break; + } else if (ret) { + break; + } + + /* Save values */ + for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++) + st->core.calib[i].scale = + st->core.resp->sensor_scale.scale[i]; + + *val = st->core.calib[idx].scale >> 15; + *val2 = ((st->core.calib[idx].scale & 0x7FFF) * 1000000LL) / + MOTION_SENSE_DEFAULT_SCALE; + ret = IIO_VAL_INT_PLUS_MICRO; break; case IIO_CHAN_INFO_SCALE: st->core.param.cmd = MOTIONSENSE_CMD_SENSOR_RANGE; @@ -134,7 +159,7 @@ static int cros_ec_sensors_write(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_CALIBBIAS: - st->core.calib[idx] = val; + st->core.calib[idx].offset = val; /* Send to EC for each axis, even if not complete */ st->core.param.cmd = MOTIONSENSE_CMD_SENSOR_OFFSET; @@ -142,10 +167,25 @@ static int cros_ec_sensors_write(struct iio_dev *indio_dev, MOTION_SENSE_SET_OFFSET; for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++) st->core.param.sensor_offset.offset[i] = - st->core.calib[i]; + st->core.calib[i].offset; st->core.param.sensor_offset.temp = EC_MOTION_SENSE_INVALID_CALIB_TEMP; + ret = cros_ec_motion_send_host_cmd(&st->core, 0); + break; + case IIO_CHAN_INFO_CALIBSCALE: + st->core.calib[idx].scale = val; + /* Send to EC for each axis, even if not complete */ + + st->core.param.cmd = MOTIONSENSE_CMD_SENSOR_SCALE; + st->core.param.sensor_offset.flags = + MOTION_SENSE_SET_OFFSET; + for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++) + st->core.param.sensor_scale.scale[i] = + st->core.calib[i].scale; + st->core.param.sensor_scale.temp = + EC_MOTION_SENSE_INVALID_CALIB_TEMP; + ret = cros_ec_motion_send_host_cmd(&st->core, 0); break; case IIO_CHAN_INFO_SCALE: @@ -206,7 +246,8 @@ static int cros_ec_sensors_probe(struct platform_device *pdev) /* Common part */ channel->info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_CALIBBIAS); + BIT(IIO_CHAN_INFO_CALIBBIAS) | + BIT(IIO_CHAN_INFO_CALIBSCALE); channel->info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_FREQUENCY) | diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index 130362ca421b..96d5aa1f4bd5 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -118,7 +118,7 @@ static ssize_t cros_ec_sensors_calibrate(struct iio_dev *indio_dev, } else { /* Save values */ for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++) - st->calib[i] = st->resp->perform_calib.offset[i]; + st->calib[i].offset = st->resp->perform_calib.offset[i]; } mutex_unlock(&st->cmd_lock); diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c index 308ee6ff2e22..b81746a99f1f 100644 --- a/drivers/iio/light/cros_ec_light_prox.c +++ b/drivers/iio/light/cros_ec_light_prox.c @@ -88,9 +88,10 @@ static int cros_ec_light_prox_read(struct iio_dev *indio_dev, } /* Save values */ - st->core.calib[0] = st->core.resp->sensor_offset.offset[0]; + st->core.calib[0].offset = + st->core.resp->sensor_offset.offset[0]; - *val = st->core.calib[idx]; + *val = st->core.calib[idx].offset; break; case IIO_CHAN_INFO_CALIBSCALE: /* @@ -134,11 +135,12 @@ static int cros_ec_light_prox_write(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_CALIBBIAS: - st->core.calib[idx] = val; + st->core.calib[idx].offset = val; /* Send to EC for each axis, even if not complete */ st->core.param.cmd = MOTIONSENSE_CMD_SENSOR_OFFSET; st->core.param.sensor_offset.flags = MOTION_SENSE_SET_OFFSET; - st->core.param.sensor_offset.offset[0] = st->core.calib[0]; + st->core.param.sensor_offset.offset[0] = + st->core.calib[0].offset; st->core.param.sensor_offset.temp = EC_MOTION_SENSE_INVALID_CALIB_TEMP; if (cros_ec_motion_send_host_cmd(&st->core, 0)) @@ -205,8 +207,6 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev) channel->ext_info = cros_ec_sensors_ext_info; channel->scan_type.sign = 'u'; - state->core.calib[0] = 0; - /* Sensor specific */ switch (state->core.type) { case MOTIONSENSE_TYPE_LIGHT: diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c index 034ce98d6e97..d3acba7ba582 100644 --- a/drivers/iio/pressure/cros_ec_baro.c +++ b/drivers/iio/pressure/cros_ec_baro.c @@ -152,8 +152,6 @@ static int cros_ec_baro_probe(struct platform_device *pdev) channel->ext_info = cros_ec_sensors_ext_info; channel->scan_type.sign = 'u'; - state->core.calib[0] = 0; - /* Sensor specific */ switch (state->core.type) { case MOTIONSENSE_TYPE_BARO: diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h index 0c636b9fe8d7..bb03a252bd04 100644 --- a/include/linux/iio/common/cros_ec_sensors_core.h +++ b/include/linux/iio/common/cros_ec_sensors_core.h @@ -62,7 +62,10 @@ struct cros_ec_sensors_core_state { enum motionsensor_type type; enum motionsensor_location loc; - s16 calib[CROS_EC_SENSOR_MAX_AXIS]; + struct calib_data { + s16 offset; + u16 scale; + } calib[CROS_EC_SENSOR_MAX_AXIS]; u8 samples[CROS_EC_SAMPLE_SIZE]; -- cgit v1.2.3-71-gd317 From 1a981c0586c038710227eb740350f291e77ce365 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 26 Jul 2019 12:27:40 +0200 Subject: net: stmmac: Make MDIO bus reset optional The Tegra EQOS driver already resets the MDIO bus at probe time via the reset GPIO specified in the phy-reset-gpios device tree property. There is no need to reset the bus again later on. This avoids the need to query the device tree for the snps,reset GPIO, which is not part of the Tegra EQOS device tree bindings. This quiesces an error message from the generic bus reset code if it doesn't find the snps,reset related delays. Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 3 +++ drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 4 +++- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 8 +++++++- include/linux/stmmac.h | 1 + 5 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 3a14cdd01f5f..66933332c68e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -333,6 +333,9 @@ static void *tegra_eqos_probe(struct platform_device *pdev, usleep_range(2000, 4000); gpiod_set_value(eqos->reset, 0); + /* MDIO bus was already reset just above */ + data->mdio_bus_data->needs_reset = false; + eqos->rst = devm_reset_control_get(&pdev->dev, "eqos"); if (IS_ERR(eqos->rst)) { err = PTR_ERR(eqos->rst); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 4304c1abc5d1..40c42637ad75 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -348,7 +348,9 @@ int stmmac_mdio_register(struct net_device *ndev) max_addr = PHY_MAX_ADDR; } - new_bus->reset = &stmmac_mdio_reset; + if (mdio_bus_data->needs_reset) + new_bus->reset = &stmmac_mdio_reset; + snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x", new_bus->name, priv->plat->bus_id); new_bus->priv = ndev; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 86f9c07a38cf..d5d08e11c353 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -63,6 +63,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat) plat->has_gmac = 1; plat->force_sf_dma_mode = 1; + plat->mdio_bus_data->needs_reset = true; plat->mdio_bus_data->phy_mask = 0; /* Set default value for multicast hash bins */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 73fc2524372e..333b09564b88 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -342,10 +342,16 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, mdio = true; } - if (mdio) + if (mdio) { plat->mdio_bus_data = devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data), GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + + plat->mdio_bus_data->needs_reset = true; + } + return 0; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7d06241582dd..7b3e354bcd3c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -81,6 +81,7 @@ struct stmmac_mdio_bus_data { unsigned int phy_mask; int *irqs; int probed_phy_irq; + bool needs_reset; }; struct stmmac_dma_cfg { -- cgit v1.2.3-71-gd317 From a090965b882333500d8780e2c1762e17782f413f Mon Sep 17 00:00:00 2001 From: Denis Ciocca Date: Thu, 18 Jul 2019 15:53:43 -0700 Subject: iio:common:st_sensors: add st_sensors_get_settings_index() helper function Extract from st_sensors_check_device_support() function the code that is used to get the specific settings for a device. This will be used as generic extractor by each ST driver. Signed-off-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- drivers/iio/common/st_sensors/st_sensors_core.c | 49 +++++++++++++++++-------- include/linux/iio/common/st_sensors.h | 4 ++ 2 files changed, 38 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 8b22dc241482..3610ca9eaa87 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -633,28 +633,47 @@ static int st_sensors_init_interface_mode(struct iio_dev *indio_dev, return 0; } +/* + * st_sensors_get_settings_index() - get index of the sensor settings for a + * specific device from list of settings + * @name: device name buffer reference. + * @list: sensor settings list. + * @list_length: length of sensor settings list. + * + * Return: non negative number on success (valid index), + * negative error code otherwise. + */ +int st_sensors_get_settings_index(const char *name, + const struct st_sensor_settings *list, + const int list_length) +{ + int i, n; + + for (i = 0; i < list_length; i++) { + for (n = 0; n < ST_SENSORS_MAX_4WAI; n++) { + if (strcmp(name, list[i].sensors_supported[n]) == 0) + return i; + } + } + + return -ENODEV; +} +EXPORT_SYMBOL(st_sensors_get_settings_index); + int st_sensors_check_device_support(struct iio_dev *indio_dev, int num_sensors_list, const struct st_sensor_settings *sensor_settings) { - int i, n, err = 0; - u8 wai; struct st_sensor_data *sdata = iio_priv(indio_dev); + int i, err; + u8 wai; - for (i = 0; i < num_sensors_list; i++) { - for (n = 0; n < ST_SENSORS_MAX_4WAI; n++) { - if (strcmp(indio_dev->name, - sensor_settings[i].sensors_supported[n]) == 0) { - break; - } - } - if (n < ST_SENSORS_MAX_4WAI) - break; - } - if (i == num_sensors_list) { + i = st_sensors_get_settings_index(indio_dev->name, + sensor_settings, num_sensors_list); + if (i < 0) { dev_err(&indio_dev->dev, "device name %s not recognized.\n", - indio_dev->name); - return -ENODEV; + indio_dev->name); + return i; } err = st_sensors_init_interface_mode(indio_dev, &sensor_settings[i]); diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 2948ac99e2da..17fbf3e9b013 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -334,6 +334,10 @@ int st_sensors_set_fullscale_by_gain(struct iio_dev *indio_dev, int scale); int st_sensors_read_info_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *ch, int *val); +int st_sensors_get_settings_index(const char *name, + const struct st_sensor_settings *list, + const int list_length); + int st_sensors_check_device_support(struct iio_dev *indio_dev, int num_sensors_list, const struct st_sensor_settings *sensor_settings); -- cgit v1.2.3-71-gd317 From 1ecd245e0eb23d1c3803474eba75589743d0d1fe Mon Sep 17 00:00:00 2001 From: Denis Ciocca Date: Thu, 18 Jul 2019 15:53:52 -0700 Subject: iio: move 3-wire spi initialization to st_sensors_spi Some devices need to be configured with special bit in order to use spi 3-wire. This was done during device identification phase. Instead, let's move this part as spi specific. Doing this the check_device_support function becomes a simple device id check, so let's rename it. Signed-off-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 4 +- drivers/iio/accel/st_accel_spi.c | 4 +- drivers/iio/common/st_sensors/st_sensors_core.c | 64 ++++++------------------ drivers/iio/common/st_sensors/st_sensors_spi.c | 65 ++++++++++++++++++++++++- drivers/iio/gyro/st_gyro_core.c | 4 +- drivers/iio/gyro/st_gyro_spi.c | 4 +- drivers/iio/magnetometer/st_magn_core.c | 4 +- drivers/iio/magnetometer/st_magn_spi.c | 4 +- drivers/iio/pressure/st_pressure_core.c | 4 +- drivers/iio/pressure/st_pressure_spi.c | 4 +- include/linux/iio/common/st_sensors.h | 3 +- include/linux/iio/common/st_sensors_spi.h | 4 +- 12 files changed, 97 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 6fc490ffef7e..630909702a19 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1183,9 +1183,7 @@ int st_accel_common_probe(struct iio_dev *indio_dev) if (err) return err; - err = st_sensors_check_device_support(indio_dev, - ARRAY_SIZE(st_accel_sensors_settings), - st_accel_sensors_settings); + err = st_sensors_verify_id(indio_dev); if (err < 0) goto st_accel_power_off; diff --git a/drivers/iio/accel/st_accel_spi.c b/drivers/iio/accel/st_accel_spi.c index c0556db9d60a..8af7027d5598 100644 --- a/drivers/iio/accel/st_accel_spi.c +++ b/drivers/iio/accel/st_accel_spi.c @@ -124,7 +124,9 @@ static int st_accel_spi_probe(struct spi_device *spi) adata = iio_priv(indio_dev); adata->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_spi_configure(indio_dev, spi, adata); + err = st_sensors_spi_configure(indio_dev, spi); + if (err < 0) + return err; err = st_accel_common_probe(indio_dev); if (err < 0) diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 3610ca9eaa87..f05bf7cf0594 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -608,31 +608,6 @@ out: } EXPORT_SYMBOL(st_sensors_read_info_raw); -static int st_sensors_init_interface_mode(struct iio_dev *indio_dev, - const struct st_sensor_settings *sensor_settings) -{ - struct st_sensor_data *sdata = iio_priv(indio_dev); - struct device_node *np = sdata->dev->of_node; - struct st_sensors_platform_data *pdata; - - pdata = (struct st_sensors_platform_data *)sdata->dev->platform_data; - if (((np && of_property_read_bool(np, "spi-3wire")) || - (pdata && pdata->spi_3wire)) && sensor_settings->sim.addr) { - int err; - - err = sdata->tf->write_byte(&sdata->tb, sdata->dev, - sensor_settings->sim.addr, - sensor_settings->sim.value); - if (err < 0) { - dev_err(&indio_dev->dev, - "failed to init interface mode\n"); - return err; - } - } - - return 0; -} - /* * st_sensors_get_settings_index() - get index of the sensor settings for a * specific device from list of settings @@ -660,36 +635,30 @@ int st_sensors_get_settings_index(const char *name, } EXPORT_SYMBOL(st_sensors_get_settings_index); -int st_sensors_check_device_support(struct iio_dev *indio_dev, - int num_sensors_list, - const struct st_sensor_settings *sensor_settings) +/* + * st_sensors_verify_id() - verify sensor ID (WhoAmI) is matching with the + * expected value + * @indio_dev: IIO device reference. + * + * Return: 0 on success (valid sensor ID), else a negative error code. + */ +int st_sensors_verify_id(struct iio_dev *indio_dev) { struct st_sensor_data *sdata = iio_priv(indio_dev); - int i, err; + int err; u8 wai; - i = st_sensors_get_settings_index(indio_dev->name, - sensor_settings, num_sensors_list); - if (i < 0) { - dev_err(&indio_dev->dev, "device name %s not recognized.\n", - indio_dev->name); - return i; - } - - err = st_sensors_init_interface_mode(indio_dev, &sensor_settings[i]); - if (err < 0) - return err; - - if (sensor_settings[i].wai_addr) { + if (sdata->sensor_settings->wai_addr) { err = sdata->tf->read_byte(&sdata->tb, sdata->dev, - sensor_settings[i].wai_addr, &wai); + sdata->sensor_settings->wai_addr, + &wai); if (err < 0) { dev_err(&indio_dev->dev, "failed to read Who-Am-I register.\n"); return err; } - if (sensor_settings[i].wai != wai) { + if (sdata->sensor_settings->wai != wai) { dev_err(&indio_dev->dev, "%s: WhoAmI mismatch (0x%x).\n", indio_dev->name, wai); @@ -697,12 +666,9 @@ int st_sensors_check_device_support(struct iio_dev *indio_dev, } } - sdata->sensor_settings = - (struct st_sensor_settings *)&sensor_settings[i]; - - return i; + return 0; } -EXPORT_SYMBOL(st_sensors_check_device_support); +EXPORT_SYMBOL(st_sensors_verify_id); ssize_t st_sensors_sysfs_sampling_frequency_avail(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/iio/common/st_sensors/st_sensors_spi.c b/drivers/iio/common/st_sensors/st_sensors_spi.c index 2213843f02cb..a57cd648975c 100644 --- a/drivers/iio/common/st_sensors/st_sensors_spi.c +++ b/drivers/iio/common/st_sensors/st_sensors_spi.c @@ -102,9 +102,68 @@ static const struct st_sensor_transfer_function st_sensors_tf_spi = { .read_multiple_byte = st_sensors_spi_read_multiple_byte, }; -void st_sensors_spi_configure(struct iio_dev *indio_dev, - struct spi_device *spi, struct st_sensor_data *sdata) +/* + * st_sensors_is_spi_3_wire() - check if SPI 3-wire mode has been selected + * @spi: spi device reference. + * + * Return: true if SPI 3-wire mode is selected, false otherwise. + */ +static bool st_sensors_is_spi_3_wire(struct spi_device *spi) +{ + struct device_node *np = spi->dev.of_node; + struct st_sensors_platform_data *pdata; + + pdata = (struct st_sensors_platform_data *)spi->dev.platform_data; + if ((np && of_property_read_bool(np, "spi-3wire")) || + (pdata && pdata->spi_3wire)) { + return true; + } + + return false; +} + +/* + * st_sensors_configure_spi_3_wire() - configure SPI 3-wire if needed + * @spi: spi device reference. + * @settings: sensor specific settings reference. + * + * Return: 0 on success, else a negative error code. + */ +static int st_sensors_configure_spi_3_wire(struct spi_device *spi, + struct st_sensor_settings *settings) +{ + if (settings->sim.addr) { + u8 buffer[] = { + settings->sim.addr, + settings->sim.value + }; + + return spi_write(spi, buffer, 2); + } + + return 0; +} + +/* + * st_sensors_spi_configure() - configure SPI interface + * @indio_dev: IIO device reference. + * @spi: spi device reference. + * + * Return: 0 on success, else a negative error code. + */ +int st_sensors_spi_configure(struct iio_dev *indio_dev, + struct spi_device *spi) { + struct st_sensor_data *sdata = iio_priv(indio_dev); + int err; + + if (st_sensors_is_spi_3_wire(spi)) { + err = st_sensors_configure_spi_3_wire(spi, + sdata->sensor_settings); + if (err < 0) + return err; + } + spi_set_drvdata(spi, indio_dev); indio_dev->dev.parent = &spi->dev; @@ -113,6 +172,8 @@ void st_sensors_spi_configure(struct iio_dev *indio_dev, sdata->dev = &spi->dev; sdata->tf = &st_sensors_tf_spi; sdata->get_irq_data_ready = st_sensors_spi_get_irq; + + return 0; } EXPORT_SYMBOL(st_sensors_spi_configure); diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index 5cc63d41d855..4b87e79aa744 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -400,9 +400,7 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) if (err) return err; - err = st_sensors_check_device_support(indio_dev, - ARRAY_SIZE(st_gyro_sensors_settings), - st_gyro_sensors_settings); + err = st_sensors_verify_id(indio_dev); if (err < 0) goto st_gyro_power_off; diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c index bb7082055f85..b5c624251231 100644 --- a/drivers/iio/gyro/st_gyro_spi.c +++ b/drivers/iio/gyro/st_gyro_spi.c @@ -91,7 +91,9 @@ static int st_gyro_spi_probe(struct spi_device *spi) gdata = iio_priv(indio_dev); gdata->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_spi_configure(indio_dev, spi, gdata); + err = st_sensors_spi_configure(indio_dev, spi); + if (err < 0) + return err; err = st_gyro_common_probe(indio_dev); if (err < 0) diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 43a49a52c81a..3f313aefece6 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -502,9 +502,7 @@ int st_magn_common_probe(struct iio_dev *indio_dev) if (err) return err; - err = st_sensors_check_device_support(indio_dev, - ARRAY_SIZE(st_magn_sensors_settings), - st_magn_sensors_settings); + err = st_sensors_verify_id(indio_dev); if (err < 0) goto st_magn_power_off; diff --git a/drivers/iio/magnetometer/st_magn_spi.c b/drivers/iio/magnetometer/st_magn_spi.c index a3045afc6b53..fbf909bde841 100644 --- a/drivers/iio/magnetometer/st_magn_spi.c +++ b/drivers/iio/magnetometer/st_magn_spi.c @@ -73,7 +73,9 @@ static int st_magn_spi_probe(struct spi_device *spi) mdata = iio_priv(indio_dev); mdata->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_spi_configure(indio_dev, spi, mdata); + err = st_sensors_spi_configure(indio_dev, spi); + if (err < 0) + return err; err = st_magn_common_probe(indio_dev); if (err < 0) diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index 35d80ff27464..a783fc075c26 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -698,9 +698,7 @@ int st_press_common_probe(struct iio_dev *indio_dev) if (err) return err; - err = st_sensors_check_device_support(indio_dev, - ARRAY_SIZE(st_press_sensors_settings), - st_press_sensors_settings); + err = st_sensors_verify_id(indio_dev); if (err < 0) goto st_press_power_off; diff --git a/drivers/iio/pressure/st_pressure_spi.c b/drivers/iio/pressure/st_pressure_spi.c index 3e8c1ffe001e..7c8b70221e70 100644 --- a/drivers/iio/pressure/st_pressure_spi.c +++ b/drivers/iio/pressure/st_pressure_spi.c @@ -83,7 +83,9 @@ static int st_press_spi_probe(struct spi_device *spi) press_data = iio_priv(indio_dev); press_data->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_spi_configure(indio_dev, spi, press_data); + err = st_sensors_spi_configure(indio_dev, spi); + if (err < 0) + return err; err = st_press_common_probe(indio_dev); if (err < 0) diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 17fbf3e9b013..566b955e2980 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -338,8 +338,7 @@ int st_sensors_get_settings_index(const char *name, const struct st_sensor_settings *list, const int list_length); -int st_sensors_check_device_support(struct iio_dev *indio_dev, - int num_sensors_list, const struct st_sensor_settings *sensor_settings); +int st_sensors_verify_id(struct iio_dev *indio_dev); ssize_t st_sensors_sysfs_sampling_frequency_avail(struct device *dev, struct device_attribute *attr, char *buf); diff --git a/include/linux/iio/common/st_sensors_spi.h b/include/linux/iio/common/st_sensors_spi.h index 6020f7167859..90b25f087f06 100644 --- a/include/linux/iio/common/st_sensors_spi.h +++ b/include/linux/iio/common/st_sensors_spi.h @@ -13,7 +13,7 @@ #include #include -void st_sensors_spi_configure(struct iio_dev *indio_dev, - struct spi_device *spi, struct st_sensor_data *sdata); +int st_sensors_spi_configure(struct iio_dev *indio_dev, + struct spi_device *spi); #endif /* ST_SENSORS_SPI_H */ -- cgit v1.2.3-71-gd317 From 062809ef7733209312562e87cefc84a470430929 Mon Sep 17 00:00:00 2001 From: Denis Ciocca Date: Thu, 18 Jul 2019 15:53:53 -0700 Subject: iio: make st_sensors drivers use regmap This patch is meant to replace the i2c/spi transfer functions with regmap. SPI framework requires DMA safe buffers so let's add GFP_DMA flag for memory allocation used by bulk_read functions. Signed-off-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_buffer.c | 3 +- drivers/iio/accel/st_accel_core.c | 3 - drivers/iio/accel/st_accel_i2c.c | 4 +- drivers/iio/common/st_sensors/st_sensors_buffer.c | 10 +-- drivers/iio/common/st_sensors/st_sensors_core.c | 39 +++----- drivers/iio/common/st_sensors/st_sensors_i2c.c | 73 ++++++++------- drivers/iio/common/st_sensors/st_sensors_spi.c | 100 +++++---------------- drivers/iio/common/st_sensors/st_sensors_trigger.c | 10 +-- drivers/iio/gyro/st_gyro_buffer.c | 3 +- drivers/iio/gyro/st_gyro_core.c | 3 - drivers/iio/gyro/st_gyro_i2c.c | 4 +- drivers/iio/magnetometer/st_magn_buffer.c | 3 +- drivers/iio/magnetometer/st_magn_core.c | 3 - drivers/iio/magnetometer/st_magn_i2c.c | 4 +- drivers/iio/pressure/st_pressure_buffer.c | 3 +- drivers/iio/pressure/st_pressure_core.c | 3 - drivers/iio/pressure/st_pressure_i2c.c | 4 +- include/linux/iio/common/st_sensors.h | 40 +-------- include/linux/iio/common/st_sensors_i2c.h | 4 +- 19 files changed, 104 insertions(+), 212 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel_buffer.c b/drivers/iio/accel/st_accel_buffer.c index 0205c0167cdd..05f9aea431e2 100644 --- a/drivers/iio/accel/st_accel_buffer.c +++ b/drivers/iio/accel/st_accel_buffer.c @@ -39,7 +39,8 @@ static int st_accel_buffer_postenable(struct iio_dev *indio_dev) int err; struct st_sensor_data *adata = iio_priv(indio_dev); - adata->buffer_data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL); + adata->buffer_data = kmalloc(indio_dev->scan_bytes, + GFP_DMA | GFP_KERNEL); if (adata->buffer_data == NULL) { err = -ENOMEM; goto allocate_memory_error; diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 630909702a19..0b17004cb12e 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -1177,7 +1176,6 @@ int st_accel_common_probe(struct iio_dev *indio_dev) indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &accel_info; - mutex_init(&adata->tb.buf_lock); err = st_sensors_power_enable(indio_dev); if (err) @@ -1188,7 +1186,6 @@ int st_accel_common_probe(struct iio_dev *indio_dev) goto st_accel_power_off; adata->num_data_channels = ST_ACCEL_NUMBER_DATA_CHANNELS; - adata->multiread_bit = adata->sensor_settings->multi_read_bit; indio_dev->num_channels = ST_SENSORS_NUMBER_ALL_CHANNELS; channels_size = indio_dev->num_channels * sizeof(struct iio_chan_spec); diff --git a/drivers/iio/accel/st_accel_i2c.c b/drivers/iio/accel/st_accel_i2c.c index a92cf776031e..50fa0fc32baa 100644 --- a/drivers/iio/accel/st_accel_i2c.c +++ b/drivers/iio/accel/st_accel_i2c.c @@ -174,7 +174,9 @@ static int st_accel_i2c_probe(struct i2c_client *client) adata = iio_priv(indio_dev); adata->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_i2c_configure(indio_dev, client, adata); + ret = st_sensors_i2c_configure(indio_dev, client); + if (ret < 0) + return ret; ret = st_accel_common_probe(indio_dev); if (ret < 0) diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index 4a68669dc555..eee30130ae23 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -17,15 +17,16 @@ #include #include #include +#include #include static int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) { - int i; struct st_sensor_data *sdata = iio_priv(indio_dev); unsigned int num_data_channels = sdata->num_data_channels; + int i; for_each_set_bit(i, indio_dev->active_scan_mask, num_data_channels) { const struct iio_chan_spec *channel = &indio_dev->channels[i]; @@ -36,11 +37,8 @@ static int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) channel->scan_type.storagebits >> 3; buf = PTR_ALIGN(buf, storage_bytes); - if (sdata->tf->read_multiple_byte(&sdata->tb, sdata->dev, - channel->address, - bytes_to_read, buf, - sdata->multiread_bit) < - bytes_to_read) + if (regmap_bulk_read(sdata->regmap, channel->address, + buf, bytes_to_read) < 0) return -EIO; /* Advance the buffer pointer */ diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index f05bf7cf0594..4a3064fb6cd9 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -28,19 +29,10 @@ static inline u32 st_sensors_get_unaligned_le24(const u8 *p) int st_sensors_write_data_with_mask(struct iio_dev *indio_dev, u8 reg_addr, u8 mask, u8 data) { - int err; - u8 new_data; struct st_sensor_data *sdata = iio_priv(indio_dev); - err = sdata->tf->read_byte(&sdata->tb, sdata->dev, reg_addr, &new_data); - if (err < 0) - goto st_sensors_write_data_with_mask_error; - - new_data = ((new_data & (~mask)) | ((data << __ffs(mask)) & mask)); - err = sdata->tf->write_byte(&sdata->tb, sdata->dev, reg_addr, new_data); - -st_sensors_write_data_with_mask_error: - return err; + return regmap_update_bits(sdata->regmap, + reg_addr, mask, data << __ffs(mask)); } int st_sensors_debugfs_reg_access(struct iio_dev *indio_dev, @@ -48,19 +40,15 @@ int st_sensors_debugfs_reg_access(struct iio_dev *indio_dev, unsigned *readval) { struct st_sensor_data *sdata = iio_priv(indio_dev); - u8 readdata; int err; if (!readval) - return sdata->tf->write_byte(&sdata->tb, sdata->dev, - (u8)reg, (u8)writeval); + return regmap_write(sdata->regmap, reg, writeval); - err = sdata->tf->read_byte(&sdata->tb, sdata->dev, (u8)reg, &readdata); + err = regmap_read(sdata->regmap, reg, readval); if (err < 0) return err; - *readval = (unsigned)readdata; - return 0; } EXPORT_SYMBOL(st_sensors_debugfs_reg_access); @@ -545,7 +533,7 @@ st_sensors_match_scale_error: EXPORT_SYMBOL(st_sensors_set_fullscale_by_gain); static int st_sensors_read_axis_data(struct iio_dev *indio_dev, - struct iio_chan_spec const *ch, int *data) + struct iio_chan_spec const *ch, int *data) { int err; u8 *outdata; @@ -554,13 +542,12 @@ static int st_sensors_read_axis_data(struct iio_dev *indio_dev, byte_for_channel = DIV_ROUND_UP(ch->scan_type.realbits + ch->scan_type.shift, 8); - outdata = kmalloc(byte_for_channel, GFP_KERNEL); + outdata = kmalloc(byte_for_channel, GFP_DMA | GFP_KERNEL); if (!outdata) return -ENOMEM; - err = sdata->tf->read_multiple_byte(&sdata->tb, sdata->dev, - ch->address, byte_for_channel, - outdata, sdata->multiread_bit); + err = regmap_bulk_read(sdata->regmap, ch->address, + outdata, byte_for_channel); if (err < 0) goto st_sensors_free_memory; @@ -645,13 +632,11 @@ EXPORT_SYMBOL(st_sensors_get_settings_index); int st_sensors_verify_id(struct iio_dev *indio_dev) { struct st_sensor_data *sdata = iio_priv(indio_dev); - int err; - u8 wai; + int wai, err; if (sdata->sensor_settings->wai_addr) { - err = sdata->tf->read_byte(&sdata->tb, sdata->dev, - sdata->sensor_settings->wai_addr, - &wai); + err = regmap_read(sdata->regmap, + sdata->sensor_settings->wai_addr, &wai); if (err < 0) { dev_err(&indio_dev->dev, "failed to read Who-Am-I register.\n"); diff --git a/drivers/iio/common/st_sensors/st_sensors_i2c.c b/drivers/iio/common/st_sensors/st_sensors_i2c.c index b1c9812407e7..9240625534df 100644 --- a/drivers/iio/common/st_sensors/st_sensors_i2c.c +++ b/drivers/iio/common/st_sensors/st_sensors_i2c.c @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -26,55 +27,51 @@ static unsigned int st_sensors_i2c_get_irq(struct iio_dev *indio_dev) return to_i2c_client(sdata->dev)->irq; } -static int st_sensors_i2c_read_byte(struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, u8 *res_byte) -{ - int err; - - err = i2c_smbus_read_byte_data(to_i2c_client(dev), reg_addr); - if (err < 0) - goto st_accel_i2c_read_byte_error; - - *res_byte = err & 0xff; - -st_accel_i2c_read_byte_error: - return err < 0 ? err : 0; -} - -static int st_sensors_i2c_read_multiple_byte( - struct st_sensor_transfer_buffer *tb, struct device *dev, - u8 reg_addr, int len, u8 *data, bool multiread_bit) -{ - if (multiread_bit) - reg_addr |= ST_SENSORS_I2C_MULTIREAD; - - return i2c_smbus_read_i2c_block_data_or_emulated(to_i2c_client(dev), - reg_addr, len, data); -} - -static int st_sensors_i2c_write_byte(struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, u8 data) -{ - return i2c_smbus_write_byte_data(to_i2c_client(dev), reg_addr, data); -} +static const struct regmap_config st_sensors_i2c_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; -static const struct st_sensor_transfer_function st_sensors_tf_i2c = { - .read_byte = st_sensors_i2c_read_byte, - .write_byte = st_sensors_i2c_write_byte, - .read_multiple_byte = st_sensors_i2c_read_multiple_byte, +static const struct regmap_config st_sensors_i2c_regmap_multiread_bit_config = { + .reg_bits = 8, + .val_bits = 8, + .read_flag_mask = ST_SENSORS_I2C_MULTIREAD, }; -void st_sensors_i2c_configure(struct iio_dev *indio_dev, - struct i2c_client *client, struct st_sensor_data *sdata) +/* + * st_sensors_i2c_configure() - configure I2C interface + * @indio_dev: IIO device reference. + * @client: i2c client reference. + * + * Return: 0 on success, else a negative error code. + */ +int st_sensors_i2c_configure(struct iio_dev *indio_dev, + struct i2c_client *client) { + struct st_sensor_data *sdata = iio_priv(indio_dev); + const struct regmap_config *config; + + if (sdata->sensor_settings->multi_read_bit) + config = &st_sensors_i2c_regmap_multiread_bit_config; + else + config = &st_sensors_i2c_regmap_config; + + sdata->regmap = devm_regmap_init_i2c(client, config); + if (IS_ERR(sdata->regmap)) { + dev_err(&client->dev, "Failed to register i2c regmap (%d)\n", + (int)PTR_ERR(sdata->regmap)); + return PTR_ERR(sdata->regmap); + } + i2c_set_clientdata(client, indio_dev); indio_dev->dev.parent = &client->dev; indio_dev->name = client->name; sdata->dev = &client->dev; - sdata->tf = &st_sensors_tf_i2c; sdata->get_irq_data_ready = st_sensors_i2c_get_irq; + + return 0; } EXPORT_SYMBOL(st_sensors_i2c_configure); diff --git a/drivers/iio/common/st_sensors/st_sensors_spi.c b/drivers/iio/common/st_sensors/st_sensors_spi.c index a57cd648975c..9c0661a283d0 100644 --- a/drivers/iio/common/st_sensors/st_sensors_spi.c +++ b/drivers/iio/common/st_sensors/st_sensors_spi.c @@ -11,12 +11,12 @@ #include #include #include +#include #include - +#include "st_sensors_core.h" #define ST_SENSORS_SPI_MULTIREAD 0xc0 -#define ST_SENSORS_SPI_READ 0x80 static unsigned int st_sensors_spi_get_irq(struct iio_dev *indio_dev) { @@ -25,81 +25,15 @@ static unsigned int st_sensors_spi_get_irq(struct iio_dev *indio_dev) return to_spi_device(sdata->dev)->irq; } -static int st_sensors_spi_read(struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, int len, u8 *data, bool multiread_bit) -{ - int err; - - struct spi_transfer xfers[] = { - { - .tx_buf = tb->tx_buf, - .bits_per_word = 8, - .len = 1, - }, - { - .rx_buf = tb->rx_buf, - .bits_per_word = 8, - .len = len, - } - }; - - mutex_lock(&tb->buf_lock); - if ((multiread_bit) && (len > 1)) - tb->tx_buf[0] = reg_addr | ST_SENSORS_SPI_MULTIREAD; - else - tb->tx_buf[0] = reg_addr | ST_SENSORS_SPI_READ; - - err = spi_sync_transfer(to_spi_device(dev), xfers, ARRAY_SIZE(xfers)); - if (err) - goto acc_spi_read_error; - - memcpy(data, tb->rx_buf, len); - mutex_unlock(&tb->buf_lock); - return len; - -acc_spi_read_error: - mutex_unlock(&tb->buf_lock); - return err; -} - -static int st_sensors_spi_read_byte(struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, u8 *res_byte) -{ - return st_sensors_spi_read(tb, dev, reg_addr, 1, res_byte, false); -} - -static int st_sensors_spi_read_multiple_byte( - struct st_sensor_transfer_buffer *tb, struct device *dev, - u8 reg_addr, int len, u8 *data, bool multiread_bit) -{ - return st_sensors_spi_read(tb, dev, reg_addr, len, data, multiread_bit); -} - -static int st_sensors_spi_write_byte(struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, u8 data) -{ - int err; - - struct spi_transfer xfers = { - .tx_buf = tb->tx_buf, - .bits_per_word = 8, - .len = 2, - }; - - mutex_lock(&tb->buf_lock); - tb->tx_buf[0] = reg_addr; - tb->tx_buf[1] = data; - - err = spi_sync_transfer(to_spi_device(dev), &xfers, 1); - mutex_unlock(&tb->buf_lock); - - return err; -} +static const struct regmap_config st_sensors_spi_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; -static const struct st_sensor_transfer_function st_sensors_tf_spi = { - .read_byte = st_sensors_spi_read_byte, - .write_byte = st_sensors_spi_write_byte, - .read_multiple_byte = st_sensors_spi_read_multiple_byte, +static const struct regmap_config st_sensors_spi_regmap_multiread_bit_config = { + .reg_bits = 8, + .val_bits = 8, + .read_flag_mask = ST_SENSORS_SPI_MULTIREAD, }; /* @@ -155,6 +89,7 @@ int st_sensors_spi_configure(struct iio_dev *indio_dev, struct spi_device *spi) { struct st_sensor_data *sdata = iio_priv(indio_dev); + const struct regmap_config *config; int err; if (st_sensors_is_spi_3_wire(spi)) { @@ -164,13 +99,24 @@ int st_sensors_spi_configure(struct iio_dev *indio_dev, return err; } + if (sdata->sensor_settings->multi_read_bit) + config = &st_sensors_spi_regmap_multiread_bit_config; + else + config = &st_sensors_spi_regmap_config; + + sdata->regmap = devm_regmap_init_spi(spi, config); + if (IS_ERR(sdata->regmap)) { + dev_err(&spi->dev, "Failed to register spi regmap (%d)\n", + (int)PTR_ERR(sdata->regmap)); + return PTR_ERR(sdata->regmap); + } + spi_set_drvdata(spi, indio_dev); indio_dev->dev.parent = &spi->dev; indio_dev->name = spi->modalias; sdata->dev = &spi->dev; - sdata->tf = &st_sensors_tf_spi; sdata->get_irq_data_ready = st_sensors_spi_get_irq; return 0; diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 630c8cb35e8b..bed7b8682b17 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "st_sensors_core.h" @@ -26,8 +27,7 @@ static int st_sensors_new_samples_available(struct iio_dev *indio_dev, struct st_sensor_data *sdata) { - u8 status; - int ret; + int ret, status; /* How would I know if I can't check it? */ if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) @@ -37,9 +37,9 @@ static int st_sensors_new_samples_available(struct iio_dev *indio_dev, if (!indio_dev->active_scan_mask) return 0; - ret = sdata->tf->read_byte(&sdata->tb, sdata->dev, - sdata->sensor_settings->drdy_irq.stat_drdy.addr, - &status); + ret = regmap_read(sdata->regmap, + sdata->sensor_settings->drdy_irq.stat_drdy.addr, + &status); if (ret < 0) { dev_err(sdata->dev, "error checking samples available\n"); diff --git a/drivers/iio/gyro/st_gyro_buffer.c b/drivers/iio/gyro/st_gyro_buffer.c index 6e362f735e92..21360681d4dd 100644 --- a/drivers/iio/gyro/st_gyro_buffer.c +++ b/drivers/iio/gyro/st_gyro_buffer.c @@ -39,7 +39,8 @@ static int st_gyro_buffer_postenable(struct iio_dev *indio_dev) int err; struct st_sensor_data *gdata = iio_priv(indio_dev); - gdata->buffer_data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL); + gdata->buffer_data = kmalloc(indio_dev->scan_bytes, + GFP_DMA | GFP_KERNEL); if (gdata->buffer_data == NULL) { err = -ENOMEM; goto allocate_memory_error; diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index 4b87e79aa744..02e42c945181 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -394,7 +393,6 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &gyro_info; - mutex_init(&gdata->tb.buf_lock); err = st_sensors_power_enable(indio_dev); if (err) @@ -405,7 +403,6 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) goto st_gyro_power_off; gdata->num_data_channels = ST_GYRO_NUMBER_DATA_CHANNELS; - gdata->multiread_bit = gdata->sensor_settings->multi_read_bit; indio_dev->channels = gdata->sensor_settings->ch; indio_dev->num_channels = ST_SENSORS_NUMBER_ALL_CHANNELS; diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c index fa71e94b76f4..05a1a0874bd5 100644 --- a/drivers/iio/gyro/st_gyro_i2c.c +++ b/drivers/iio/gyro/st_gyro_i2c.c @@ -87,7 +87,9 @@ static int st_gyro_i2c_probe(struct i2c_client *client, gdata = iio_priv(indio_dev); gdata->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_i2c_configure(indio_dev, client, gdata); + err = st_sensors_i2c_configure(indio_dev, client); + if (err < 0) + return err; err = st_gyro_common_probe(indio_dev); if (err < 0) diff --git a/drivers/iio/magnetometer/st_magn_buffer.c b/drivers/iio/magnetometer/st_magn_buffer.c index 11d7806655bc..9dba93539a99 100644 --- a/drivers/iio/magnetometer/st_magn_buffer.c +++ b/drivers/iio/magnetometer/st_magn_buffer.c @@ -34,7 +34,8 @@ static int st_magn_buffer_postenable(struct iio_dev *indio_dev) int err; struct st_sensor_data *mdata = iio_priv(indio_dev); - mdata->buffer_data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL); + mdata->buffer_data = kmalloc(indio_dev->scan_bytes, + GFP_DMA | GFP_KERNEL); if (mdata->buffer_data == NULL) { err = -ENOMEM; goto allocate_memory_error; diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 3f313aefece6..804353a483c7 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -496,7 +495,6 @@ int st_magn_common_probe(struct iio_dev *indio_dev) indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &magn_info; - mutex_init(&mdata->tb.buf_lock); err = st_sensors_power_enable(indio_dev); if (err) @@ -507,7 +505,6 @@ int st_magn_common_probe(struct iio_dev *indio_dev) goto st_magn_power_off; mdata->num_data_channels = ST_MAGN_NUMBER_DATA_CHANNELS; - mdata->multiread_bit = mdata->sensor_settings->multi_read_bit; indio_dev->channels = mdata->sensor_settings->ch; indio_dev->num_channels = ST_SENSORS_NUMBER_ALL_CHANNELS; diff --git a/drivers/iio/magnetometer/st_magn_i2c.c b/drivers/iio/magnetometer/st_magn_i2c.c index d5d565639bed..fdba480a12be 100644 --- a/drivers/iio/magnetometer/st_magn_i2c.c +++ b/drivers/iio/magnetometer/st_magn_i2c.c @@ -79,7 +79,9 @@ static int st_magn_i2c_probe(struct i2c_client *client, mdata = iio_priv(indio_dev); mdata->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_i2c_configure(indio_dev, client, mdata); + err = st_sensors_i2c_configure(indio_dev, client); + if (err < 0) + return err; err = st_magn_common_probe(indio_dev); if (err < 0) diff --git a/drivers/iio/pressure/st_pressure_buffer.c b/drivers/iio/pressure/st_pressure_buffer.c index 4566e08a64a1..f21b630abaa0 100644 --- a/drivers/iio/pressure/st_pressure_buffer.c +++ b/drivers/iio/pressure/st_pressure_buffer.c @@ -39,7 +39,8 @@ static int st_press_buffer_postenable(struct iio_dev *indio_dev) int err; struct st_sensor_data *press_data = iio_priv(indio_dev); - press_data->buffer_data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL); + press_data->buffer_data = kmalloc(indio_dev->scan_bytes, + GFP_DMA | GFP_KERNEL); if (press_data->buffer_data == NULL) { err = -ENOMEM; goto allocate_memory_error; diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index a783fc075c26..9ef92a501286 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -692,7 +691,6 @@ int st_press_common_probe(struct iio_dev *indio_dev) indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &press_info; - mutex_init(&press_data->tb.buf_lock); err = st_sensors_power_enable(indio_dev); if (err) @@ -709,7 +707,6 @@ int st_press_common_probe(struct iio_dev *indio_dev) * element. */ press_data->num_data_channels = press_data->sensor_settings->num_ch - 1; - press_data->multiread_bit = press_data->sensor_settings->multi_read_bit; indio_dev->channels = press_data->sensor_settings->ch; indio_dev->num_channels = press_data->sensor_settings->num_ch; diff --git a/drivers/iio/pressure/st_pressure_i2c.c b/drivers/iio/pressure/st_pressure_i2c.c index 466e7dde5eae..71d2ed6b4948 100644 --- a/drivers/iio/pressure/st_pressure_i2c.c +++ b/drivers/iio/pressure/st_pressure_i2c.c @@ -112,7 +112,9 @@ static int st_press_i2c_probe(struct i2c_client *client, press_data = iio_priv(indio_dev); press_data->sensor_settings = (struct st_sensor_settings *)settings; - st_sensors_i2c_configure(indio_dev, client, press_data); + ret = st_sensors_i2c_configure(indio_dev, client); + if (ret < 0) + return ret; ret = st_press_common_probe(indio_dev); if (ret < 0) diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 566b955e2980..28fc1f9fa7d5 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -16,6 +16,7 @@ #include #include #include +#include #include @@ -169,36 +170,6 @@ struct st_sensor_data_ready_irq { } ig1; }; -/** - * struct st_sensor_transfer_buffer - ST sensor device I/O buffer - * @buf_lock: Mutex to protect rx and tx buffers. - * @tx_buf: Buffer used by SPI transfer function to send data to the sensors. - * This buffer is used to avoid DMA not-aligned issue. - * @rx_buf: Buffer used by SPI transfer to receive data from sensors. - * This buffer is used to avoid DMA not-aligned issue. - */ -struct st_sensor_transfer_buffer { - struct mutex buf_lock; - u8 rx_buf[ST_SENSORS_RX_MAX_LENGTH]; - u8 tx_buf[ST_SENSORS_TX_MAX_LENGTH] ____cacheline_aligned; -}; - -/** - * struct st_sensor_transfer_function - ST sensor device I/O function - * @read_byte: Function used to read one byte. - * @write_byte: Function used to write one byte. - * @read_multiple_byte: Function used to read multiple byte. - */ -struct st_sensor_transfer_function { - int (*read_byte) (struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, u8 *res_byte); - int (*write_byte) (struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, u8 data); - int (*read_multiple_byte) (struct st_sensor_transfer_buffer *tb, - struct device *dev, u8 reg_addr, int len, u8 *data, - bool multiread_bit); -}; - /** * struct st_sensor_settings - ST specific sensor settings * @wai: Contents of WhoAmI register. @@ -242,16 +213,14 @@ struct st_sensor_settings { * @current_fullscale: Maximum range of measure by the sensor. * @vdd: Pointer to sensor's Vdd power supply * @vdd_io: Pointer to sensor's Vdd-IO power supply + * @regmap: Pointer to specific sensor regmap configuration. * @enabled: Status of the sensor (false->off, true->on). - * @multiread_bit: Use or not particular bit for [I2C/SPI] multiread. * @buffer_data: Data used by buffer part. * @odr: Output data rate of the sensor [Hz]. * num_data_channels: Number of data channels used in buffer. * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). * @int_pin_open_drain: Set the interrupt/DRDY to open drain. * @get_irq_data_ready: Function to get the IRQ used for data ready signal. - * @tf: Transfer function structure used by I/O operations. - * @tb: Transfer buffers and mutex used by I/O operations. * @edge_irq: the IRQ triggers on edges and need special handling. * @hw_irq_trigger: if we're using the hardware interrupt on the sensor. * @hw_timestamp: Latest timestamp from the interrupt handler, when in use. @@ -264,9 +233,9 @@ struct st_sensor_data { struct st_sensor_fullscale_avl *current_fullscale; struct regulator *vdd; struct regulator *vdd_io; + struct regmap *regmap; bool enabled; - bool multiread_bit; char *buffer_data; @@ -278,9 +247,6 @@ struct st_sensor_data { unsigned int (*get_irq_data_ready) (struct iio_dev *indio_dev); - const struct st_sensor_transfer_function *tf; - struct st_sensor_transfer_buffer tb; - bool edge_irq; bool hw_irq_trigger; s64 hw_timestamp; diff --git a/include/linux/iio/common/st_sensors_i2c.h b/include/linux/iio/common/st_sensors_i2c.h index 5ada89944698..01e424e2af4f 100644 --- a/include/linux/iio/common/st_sensors_i2c.h +++ b/include/linux/iio/common/st_sensors_i2c.h @@ -14,8 +14,8 @@ #include #include -void st_sensors_i2c_configure(struct iio_dev *indio_dev, - struct i2c_client *client, struct st_sensor_data *sdata); +int st_sensors_i2c_configure(struct iio_dev *indio_dev, + struct i2c_client *client); #ifdef CONFIG_ACPI int st_sensors_match_acpi_device(struct device *dev); -- cgit v1.2.3-71-gd317 From dca39af8831e65adc13e0f9f8bdca3a746185072 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 23 Jul 2019 10:36:38 +0300 Subject: iio: imu: adis: Add support for SPI transfer cs_change_delay The ADIS16460 requires a higher delay before the next transfer. Since the SPI framework supports configuring the delay before the next transfer, this driver will become the first user of it. The support for this functionality in ADIS16460 requires an addition to the ADIS lib to support the `cs_change_delay` functionality from the SPI subsystem. Signed-off-by: Michael Hennerich Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- drivers/iio/imu/adis.c | 12 ++++++++++++ include/linux/iio/imu/adis.h | 2 ++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index 30281e91dbf9..1631c255deab 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -39,18 +39,24 @@ int adis_write_reg(struct adis *adis, unsigned int reg, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, + .cs_change_delay = adis->data->cs_change_delay, + .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 2, .bits_per_word = 8, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, + .cs_change_delay = adis->data->cs_change_delay, + .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 4, .bits_per_word = 8, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, + .cs_change_delay = adis->data->cs_change_delay, + .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 6, .bits_per_word = 8, @@ -133,12 +139,16 @@ int adis_read_reg(struct adis *adis, unsigned int reg, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, + .cs_change_delay = adis->data->cs_change_delay, + .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 2, .bits_per_word = 8, .len = 2, .cs_change = 1, .delay_usecs = adis->data->read_delay, + .cs_change_delay = adis->data->cs_change_delay, + .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 4, .rx_buf = adis->rx, @@ -146,6 +156,8 @@ int adis_read_reg(struct adis *adis, unsigned int reg, .len = 2, .cs_change = 1, .delay_usecs = adis->data->read_delay, + .cs_change_delay = adis->data->cs_change_delay, + .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, }, { .rx_buf = adis->rx + 2, .bits_per_word = 8, diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 3428d06b2f44..4c53815bb729 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -26,6 +26,7 @@ struct adis_burst; * struct adis_data - ADIS chip variant specific data * @read_delay: SPI delay for read operations in us * @write_delay: SPI delay for write operations in us + * @cs_change_delay: SPI delay between CS changes in us * @glob_cmd_reg: Register address of the GLOB_CMD register * @msc_ctrl_reg: Register address of the MSC_CTRL register * @diag_stat_reg: Register address of the DIAG_STAT register @@ -35,6 +36,7 @@ struct adis_burst; struct adis_data { unsigned int read_delay; unsigned int write_delay; + unsigned int cs_change_delay; unsigned int glob_cmd_reg; unsigned int msc_ctrl_reg; -- cgit v1.2.3-71-gd317 From 12bf745c9afb6755acba186091bcbb61229f4165 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Mon, 15 Jul 2019 16:14:51 -0700 Subject: iio: cros_ec: Add sign vector in core for backward compatibility To allow cros_ec iio core library to be used with legacy device, add a vector to rotate sensor data if necessary: legacy devices are not reporting data in HTML5/Android sensor referential. Check the data is not rotated on recent chromebooks that use the HTML5 standard to present sensor data. Signed-off-by: Gwendal Grignou Reviewed-by: Douglas Anderson Signed-off-by: Jonathan Cameron --- drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c | 4 ++++ include/linux/iio/common/cros_ec_sensors_core.h | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index d02660b1f0fe..3b491cf7be95 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -101,6 +101,9 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, } state->type = state->resp->info.type; state->loc = state->resp->info.location; + + /* Set sign vector, only used for backward compatibility. */ + memset(state->sign, 1, CROS_EC_SENSOR_MAX_AXIS); } return 0; @@ -303,6 +306,7 @@ static int cros_ec_sensors_read_data_unsafe(struct iio_dev *indio_dev, if (ret < 0) return ret; + *data *= st->sign[i]; data++; } diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h index bb03a252bd04..6f13c73bac3d 100644 --- a/include/linux/iio/common/cros_ec_sensors_core.h +++ b/include/linux/iio/common/cros_ec_sensors_core.h @@ -66,7 +66,7 @@ struct cros_ec_sensors_core_state { s16 offset; u16 scale; } calib[CROS_EC_SENSOR_MAX_AXIS]; - + s8 sign[CROS_EC_SENSOR_MAX_AXIS]; u8 samples[CROS_EC_SAMPLE_SIZE]; int (*read_ec_sensors_data)(struct iio_dev *indio_dev, -- cgit v1.2.3-71-gd317 From ae7b02ad2f32d39d1434655f346c04a16c1aa703 Mon Sep 17 00:00:00 2001 From: Fabien Lahoudere Date: Tue, 16 Jul 2019 11:11:06 +0200 Subject: iio: common: cros_ec_sensors: Expose cros_ec_sensors frequency range via iio sysfs Embedded controller return minimum and maximum frequencies, unfortunately we have no way to know the step for all available frequencies. Even if not complete, we can return a list of known values using the standard read_avail callback (IIO_CHAN_INFO_SAMP_FREQ) to provide them to userland. Now cros_ec_* sensors provides frequencies values in sysfs like this: "0 min max". 0 is always true to disable the sensor. Default frequencies are provided for earlier protocol. Signed-off-by: Nick Vaccaro Signed-off-by: Fabien Lahoudere [rebased on top of iio/testing and solved conflicts] Signed-off-by: Enric Balletbo i Serra Signed-off-by: Jonathan Cameron --- .../iio/common/cros_ec_sensors/cros_ec_sensors.c | 3 + .../common/cros_ec_sensors/cros_ec_sensors_core.c | 65 ++++++++++++++++++++++ drivers/iio/light/cros_ec_light_prox.c | 3 + include/linux/iio/common/cros_ec_sensors_core.h | 21 +++++++ 4 files changed, 92 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index 2af09606c438..6a4919cd83c3 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -215,6 +215,7 @@ static int cros_ec_sensors_write(struct iio_dev *indio_dev, static const struct iio_info ec_sensors_info = { .read_raw = &cros_ec_sensors_read, .write_raw = &cros_ec_sensors_write, + .read_avail = &cros_ec_sensors_core_read_avail, }; static int cros_ec_sensors_probe(struct platform_device *pdev) @@ -252,6 +253,8 @@ static int cros_ec_sensors_probe(struct platform_device *pdev) BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_FREQUENCY) | BIT(IIO_CHAN_INFO_SAMP_FREQ); + channel->info_mask_shared_by_all_available = + BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->scan_type.realbits = CROS_EC_SENSOR_BITS; channel->scan_type.storagebits = CROS_EC_SENSOR_BITS; channel->scan_index = i; diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index 3b491cf7be95..fd833295bb17 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -50,6 +50,37 @@ static int cros_ec_get_host_cmd_version_mask(struct cros_ec_device *ec_dev, return ret; } +static void get_default_min_max_freq(enum motionsensor_type type, + u32 *min_freq, + u32 *max_freq) +{ + switch (type) { + case MOTIONSENSE_TYPE_ACCEL: + case MOTIONSENSE_TYPE_GYRO: + *min_freq = 12500; + *max_freq = 100000; + break; + case MOTIONSENSE_TYPE_MAG: + *min_freq = 5000; + *max_freq = 25000; + break; + case MOTIONSENSE_TYPE_PROX: + case MOTIONSENSE_TYPE_LIGHT: + *min_freq = 100; + *max_freq = 50000; + break; + case MOTIONSENSE_TYPE_BARO: + *min_freq = 250; + *max_freq = 20000; + break; + case MOTIONSENSE_TYPE_ACTIVITY: + default: + *min_freq = 0; + *max_freq = 0; + break; + } +} + int cros_ec_sensors_core_init(struct platform_device *pdev, struct iio_dev *indio_dev, bool physical_device) @@ -104,6 +135,19 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, /* Set sign vector, only used for backward compatibility. */ memset(state->sign, 1, CROS_EC_SENSOR_MAX_AXIS); + + /* 0 is a correct value used to stop the device */ + state->frequencies[0] = 0; + if (state->msg->version < 3) { + get_default_min_max_freq(state->resp->info.type, + &state->frequencies[1], + &state->frequencies[2]); + } else { + state->frequencies[1] = + state->resp->info_3.min_frequency; + state->frequencies[2] = + state->resp->info_3.max_frequency; + } } return 0; @@ -471,6 +515,27 @@ int cros_ec_sensors_core_read(struct cros_ec_sensors_core_state *st, } EXPORT_SYMBOL_GPL(cros_ec_sensors_core_read); +int cros_ec_sensors_core_read_avail(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + const int **vals, + int *type, + int *length, + long mask) +{ + struct cros_ec_sensors_core_state *state = iio_priv(indio_dev); + + switch (mask) { + case IIO_CHAN_INFO_SAMP_FREQ: + *length = ARRAY_SIZE(state->frequencies); + *vals = (const int *)&state->frequencies; + *type = IIO_VAL_INT; + return IIO_AVAIL_LIST; + } + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(cros_ec_sensors_core_read_avail); + int cros_ec_sensors_core_write(struct cros_ec_sensors_core_state *st, struct iio_chan_spec const *chan, int val, int val2, long mask) diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c index 965f346d7d64..44313a009928 100644 --- a/drivers/iio/light/cros_ec_light_prox.c +++ b/drivers/iio/light/cros_ec_light_prox.c @@ -162,6 +162,7 @@ static int cros_ec_light_prox_write(struct iio_dev *indio_dev, static const struct iio_info cros_ec_light_prox_info = { .read_raw = &cros_ec_light_prox_read, .write_raw = &cros_ec_light_prox_write, + .read_avail = &cros_ec_sensors_core_read_avail, }; static int cros_ec_light_prox_probe(struct platform_device *pdev) @@ -196,6 +197,8 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev) channel->info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ) | BIT(IIO_CHAN_INFO_FREQUENCY); + channel->info_mask_shared_by_all_available = + BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->scan_type.realbits = CROS_EC_SENSOR_BITS; channel->scan_type.storagebits = CROS_EC_SENSOR_BITS; channel->scan_type.shift = 0; diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h index 6f13c73bac3d..ea1f50ce2e49 100644 --- a/include/linux/iio/common/cros_ec_sensors_core.h +++ b/include/linux/iio/common/cros_ec_sensors_core.h @@ -73,6 +73,9 @@ struct cros_ec_sensors_core_state { unsigned long scan_mask, s16 *data); int curr_sampl_freq; + + /* Table of known available frequencies : 0, Min and Max in mHz */ + int frequencies[3]; }; /** @@ -153,6 +156,24 @@ int cros_ec_sensors_core_read(struct cros_ec_sensors_core_state *st, struct iio_chan_spec const *chan, int *val, int *val2, long mask); +/** + * cros_ec_sensors_core_read_avail() - get available values + * @indio_dev: pointer to state information for device + * @chan: channel specification structure table + * @vals: list of available values + * @type: type of data returned + * @length: number of data returned in the array + * @mask: specifies which values to be requested + * + * Return: an error code, IIO_AVAIL_RANGE or IIO_AVAIL_LIST + */ +int cros_ec_sensors_core_read_avail(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + const int **vals, + int *type, + int *length, + long mask); + /** * cros_ec_sensors_core_write() - function to write a value to the sensor * @st: pointer to state information for device -- cgit v1.2.3-71-gd317 From 5585f2af737ae3d7454cb0ae77b995cd3ac7e43c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 22 Jul 2019 09:26:21 -0700 Subject: fs-verity: add inode and superblock fields Analogous to fs/crypto/, add fields to the VFS inode and superblock for use by the fs/verity/ support layer: - ->s_vop: points to the fsverity_operations if the filesystem supports fs-verity, otherwise is NULL. - ->i_verity_info: points to cached fs-verity information for the inode after someone opens it, otherwise is NULL. - S_VERITY: bit in ->i_flags that identifies verity inodes, even when they haven't been opened yet and thus still have NULL ->i_verity_info. Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- include/linux/fs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 56b8e358af5c..b3a0f5bfb06d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -64,6 +64,8 @@ struct workqueue_struct; struct iov_iter; struct fscrypt_info; struct fscrypt_operations; +struct fsverity_info; +struct fsverity_operations; struct fs_context; struct fs_parameter_description; @@ -723,6 +725,10 @@ struct inode { struct fscrypt_info *i_crypt_info; #endif +#ifdef CONFIG_FS_VERITY + struct fsverity_info *i_verity_info; +#endif + void *i_private; /* fs or device private pointer */ } __randomize_layout; @@ -1427,6 +1433,9 @@ struct super_block { const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; +#endif +#ifdef CONFIG_FS_VERITY + const struct fsverity_operations *s_vop; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ @@ -1965,6 +1974,7 @@ struct super_operations { #endif #define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD 32768 /* Casefolded file */ +#define S_VERITY 65536 /* Verity file (using fs/verity/) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -2006,6 +2016,7 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) +#define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) -- cgit v1.2.3-71-gd317 From fd2d1acfcadfe2e42567afaec5e989b38061a7d2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 22 Jul 2019 09:26:22 -0700 Subject: fs-verity: add the hook for file ->open() Add the fsverity_file_open() function, which prepares an fs-verity file to be read from. If not already done, it loads the fs-verity descriptor from the filesystem and sets up an fsverity_info structure for the inode which describes the Merkle tree and contains the file measurement. It also denies all attempts to open verity files for writing. This commit also begins the include/linux/fsverity.h header, which declares the interface between fs/verity/ and filesystems. Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- fs/verity/Makefile | 3 +- fs/verity/fsverity_private.h | 54 +++++++- fs/verity/init.c | 6 + fs/verity/open.c | 318 +++++++++++++++++++++++++++++++++++++++++++ include/linux/fsverity.h | 71 ++++++++++ 5 files changed, 449 insertions(+), 3 deletions(-) create mode 100644 fs/verity/open.c create mode 100644 include/linux/fsverity.h (limited to 'include/linux') diff --git a/fs/verity/Makefile b/fs/verity/Makefile index 398f3f85fa18..e6a8951c493a 100644 --- a/fs/verity/Makefile +++ b/fs/verity/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_FS_VERITY) += hash_algs.o \ - init.o + init.o \ + open.o diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index 9697aaebb5dc..c79746ff335e 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -15,8 +15,7 @@ #define pr_fmt(fmt) "fs-verity: " fmt #include -#include -#include +#include struct ahash_request; @@ -59,6 +58,40 @@ struct merkle_tree_params { u64 level_start[FS_VERITY_MAX_LEVELS]; }; +/** + * fsverity_info - cached verity metadata for an inode + * + * When a verity file is first opened, an instance of this struct is allocated + * and stored in ->i_verity_info; it remains until the inode is evicted. It + * caches information about the Merkle tree that's needed to efficiently verify + * data read from the file. It also caches the file measurement. The Merkle + * tree pages themselves are not cached here, but the filesystem may cache them. + */ +struct fsverity_info { + struct merkle_tree_params tree_params; + u8 root_hash[FS_VERITY_MAX_DIGEST_SIZE]; + u8 measurement[FS_VERITY_MAX_DIGEST_SIZE]; + const struct inode *inode; +}; + +/* + * Merkle tree properties. The file measurement is the hash of this structure. + */ +struct fsverity_descriptor { + __u8 version; /* must be 1 */ + __u8 hash_algorithm; /* Merkle tree hash algorithm */ + __u8 log_blocksize; /* log2 of size of data and tree blocks */ + __u8 salt_size; /* size of salt in bytes; 0 if none */ + __le32 sig_size; /* reserved, must be 0 */ + __le64 data_size; /* size of file the Merkle tree is built over */ + __u8 root_hash[64]; /* Merkle tree root hash */ + __u8 salt[32]; /* salt prepended to each hashed block */ + __u8 __reserved[144]; /* must be 0's */ +}; + +/* Arbitrary limit to bound the kmalloc() size. Can be changed. */ +#define FS_VERITY_MAX_DESCRIPTOR_SIZE 16384 + /* hash_algs.c */ extern struct fsverity_hash_alg fsverity_hash_algs[]; @@ -85,4 +118,21 @@ fsverity_msg(const struct inode *inode, const char *level, #define fsverity_err(inode, fmt, ...) \ fsverity_msg((inode), KERN_ERR, fmt, ##__VA_ARGS__) +/* open.c */ + +int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, + const struct inode *inode, + unsigned int hash_algorithm, + unsigned int log_blocksize, + const u8 *salt, size_t salt_size); + +struct fsverity_info *fsverity_create_info(const struct inode *inode, + const void *desc, size_t desc_size); + +void fsverity_set_info(struct inode *inode, struct fsverity_info *vi); + +void fsverity_free_info(struct fsverity_info *vi); + +int __init fsverity_init_info_cache(void); + #endif /* _FSVERITY_PRIVATE_H */ diff --git a/fs/verity/init.c b/fs/verity/init.c index 40076bbe452a..fff1fd634335 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -33,8 +33,14 @@ void fsverity_msg(const struct inode *inode, const char *level, static int __init fsverity_init(void) { + int err; + fsverity_check_hash_algs(); + err = fsverity_init_info_cache(); + if (err) + return err; + pr_debug("Initialized fs-verity\n"); return 0; } diff --git a/fs/verity/open.c b/fs/verity/open.c new file mode 100644 index 000000000000..8013f77f907e --- /dev/null +++ b/fs/verity/open.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fs/verity/open.c: opening fs-verity files + * + * Copyright 2019 Google LLC + */ + +#include "fsverity_private.h" + +#include + +static struct kmem_cache *fsverity_info_cachep; + +/** + * fsverity_init_merkle_tree_params() - initialize Merkle tree parameters + * @params: the parameters struct to initialize + * @inode: the inode for which the Merkle tree is being built + * @hash_algorithm: number of hash algorithm to use + * @log_blocksize: log base 2 of block size to use + * @salt: pointer to salt (optional) + * @salt_size: size of salt, possibly 0 + * + * Validate the hash algorithm and block size, then compute the tree topology + * (num levels, num blocks in each level, etc.) and initialize @params. + * + * Return: 0 on success, -errno on failure + */ +int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, + const struct inode *inode, + unsigned int hash_algorithm, + unsigned int log_blocksize, + const u8 *salt, size_t salt_size) +{ + const struct fsverity_hash_alg *hash_alg; + int err; + u64 blocks; + u64 offset; + int level; + + memset(params, 0, sizeof(*params)); + + hash_alg = fsverity_get_hash_alg(inode, hash_algorithm); + if (IS_ERR(hash_alg)) + return PTR_ERR(hash_alg); + params->hash_alg = hash_alg; + params->digest_size = hash_alg->digest_size; + + params->hashstate = fsverity_prepare_hash_state(hash_alg, salt, + salt_size); + if (IS_ERR(params->hashstate)) { + err = PTR_ERR(params->hashstate); + params->hashstate = NULL; + fsverity_err(inode, "Error %d preparing hash state", err); + goto out_err; + } + + if (log_blocksize != PAGE_SHIFT) { + fsverity_warn(inode, "Unsupported log_blocksize: %u", + log_blocksize); + err = -EINVAL; + goto out_err; + } + params->log_blocksize = log_blocksize; + params->block_size = 1 << log_blocksize; + + if (WARN_ON(!is_power_of_2(params->digest_size))) { + err = -EINVAL; + goto out_err; + } + if (params->block_size < 2 * params->digest_size) { + fsverity_warn(inode, + "Merkle tree block size (%u) too small for hash algorithm \"%s\"", + params->block_size, hash_alg->name); + err = -EINVAL; + goto out_err; + } + params->log_arity = params->log_blocksize - ilog2(params->digest_size); + params->hashes_per_block = 1 << params->log_arity; + + pr_debug("Merkle tree uses %s with %u-byte blocks (%u hashes/block), salt=%*phN\n", + hash_alg->name, params->block_size, params->hashes_per_block, + (int)salt_size, salt); + + /* + * Compute the number of levels in the Merkle tree and create a map from + * level to the starting block of that level. Level 'num_levels - 1' is + * the root and is stored first. Level 0 is the level directly "above" + * the data blocks and is stored last. + */ + + /* Compute number of levels and the number of blocks in each level */ + blocks = (inode->i_size + params->block_size - 1) >> log_blocksize; + pr_debug("Data is %lld bytes (%llu blocks)\n", inode->i_size, blocks); + while (blocks > 1) { + if (params->num_levels >= FS_VERITY_MAX_LEVELS) { + fsverity_err(inode, "Too many levels in Merkle tree"); + err = -EINVAL; + goto out_err; + } + blocks = (blocks + params->hashes_per_block - 1) >> + params->log_arity; + /* temporarily using level_start[] to store blocks in level */ + params->level_start[params->num_levels++] = blocks; + } + + /* Compute the starting block of each level */ + offset = 0; + for (level = (int)params->num_levels - 1; level >= 0; level--) { + blocks = params->level_start[level]; + params->level_start[level] = offset; + pr_debug("Level %d is %llu blocks starting at index %llu\n", + level, blocks, offset); + offset += blocks; + } + + params->tree_size = offset << log_blocksize; + return 0; + +out_err: + kfree(params->hashstate); + memset(params, 0, sizeof(*params)); + return err; +} + +/* Compute the file measurement by hashing the fsverity_descriptor. */ +static int compute_file_measurement(const struct fsverity_hash_alg *hash_alg, + const struct fsverity_descriptor *desc, + u8 *measurement) +{ + return fsverity_hash_buffer(hash_alg, desc, sizeof(*desc), measurement); +} + +/* + * Validate the given fsverity_descriptor and create a new fsverity_info from + * it. + */ +struct fsverity_info *fsverity_create_info(const struct inode *inode, + const void *_desc, size_t desc_size) +{ + const struct fsverity_descriptor *desc = _desc; + struct fsverity_info *vi; + int err; + + if (desc_size < sizeof(*desc)) { + fsverity_err(inode, "Unrecognized descriptor size: %zu bytes", + desc_size); + return ERR_PTR(-EINVAL); + } + + if (desc->version != 1) { + fsverity_err(inode, "Unrecognized descriptor version: %u", + desc->version); + return ERR_PTR(-EINVAL); + } + + if (desc->sig_size || + memchr_inv(desc->__reserved, 0, sizeof(desc->__reserved))) { + fsverity_err(inode, "Reserved bits set in descriptor"); + return ERR_PTR(-EINVAL); + } + + if (desc->salt_size > sizeof(desc->salt)) { + fsverity_err(inode, "Invalid salt_size: %u", desc->salt_size); + return ERR_PTR(-EINVAL); + } + + if (le64_to_cpu(desc->data_size) != inode->i_size) { + fsverity_err(inode, + "Wrong data_size: %llu (desc) != %lld (inode)", + le64_to_cpu(desc->data_size), inode->i_size); + return ERR_PTR(-EINVAL); + } + + vi = kmem_cache_zalloc(fsverity_info_cachep, GFP_KERNEL); + if (!vi) + return ERR_PTR(-ENOMEM); + vi->inode = inode; + + err = fsverity_init_merkle_tree_params(&vi->tree_params, inode, + desc->hash_algorithm, + desc->log_blocksize, + desc->salt, desc->salt_size); + if (err) { + fsverity_err(inode, + "Error %d initializing Merkle tree parameters", + err); + goto out; + } + + memcpy(vi->root_hash, desc->root_hash, vi->tree_params.digest_size); + + err = compute_file_measurement(vi->tree_params.hash_alg, desc, + vi->measurement); + if (err) { + fsverity_err(inode, "Error %d computing file measurement", err); + goto out; + } + pr_debug("Computed file measurement: %s:%*phN\n", + vi->tree_params.hash_alg->name, + vi->tree_params.digest_size, vi->measurement); +out: + if (err) { + fsverity_free_info(vi); + vi = ERR_PTR(err); + } + return vi; +} + +void fsverity_set_info(struct inode *inode, struct fsverity_info *vi) +{ + /* + * Multiple processes may race to set ->i_verity_info, so use cmpxchg. + * This pairs with the READ_ONCE() in fsverity_get_info(). + */ + if (cmpxchg(&inode->i_verity_info, NULL, vi) != NULL) + fsverity_free_info(vi); +} + +void fsverity_free_info(struct fsverity_info *vi) +{ + if (!vi) + return; + kfree(vi->tree_params.hashstate); + kmem_cache_free(fsverity_info_cachep, vi); +} + +/* Ensure the inode has an ->i_verity_info */ +static int ensure_verity_info(struct inode *inode) +{ + struct fsverity_info *vi = fsverity_get_info(inode); + struct fsverity_descriptor *desc; + int res; + + if (vi) + return 0; + + res = inode->i_sb->s_vop->get_verity_descriptor(inode, NULL, 0); + if (res < 0) { + fsverity_err(inode, + "Error %d getting verity descriptor size", res); + return res; + } + if (res > FS_VERITY_MAX_DESCRIPTOR_SIZE) { + fsverity_err(inode, "Verity descriptor is too large (%d bytes)", + res); + return -EMSGSIZE; + } + desc = kmalloc(res, GFP_KERNEL); + if (!desc) + return -ENOMEM; + res = inode->i_sb->s_vop->get_verity_descriptor(inode, desc, res); + if (res < 0) { + fsverity_err(inode, "Error %d reading verity descriptor", res); + goto out_free_desc; + } + + vi = fsverity_create_info(inode, desc, res); + if (IS_ERR(vi)) { + res = PTR_ERR(vi); + goto out_free_desc; + } + + fsverity_set_info(inode, vi); + res = 0; +out_free_desc: + kfree(desc); + return res; +} + +/** + * fsverity_file_open() - prepare to open a verity file + * @inode: the inode being opened + * @filp: the struct file being set up + * + * When opening a verity file, deny the open if it is for writing. Otherwise, + * set up the inode's ->i_verity_info if not already done. + * + * When combined with fscrypt, this must be called after fscrypt_file_open(). + * Otherwise, we won't have the key set up to decrypt the verity metadata. + * + * Return: 0 on success, -errno on failure + */ +int fsverity_file_open(struct inode *inode, struct file *filp) +{ + if (!IS_VERITY(inode)) + return 0; + + if (filp->f_mode & FMODE_WRITE) { + pr_debug("Denying opening verity file (ino %lu) for write\n", + inode->i_ino); + return -EPERM; + } + + return ensure_verity_info(inode); +} +EXPORT_SYMBOL_GPL(fsverity_file_open); + +/** + * fsverity_cleanup_inode() - free the inode's verity info, if present + * + * Filesystems must call this on inode eviction to free ->i_verity_info. + */ +void fsverity_cleanup_inode(struct inode *inode) +{ + fsverity_free_info(inode->i_verity_info); + inode->i_verity_info = NULL; +} +EXPORT_SYMBOL_GPL(fsverity_cleanup_inode); + +int __init fsverity_init_info_cache(void) +{ + fsverity_info_cachep = KMEM_CACHE_USERCOPY(fsverity_info, + SLAB_RECLAIM_ACCOUNT, + measurement); + if (!fsverity_info_cachep) + return -ENOMEM; + return 0; +} diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h new file mode 100644 index 000000000000..09b04dab6452 --- /dev/null +++ b/include/linux/fsverity.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * fs-verity: read-only file-based authenticity protection + * + * This header declares the interface between the fs/verity/ support layer and + * filesystems that support fs-verity. + * + * Copyright 2019 Google LLC + */ + +#ifndef _LINUX_FSVERITY_H +#define _LINUX_FSVERITY_H + +#include +#include + +/* Verity operations for filesystems */ +struct fsverity_operations { + + /** + * Get the verity descriptor of the given inode. + * + * @inode: an inode with the S_VERITY flag set + * @buf: buffer in which to place the verity descriptor + * @bufsize: size of @buf, or 0 to retrieve the size only + * + * If bufsize == 0, then the size of the verity descriptor is returned. + * Otherwise the verity descriptor is written to 'buf' and its actual + * size is returned; -ERANGE is returned if it's too large. This may be + * called by multiple processes concurrently on the same inode. + * + * Return: the size on success, -errno on failure + */ + int (*get_verity_descriptor)(struct inode *inode, void *buf, + size_t bufsize); +}; + +#ifdef CONFIG_FS_VERITY + +static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) +{ + /* pairs with the cmpxchg() in fsverity_set_info() */ + return READ_ONCE(inode->i_verity_info); +} + +/* open.c */ + +extern int fsverity_file_open(struct inode *inode, struct file *filp); +extern void fsverity_cleanup_inode(struct inode *inode); + +#else /* !CONFIG_FS_VERITY */ + +static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) +{ + return NULL; +} + +/* open.c */ + +static inline int fsverity_file_open(struct inode *inode, struct file *filp) +{ + return IS_VERITY(inode) ? -EOPNOTSUPP : 0; +} + +static inline void fsverity_cleanup_inode(struct inode *inode) +{ +} + +#endif /* !CONFIG_FS_VERITY */ + +#endif /* _LINUX_FSVERITY_H */ -- cgit v1.2.3-71-gd317 From c1d9b584e2cf3f0562d8fcf34574c044d17853a1 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 22 Jul 2019 09:26:22 -0700 Subject: fs-verity: add the hook for file ->setattr() Add a function fsverity_prepare_setattr() which filesystems that support fs-verity must call to deny truncates of verity files. Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- fs/verity/open.c | 21 +++++++++++++++++++++ include/linux/fsverity.h | 7 +++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/fs/verity/open.c b/fs/verity/open.c index 8013f77f907e..2cb2fe8082bf 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -295,6 +295,27 @@ int fsverity_file_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL_GPL(fsverity_file_open); +/** + * fsverity_prepare_setattr() - prepare to change a verity inode's attributes + * @dentry: dentry through which the inode is being changed + * @attr: attributes to change + * + * Verity files are immutable, so deny truncates. This isn't covered by the + * open-time check because sys_truncate() takes a path, not a file descriptor. + * + * Return: 0 on success, -errno on failure + */ +int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr) +{ + if (IS_VERITY(d_inode(dentry)) && (attr->ia_valid & ATTR_SIZE)) { + pr_debug("Denying truncate of verity file (ino %lu)\n", + d_inode(dentry)->i_ino); + return -EPERM; + } + return 0; +} +EXPORT_SYMBOL_GPL(fsverity_prepare_setattr); + /** * fsverity_cleanup_inode() - free the inode's verity info, if present * diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 09b04dab6452..cbd0f84e1620 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -46,6 +46,7 @@ static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) /* open.c */ extern int fsverity_file_open(struct inode *inode, struct file *filp); +extern int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); extern void fsverity_cleanup_inode(struct inode *inode); #else /* !CONFIG_FS_VERITY */ @@ -62,6 +63,12 @@ static inline int fsverity_file_open(struct inode *inode, struct file *filp) return IS_VERITY(inode) ? -EOPNOTSUPP : 0; } +static inline int fsverity_prepare_setattr(struct dentry *dentry, + struct iattr *attr) +{ + return IS_VERITY(d_inode(dentry)) ? -EOPNOTSUPP : 0; +} + static inline void fsverity_cleanup_inode(struct inode *inode) { } -- cgit v1.2.3-71-gd317 From 8a1d0f9cacc997bedc017056a94f35dc823394ed Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 22 Jul 2019 09:26:22 -0700 Subject: fs-verity: add data verification hooks for ->readpages() Add functions that verify data pages that have been read from a fs-verity file, against that file's Merkle tree. These will be called from filesystems' ->readpage() and ->readpages() methods. Since data verification can block, a workqueue is provided for these methods to enqueue verification work from their bio completion callback. See the "Verifying data" section of Documentation/filesystems/fsverity.rst for more information. Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- fs/verity/Makefile | 3 +- fs/verity/fsverity_private.h | 5 + fs/verity/init.c | 8 ++ fs/verity/open.c | 6 + fs/verity/verify.c | 275 +++++++++++++++++++++++++++++++++++++++++++ include/linux/fsverity.h | 56 +++++++++ 6 files changed, 352 insertions(+), 1 deletion(-) create mode 100644 fs/verity/verify.c (limited to 'include/linux') diff --git a/fs/verity/Makefile b/fs/verity/Makefile index e6a8951c493a..7fa628cd5eba 100644 --- a/fs/verity/Makefile +++ b/fs/verity/Makefile @@ -2,4 +2,5 @@ obj-$(CONFIG_FS_VERITY) += hash_algs.o \ init.o \ - open.o + open.o \ + verify.o diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index c79746ff335e..eaa2b3b93bbf 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -134,5 +134,10 @@ void fsverity_set_info(struct inode *inode, struct fsverity_info *vi); void fsverity_free_info(struct fsverity_info *vi); int __init fsverity_init_info_cache(void); +void __init fsverity_exit_info_cache(void); + +/* verify.c */ + +int __init fsverity_init_workqueue(void); #endif /* _FSVERITY_PRIVATE_H */ diff --git a/fs/verity/init.c b/fs/verity/init.c index fff1fd634335..b593805aafcc 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -41,7 +41,15 @@ static int __init fsverity_init(void) if (err) return err; + err = fsverity_init_workqueue(); + if (err) + goto err_exit_info_cache; + pr_debug("Initialized fs-verity\n"); return 0; + +err_exit_info_cache: + fsverity_exit_info_cache(); + return err; } late_initcall(fsverity_init) diff --git a/fs/verity/open.c b/fs/verity/open.c index 2cb2fe8082bf..3636a1ed8e2c 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -337,3 +337,9 @@ int __init fsverity_init_info_cache(void) return -ENOMEM; return 0; } + +void __init fsverity_exit_info_cache(void) +{ + kmem_cache_destroy(fsverity_info_cachep); + fsverity_info_cachep = NULL; +} diff --git a/fs/verity/verify.c b/fs/verity/verify.c new file mode 100644 index 000000000000..62ab8f6a8ea1 --- /dev/null +++ b/fs/verity/verify.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fs/verity/verify.c: data verification functions, i.e. hooks for ->readpages() + * + * Copyright 2019 Google LLC + */ + +#include "fsverity_private.h" + +#include +#include +#include + +static struct workqueue_struct *fsverity_read_workqueue; + +/** + * hash_at_level() - compute the location of the block's hash at the given level + * + * @params: (in) the Merkle tree parameters + * @dindex: (in) the index of the data block being verified + * @level: (in) the level of hash we want (0 is leaf level) + * @hindex: (out) the index of the hash block containing the wanted hash + * @hoffset: (out) the byte offset to the wanted hash within the hash block + */ +static void hash_at_level(const struct merkle_tree_params *params, + pgoff_t dindex, unsigned int level, pgoff_t *hindex, + unsigned int *hoffset) +{ + pgoff_t position; + + /* Offset of the hash within the level's region, in hashes */ + position = dindex >> (level * params->log_arity); + + /* Index of the hash block in the tree overall */ + *hindex = params->level_start[level] + (position >> params->log_arity); + + /* Offset of the wanted hash (in bytes) within the hash block */ + *hoffset = (position & ((1 << params->log_arity) - 1)) << + (params->log_blocksize - params->log_arity); +} + +/* Extract a hash from a hash page */ +static void extract_hash(struct page *hpage, unsigned int hoffset, + unsigned int hsize, u8 *out) +{ + void *virt = kmap_atomic(hpage); + + memcpy(out, virt + hoffset, hsize); + kunmap_atomic(virt); +} + +static inline int cmp_hashes(const struct fsverity_info *vi, + const u8 *want_hash, const u8 *real_hash, + pgoff_t index, int level) +{ + const unsigned int hsize = vi->tree_params.digest_size; + + if (memcmp(want_hash, real_hash, hsize) == 0) + return 0; + + fsverity_err(vi->inode, + "FILE CORRUPTED! index=%lu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN", + index, level, + vi->tree_params.hash_alg->name, hsize, want_hash, + vi->tree_params.hash_alg->name, hsize, real_hash); + return -EBADMSG; +} + +/* + * Verify a single data page against the file's Merkle tree. + * + * In principle, we need to verify the entire path to the root node. However, + * for efficiency the filesystem may cache the hash pages. Therefore we need + * only ascend the tree until an already-verified page is seen, as indicated by + * the PageChecked bit being set; then verify the path to that page. + * + * This code currently only supports the case where the verity block size is + * equal to PAGE_SIZE. Doing otherwise would be possible but tricky, since we + * wouldn't be able to use the PageChecked bit. + * + * Note that multiple processes may race to verify a hash page and mark it + * Checked, but it doesn't matter; the result will be the same either way. + * + * Return: true if the page is valid, else false. + */ +static bool verify_page(struct inode *inode, const struct fsverity_info *vi, + struct ahash_request *req, struct page *data_page) +{ + const struct merkle_tree_params *params = &vi->tree_params; + const unsigned int hsize = params->digest_size; + const pgoff_t index = data_page->index; + int level; + u8 _want_hash[FS_VERITY_MAX_DIGEST_SIZE]; + const u8 *want_hash; + u8 real_hash[FS_VERITY_MAX_DIGEST_SIZE]; + struct page *hpages[FS_VERITY_MAX_LEVELS]; + unsigned int hoffsets[FS_VERITY_MAX_LEVELS]; + int err; + + if (WARN_ON_ONCE(!PageLocked(data_page) || PageUptodate(data_page))) + return false; + + pr_debug_ratelimited("Verifying data page %lu...\n", index); + + /* + * Starting at the leaf level, ascend the tree saving hash pages along + * the way until we find a verified hash page, indicated by PageChecked; + * or until we reach the root. + */ + for (level = 0; level < params->num_levels; level++) { + pgoff_t hindex; + unsigned int hoffset; + struct page *hpage; + + hash_at_level(params, index, level, &hindex, &hoffset); + + pr_debug_ratelimited("Level %d: hindex=%lu, hoffset=%u\n", + level, hindex, hoffset); + + hpage = inode->i_sb->s_vop->read_merkle_tree_page(inode, + hindex); + if (IS_ERR(hpage)) { + err = PTR_ERR(hpage); + fsverity_err(inode, + "Error %d reading Merkle tree page %lu", + err, hindex); + goto out; + } + + if (PageChecked(hpage)) { + extract_hash(hpage, hoffset, hsize, _want_hash); + want_hash = _want_hash; + put_page(hpage); + pr_debug_ratelimited("Hash page already checked, want %s:%*phN\n", + params->hash_alg->name, + hsize, want_hash); + goto descend; + } + pr_debug_ratelimited("Hash page not yet checked\n"); + hpages[level] = hpage; + hoffsets[level] = hoffset; + } + + want_hash = vi->root_hash; + pr_debug("Want root hash: %s:%*phN\n", + params->hash_alg->name, hsize, want_hash); +descend: + /* Descend the tree verifying hash pages */ + for (; level > 0; level--) { + struct page *hpage = hpages[level - 1]; + unsigned int hoffset = hoffsets[level - 1]; + + err = fsverity_hash_page(params, inode, req, hpage, real_hash); + if (err) + goto out; + err = cmp_hashes(vi, want_hash, real_hash, index, level - 1); + if (err) + goto out; + SetPageChecked(hpage); + extract_hash(hpage, hoffset, hsize, _want_hash); + want_hash = _want_hash; + put_page(hpage); + pr_debug("Verified hash page at level %d, now want %s:%*phN\n", + level - 1, params->hash_alg->name, hsize, want_hash); + } + + /* Finally, verify the data page */ + err = fsverity_hash_page(params, inode, req, data_page, real_hash); + if (err) + goto out; + err = cmp_hashes(vi, want_hash, real_hash, index, -1); +out: + for (; level > 0; level--) + put_page(hpages[level - 1]); + + return err == 0; +} + +/** + * fsverity_verify_page() - verify a data page + * + * Verify a page that has just been read from a verity file. The page must be a + * pagecache page that is still locked and not yet uptodate. + * + * Return: true if the page is valid, else false. + */ +bool fsverity_verify_page(struct page *page) +{ + struct inode *inode = page->mapping->host; + const struct fsverity_info *vi = inode->i_verity_info; + struct ahash_request *req; + bool valid; + + req = ahash_request_alloc(vi->tree_params.hash_alg->tfm, GFP_NOFS); + if (unlikely(!req)) + return false; + + valid = verify_page(inode, vi, req, page); + + ahash_request_free(req); + + return valid; +} +EXPORT_SYMBOL_GPL(fsverity_verify_page); + +#ifdef CONFIG_BLOCK +/** + * fsverity_verify_bio() - verify a 'read' bio that has just completed + * + * Verify a set of pages that have just been read from a verity file. The pages + * must be pagecache pages that are still locked and not yet uptodate. Pages + * that fail verification are set to the Error state. Verification is skipped + * for pages already in the Error state, e.g. due to fscrypt decryption failure. + * + * This is a helper function for use by the ->readpages() method of filesystems + * that issue bios to read data directly into the page cache. Filesystems that + * populate the page cache without issuing bios (e.g. non block-based + * filesystems) must instead call fsverity_verify_page() directly on each page. + * All filesystems must also call fsverity_verify_page() on holes. + */ +void fsverity_verify_bio(struct bio *bio) +{ + struct inode *inode = bio_first_page_all(bio)->mapping->host; + const struct fsverity_info *vi = inode->i_verity_info; + struct ahash_request *req; + struct bio_vec *bv; + struct bvec_iter_all iter_all; + + req = ahash_request_alloc(vi->tree_params.hash_alg->tfm, GFP_NOFS); + if (unlikely(!req)) { + bio_for_each_segment_all(bv, bio, iter_all) + SetPageError(bv->bv_page); + return; + } + + bio_for_each_segment_all(bv, bio, iter_all) { + struct page *page = bv->bv_page; + + if (!PageError(page) && !verify_page(inode, vi, req, page)) + SetPageError(page); + } + + ahash_request_free(req); +} +EXPORT_SYMBOL_GPL(fsverity_verify_bio); +#endif /* CONFIG_BLOCK */ + +/** + * fsverity_enqueue_verify_work() - enqueue work on the fs-verity workqueue + * + * Enqueue verification work for asynchronous processing. + */ +void fsverity_enqueue_verify_work(struct work_struct *work) +{ + queue_work(fsverity_read_workqueue, work); +} +EXPORT_SYMBOL_GPL(fsverity_enqueue_verify_work); + +int __init fsverity_init_workqueue(void) +{ + /* + * Use an unbound workqueue to allow bios to be verified in parallel + * even when they happen to complete on the same CPU. This sacrifices + * locality, but it's worthwhile since hashing is CPU-intensive. + * + * Also use a high-priority workqueue to prioritize verification work, + * which blocks reads from completing, over regular application tasks. + */ + fsverity_read_workqueue = alloc_workqueue("fsverity_read_queue", + WQ_UNBOUND | WQ_HIGHPRI, + num_online_cpus()); + if (!fsverity_read_workqueue) + return -ENOMEM; + return 0; +} diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index cbd0f84e1620..95c257cd7ff0 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -33,6 +33,23 @@ struct fsverity_operations { */ int (*get_verity_descriptor)(struct inode *inode, void *buf, size_t bufsize); + + /** + * Read a Merkle tree page of the given inode. + * + * @inode: the inode + * @index: 0-based index of the page within the Merkle tree + * + * This can be called at any time on an open verity file, as well as + * between ->begin_enable_verity() and ->end_enable_verity(). It may be + * called by multiple processes concurrently, even with the same page. + * + * Note that this must retrieve a *page*, not necessarily a *block*. + * + * Return: the page on success, ERR_PTR() on failure + */ + struct page *(*read_merkle_tree_page)(struct inode *inode, + pgoff_t index); }; #ifdef CONFIG_FS_VERITY @@ -49,6 +66,12 @@ extern int fsverity_file_open(struct inode *inode, struct file *filp); extern int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); extern void fsverity_cleanup_inode(struct inode *inode); +/* verify.c */ + +extern bool fsverity_verify_page(struct page *page); +extern void fsverity_verify_bio(struct bio *bio); +extern void fsverity_enqueue_verify_work(struct work_struct *work); + #else /* !CONFIG_FS_VERITY */ static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) @@ -73,6 +96,39 @@ static inline void fsverity_cleanup_inode(struct inode *inode) { } +/* verify.c */ + +static inline bool fsverity_verify_page(struct page *page) +{ + WARN_ON(1); + return false; +} + +static inline void fsverity_verify_bio(struct bio *bio) +{ + WARN_ON(1); +} + +static inline void fsverity_enqueue_verify_work(struct work_struct *work) +{ + WARN_ON(1); +} + #endif /* !CONFIG_FS_VERITY */ +/** + * fsverity_active() - do reads from the inode need to go through fs-verity? + * + * This checks whether ->i_verity_info has been set. + * + * Filesystems call this from ->readpages() to check whether the pages need to + * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to + * a race condition where the file is being read concurrently with + * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) + */ +static inline bool fsverity_active(const struct inode *inode) +{ + return fsverity_get_info(inode) != NULL; +} + #endif /* _LINUX_FSVERITY_H */ -- cgit v1.2.3-71-gd317 From 90d4962cfc87a6994a19db0d76e1fa214dd67267 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Mon, 29 Jul 2019 12:23:41 +0200 Subject: mac80211: fix ieee80211_he_oper_size() comment Johannes mentioned that the comment should not reference mac80211 as other subsystems might call the helper. Signed-off-by: John Crispin Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20190729102342.8659-1-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a656f31262f1..9c81895c63c1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2053,8 +2053,8 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the the byte * after the ext ID byte. It is assumed that he_oper_ie has at least - * sizeof(struct ieee80211_he_operation) bytes, checked already in - * ieee802_11_parse_elems_crc() + * sizeof(struct ieee80211_he_operation) bytes, the caller must have + * validated this. * @return the actual size of the IE data (not including header), or 0 on error */ static inline u8 -- cgit v1.2.3-71-gd317 From 2ab45876756fb6c132ae801b0939e0474f84c426 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Mon, 29 Jul 2019 12:45:12 +0200 Subject: mac80211: add support for the ADDBA extension element HE allows peers to negotiate the aggregation fragmentation level to be used during transmission. The level can be 1-3. The Ext element is added behind the ADDBA request inside the action frame. The responder will then reply with the same level or a lower one if the requested one is not supported. This patch only handles the negotiation part as the ADDBA frames get passed to the ATH11k firmware, which does the rest of the magic for us aswell as generating the requests. Signed-off-by: Shashidhar Lakkavalli Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20190729104512.27615-1-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ net/mac80211/agg-rx.c | 70 ++++++++++++++++++++++++++++++++++++++++------ net/mac80211/ht.c | 2 +- net/mac80211/ieee80211_i.h | 3 +- 4 files changed, 66 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9c81895c63c1..7d3f2ced92d1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -981,6 +981,8 @@ struct ieee80211_mgmt { __le16 capab; __le16 timeout; __le16 start_seq_num; + /* followed by BA Extension */ + u8 variable[0]; } __packed addba_req; struct{ u8 action_code; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 01b0dad24500..0e1bb43973b8 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -178,17 +178,52 @@ static void sta_rx_agg_reorder_timer_expired(struct timer_list *t) rcu_read_unlock(); } -static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *da, u16 tid, +static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + const struct ieee80211_addba_ext_ie *req) +{ + struct ieee80211_supported_band *sband; + struct ieee80211_addba_ext_ie *resp; + const struct ieee80211_sta_he_cap *he_cap; + u8 frag_level, cap_frag_level; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type); + if (!he_cap) + return; + + pos = skb_put_zero(skb, 2 + sizeof(struct ieee80211_addba_ext_ie)); + *pos++ = WLAN_EID_ADDBA_EXT; + *pos++ = sizeof(struct ieee80211_addba_ext_ie); + resp = (struct ieee80211_addba_ext_ie *)pos; + resp->data = req->data & IEEE80211_ADDBA_EXT_NO_FRAG; + + frag_level = u32_get_bits(req->data, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); + cap_frag_level = u32_get_bits(he_cap->he_cap_elem.mac_cap_info[0], + IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK); + if (frag_level > cap_frag_level) + frag_level = cap_frag_level; + resp->data |= u8_encode_bits(frag_level, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); +} + +static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid, u8 dialog_token, u16 status, u16 policy, - u16 buf_size, u16 timeout) + u16 buf_size, u16 timeout, + const struct ieee80211_addba_ext_ie *addbaext) { + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; bool amsdu = ieee80211_hw_check(&local->hw, SUPPORTS_AMSDU_IN_AMPDU); u16 capab; - skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); + skb = dev_alloc_skb(sizeof(*mgmt) + + 2 + sizeof(struct ieee80211_addba_ext_ie) + + local->hw.extra_tx_headroom); if (!skb) return; @@ -222,13 +257,17 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout); mgmt->u.action.u.addba_resp.status = cpu_to_le16(status); + if (sta->sta.he_cap.has_he && addbaext) + ieee80211_add_addbaext(sdata, skb, addbaext); + ieee80211_tx_skb(sdata, skb); } void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq) + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { struct ieee80211_local *local = sta->sdata->local; struct tid_ampdu_rx *tid_agg_rx; @@ -410,21 +449,22 @@ end: } if (tx) - ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, tid, + ieee80211_send_addba_resp(sta, sta->sta.addr, tid, dialog_token, status, 1, buf_size, - timeout); + timeout, addbaext); } static void __ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, u16 buf_size, bool tx, - bool auto_seq) + bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { mutex_lock(&sta->ampdu_mlme.mtx); ___ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, tx, auto_seq); + buf_size, tx, auto_seq, addbaext); mutex_unlock(&sta->ampdu_mlme.mtx); } @@ -434,7 +474,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len) { u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num; + struct ieee802_11_elems elems = { 0 }; u8 dialog_token; + int ies_len; /* extract session parameters from addba request frame */ dialog_token = mgmt->u.action.u.addba_req.dialog_token; @@ -447,9 +489,19 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; + ies_len = len - offsetof(struct ieee80211_mgmt, + u.action.u.addba_req.variable); + if (ies_len) { + ieee802_11_parse_elems(mgmt->u.action.u.addba_req.variable, + ies_len, true, &elems, mgmt->bssid, NULL); + if (elems.parse_error) + return; + } + __ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, true, false); + buf_size, true, false, + elems.addba_ext_ie); } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d5a500b2a448..a2e4d6b8fd98 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -359,7 +359,7 @@ void ieee80211_ba_session_work(struct work_struct *work) sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, IEEE80211_MAX_AMPDU_BUF_HT, - false, true); + false, true, NULL); if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, sta->ampdu_mlme.tid_rx_manage_offl)) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ba1bc245678e..38769f5c3da4 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1807,7 +1807,8 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq); + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext); void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, enum ieee80211_agg_stop_reason reason); void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, -- cgit v1.2.3-71-gd317 From 3b0b278312ba7d6c1eb8b2fb48d459fb7f341a20 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 29 Jul 2019 16:35:03 +0300 Subject: NFC: nxp-nci: Get rid of platform data Legacy platform data must go away. We are on the safe side here since there are no users of it in the kernel. If anyone by any odd reason needs it the GPIO lookup tables and built-in device properties at your service. Signed-off-by: Andy Shevchenko Tested-by: Sedat Dilek Signed-off-by: David S. Miller --- MAINTAINERS | 1 - drivers/nfc/nxp-nci/core.c | 1 - drivers/nfc/nxp-nci/i2c.c | 9 +-------- drivers/nfc/nxp-nci/nxp-nci.h | 1 - include/linux/platform_data/nxp-nci.h | 19 ------------------- 5 files changed, 1 insertion(+), 30 deletions(-) delete mode 100644 include/linux/platform_data/nxp-nci.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 9cc156c58f0c..ee663e0e2f2e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11327,7 +11327,6 @@ F: include/net/nfc/ F: include/uapi/linux/nfc.h F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h -F: include/linux/platform_data/nxp-nci.h F: Documentation/devicetree/bindings/net/nfc/ NFS, SUNRPC, AND LOCKD CLIENTS diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index 8dafc696719f..aed18ca60170 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -14,7 +14,6 @@ #include #include #include -#include #include diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 5db71869f04b..47b3b7e612e6 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include @@ -304,7 +303,6 @@ static int nxp_nci_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct nxp_nci_i2c_phy *phy; - struct nxp_nci_nfc_platform_data *pdata; int r; if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { @@ -323,17 +321,12 @@ static int nxp_nci_i2c_probe(struct i2c_client *client, phy->i2c_dev = client; i2c_set_clientdata(client, phy); - pdata = client->dev.platform_data; - - if (!pdata && client->dev.of_node) { + if (client->dev.of_node) { r = nxp_nci_i2c_parse_devtree(client); if (r < 0) { nfc_err(&client->dev, "Failed to get DT data\n"); goto probe_exit; } - } else if (pdata) { - phy->gpio_en = pdata->gpio_en; - phy->gpio_fw = pdata->gpio_fw; } else if (ACPI_HANDLE(&client->dev)) { r = nxp_nci_i2c_acpi_config(phy); if (r < 0) diff --git a/drivers/nfc/nxp-nci/nxp-nci.h b/drivers/nfc/nxp-nci/nxp-nci.h index 6fe7c45544bf..ae3fb2735a4e 100644 --- a/drivers/nfc/nxp-nci/nxp-nci.h +++ b/drivers/nfc/nxp-nci/nxp-nci.h @@ -14,7 +14,6 @@ #include #include #include -#include #include diff --git a/include/linux/platform_data/nxp-nci.h b/include/linux/platform_data/nxp-nci.h deleted file mode 100644 index 97827ad468e2..000000000000 --- a/include/linux/platform_data/nxp-nci.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Generic platform data for the NXP NCI NFC chips. - * - * Copyright (C) 2014 NXP Semiconductors All rights reserved. - * - * Authors: Clément Perrochaud - */ - -#ifndef _NXP_NCI_H_ -#define _NXP_NCI_H_ - -struct nxp_nci_nfc_platform_data { - unsigned int gpio_en; - unsigned int gpio_fw; - unsigned int irq; -}; - -#endif /* _NXP_NCI_H_ */ -- cgit v1.2.3-71-gd317 From 56f8af5e9d38f120cba2c2adb0786fa2dbc901a4 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:44:06 +0100 Subject: iommu: Pass struct iommu_iotlb_gather to ->unmap() and ->iotlb_sync() To allow IOMMU drivers to batch up TLB flushing operations and postpone them until ->iotlb_sync() is called, extend the prototypes for the ->unmap() and ->iotlb_sync() IOMMU ops callbacks to take a pointer to the current iommu_iotlb_gather structure. All affected IOMMU drivers are updated, but there should be no functional change since the extra parameter is ignored for now. Signed-off-by: Will Deacon --- drivers/iommu/amd_iommu.c | 11 +++++++++-- drivers/iommu/arm-smmu-v3.c | 7 ++++--- drivers/iommu/arm-smmu.c | 5 +++-- drivers/iommu/exynos-iommu.c | 3 ++- drivers/iommu/intel-iommu.c | 3 ++- drivers/iommu/iommu.c | 2 +- drivers/iommu/ipmmu-vmsa.c | 12 +++++++++--- drivers/iommu/msm_iommu.c | 2 +- drivers/iommu/mtk_iommu.c | 13 ++++++++++--- drivers/iommu/mtk_iommu_v1.c | 3 ++- drivers/iommu/omap-iommu.c | 2 +- drivers/iommu/qcom_iommu.c | 12 +++++++++--- drivers/iommu/rockchip-iommu.c | 2 +- drivers/iommu/s390-iommu.c | 3 ++- drivers/iommu/tegra-gart.c | 12 +++++++++--- drivers/iommu/tegra-smmu.c | 2 +- drivers/iommu/virtio-iommu.c | 5 +++-- include/linux/iommu.h | 7 ++++--- 18 files changed, 73 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index f93b148cf55e..29eeea914660 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3055,7 +3055,8 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, } static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, - size_t page_size) + size_t page_size, + struct iommu_iotlb_gather *gather) { struct protection_domain *domain = to_pdomain(dom); size_t unmap_size; @@ -3196,6 +3197,12 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain) domain_flush_complete(dom); } +static void amd_iommu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) +{ + amd_iommu_flush_iotlb_all(domain); +} + const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .domain_alloc = amd_iommu_domain_alloc, @@ -3214,7 +3221,7 @@ const struct iommu_ops amd_iommu_ops = { .is_attach_deferred = amd_iommu_is_attach_deferred, .pgsize_bitmap = AMD_IOMMU_PGSIZES, .flush_iotlb_all = amd_iommu_flush_iotlb_all, - .iotlb_sync = amd_iommu_flush_iotlb_all, + .iotlb_sync = amd_iommu_iotlb_sync, }; /***************************************************************************** diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 7e137e1e28f1..80753b8ca054 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1985,8 +1985,8 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, return ops->map(ops, iova, paddr, size, prot); } -static size_t -arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) +static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *gather) { int ret; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -2010,7 +2010,8 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) arm_smmu_tlb_inv_context(smmu_domain); } -static void arm_smmu_iotlb_sync(struct iommu_domain *domain) +static void arm_smmu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) { struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index dc08db347ef3..e535ae2a9e65 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1301,7 +1301,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, } static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; @@ -1329,7 +1329,8 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) } } -static void arm_smmu_iotlb_sync(struct iommu_domain *domain) +static void arm_smmu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index b0c1e5f9daae..cf5af34cb681 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1130,7 +1130,8 @@ static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *domain } static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain, - unsigned long l_iova, size_t size) + unsigned long l_iova, size_t size, + struct iommu_iotlb_gather *gather) { struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain); sysmmu_iova_t iova = (sysmmu_iova_t)l_iova; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac4172c02244..b9fb8d6ddc6e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5147,7 +5147,8 @@ static int intel_iommu_map(struct iommu_domain *domain, } static size_t intel_iommu_unmap(struct iommu_domain *domain, - unsigned long iova, size_t size) + unsigned long iova, size_t size, + struct iommu_iotlb_gather *gather) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct page *freelist = NULL; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d67222fdfe44..70bfbcc09248 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1899,7 +1899,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain, while (unmapped < size) { size_t pgsize = iommu_pgsize(domain, iova, size - unmapped); - unmapped_page = ops->unmap(domain, iova, pgsize); + unmapped_page = ops->unmap(domain, iova, pgsize, iotlb_gather); if (!unmapped_page) break; diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 2c14a2c65b22..a9332b893ce2 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -733,14 +733,14 @@ static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, } static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); return domain->iop->unmap(domain->iop, iova, size); } -static void ipmmu_iotlb_sync(struct iommu_domain *io_domain) +static void ipmmu_flush_iotlb_all(struct iommu_domain *io_domain) { struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); @@ -748,6 +748,12 @@ static void ipmmu_iotlb_sync(struct iommu_domain *io_domain) ipmmu_tlb_flush_all(domain); } +static void ipmmu_iotlb_sync(struct iommu_domain *io_domain, + struct iommu_iotlb_gather *gather) +{ + ipmmu_flush_iotlb_all(io_domain); +} + static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain, dma_addr_t iova) { @@ -957,7 +963,7 @@ static const struct iommu_ops ipmmu_ops = { .detach_dev = ipmmu_detach_device, .map = ipmmu_map, .unmap = ipmmu_unmap, - .flush_iotlb_all = ipmmu_iotlb_sync, + .flush_iotlb_all = ipmmu_flush_iotlb_all, .iotlb_sync = ipmmu_iotlb_sync, .iova_to_phys = ipmmu_iova_to_phys, .add_device = ipmmu_add_device, diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 8b602384a385..681ab3d3376d 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -509,7 +509,7 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova, } static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t len) + size_t len, struct iommu_iotlb_gather *gather) { struct msm_priv *priv = to_msm_priv(domain); unsigned long flags; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index fed77658d67e..c870f1674903 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -371,7 +371,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, } static size_t mtk_iommu_unmap(struct iommu_domain *domain, - unsigned long iova, size_t size) + unsigned long iova, size_t size, + struct iommu_iotlb_gather *gather) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); unsigned long flags; @@ -384,7 +385,13 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain, return unmapsz; } -static void mtk_iommu_iotlb_sync(struct iommu_domain *domain) +static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain) +{ + mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data()); +} + +static void mtk_iommu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) { mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data()); } @@ -490,7 +497,7 @@ static const struct iommu_ops mtk_iommu_ops = { .detach_dev = mtk_iommu_detach_device, .map = mtk_iommu_map, .unmap = mtk_iommu_unmap, - .flush_iotlb_all = mtk_iommu_iotlb_sync, + .flush_iotlb_all = mtk_iommu_flush_iotlb_all, .iotlb_sync = mtk_iommu_iotlb_sync, .iova_to_phys = mtk_iommu_iova_to_phys, .add_device = mtk_iommu_add_device, diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index abeeac488372..7b92ddd5d9fd 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -324,7 +324,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, } static size_t mtk_iommu_unmap(struct iommu_domain *domain, - unsigned long iova, size_t size) + unsigned long iova, size_t size, + struct iommu_iotlb_gather *gather) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); unsigned long flags; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index dfb961d8c21b..8039bc5ee425 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1149,7 +1149,7 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da, } static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct device *dev = omap_domain->dev; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index fd9d9f4da735..a7432991fa04 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -417,7 +417,7 @@ static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, } static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { size_t ret; unsigned long flags; @@ -441,7 +441,7 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova, return ret; } -static void qcom_iommu_iotlb_sync(struct iommu_domain *domain) +static void qcom_iommu_flush_iotlb_all(struct iommu_domain *domain) { struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops, @@ -454,6 +454,12 @@ static void qcom_iommu_iotlb_sync(struct iommu_domain *domain) pm_runtime_put_sync(qcom_domain->iommu->dev); } +static void qcom_iommu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) +{ + qcom_iommu_flush_iotlb_all(domain); +} + static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { @@ -581,7 +587,7 @@ static const struct iommu_ops qcom_iommu_ops = { .detach_dev = qcom_iommu_detach_dev, .map = qcom_iommu_map, .unmap = qcom_iommu_unmap, - .flush_iotlb_all = qcom_iommu_iotlb_sync, + .flush_iotlb_all = qcom_iommu_flush_iotlb_all, .iotlb_sync = qcom_iommu_iotlb_sync, .iova_to_phys = qcom_iommu_iova_to_phys, .add_device = qcom_iommu_add_device, diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index dc26d74d79c2..26290f310f90 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -794,7 +794,7 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, } static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 22d4db302c1c..3b0b18e23187 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -314,7 +314,8 @@ static phys_addr_t s390_iommu_iova_to_phys(struct iommu_domain *domain, } static size_t s390_iommu_unmap(struct iommu_domain *domain, - unsigned long iova, size_t size) + unsigned long iova, size_t size, + struct iommu_iotlb_gather *gather) { struct s390_domain *s390_domain = to_s390_domain(domain); int flags = ZPCI_PTE_INVALID; diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 6d40bc1b38bf..3924f7c05544 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -207,7 +207,7 @@ static inline int __gart_iommu_unmap(struct gart_device *gart, } static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t bytes) + size_t bytes, struct iommu_iotlb_gather *gather) { struct gart_device *gart = gart_handle; int err; @@ -273,11 +273,17 @@ static int gart_iommu_of_xlate(struct device *dev, return 0; } -static void gart_iommu_sync(struct iommu_domain *domain) +static void gart_iommu_sync_map(struct iommu_domain *domain) { FLUSH_GART_REGS(gart_handle); } +static void gart_iommu_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) +{ + gart_iommu_sync_map(domain); +} + static const struct iommu_ops gart_iommu_ops = { .capable = gart_iommu_capable, .domain_alloc = gart_iommu_domain_alloc, @@ -292,7 +298,7 @@ static const struct iommu_ops gart_iommu_ops = { .iova_to_phys = gart_iommu_iova_to_phys, .pgsize_bitmap = GART_IOMMU_PGSIZES, .of_xlate = gart_iommu_of_xlate, - .iotlb_sync_map = gart_iommu_sync, + .iotlb_sync_map = gart_iommu_sync_map, .iotlb_sync = gart_iommu_sync, }; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index c4a652b227f8..7293fc3f796d 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -680,7 +680,7 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, } static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct tegra_smmu_as *as = to_smmu_as(domain); dma_addr_t pte_dma; diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 433f4d2ee956..5f9f91a4d7f3 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -742,7 +742,7 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova, } static size_t viommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { int ret = 0; size_t unmapped; @@ -788,7 +788,8 @@ static phys_addr_t viommu_iova_to_phys(struct iommu_domain *domain, return paddr; } -static void viommu_iotlb_sync(struct iommu_domain *domain) +static void viommu_iotlb_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather) { struct viommu_domain *vdomain = to_viommu_domain(domain); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ad41aee55bc6..64ebaff33455 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -258,10 +258,11 @@ struct iommu_ops { int (*map)(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, - size_t size); + size_t size, struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); void (*iotlb_sync_map)(struct iommu_domain *domain); - void (*iotlb_sync)(struct iommu_domain *domain); + void (*iotlb_sync)(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); void (*remove_device)(struct device *dev); @@ -502,7 +503,7 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { if (domain->ops->iotlb_sync) - domain->ops->iotlb_sync(domain); + domain->ops->iotlb_sync(domain, iotlb_gather); iommu_iotlb_gather_init(iotlb_gather); } -- cgit v1.2.3-71-gd317 From 3445545b2248300319b6965208e77140c960c3fd Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:44:16 +0100 Subject: iommu/io-pgtable: Introduce tlb_flush_walk() and tlb_flush_leaf() In preparation for deferring TLB flushes to iommu_tlb_sync(), introduce two new synchronous invalidation helpers to the io-pgtable API, which allow the unmap() code to force invalidation in cases where it cannot be deferred (e.g. when replacing a table with a block or when TLBI_ON_MAP is set). Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 6292ea15d674..27275575b305 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -19,17 +19,31 @@ enum io_pgtable_fmt { /** * struct iommu_flush_ops - IOMMU callbacks for TLB and page table management. * - * @tlb_flush_all: Synchronously invalidate the entire TLB context. - * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range. - * @tlb_sync: Ensure any queued TLB invalidation has taken effect, and - * any corresponding page table updates are visible to the - * IOMMU. + * @tlb_flush_all: Synchronously invalidate the entire TLB context. + * @tlb_flush_walk: Synchronously invalidate all intermediate TLB state + * (sometimes referred to as the "walk cache") for a virtual + * address range. + * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual + * address range. + * @tlb_add_flush: Optional callback to queue up leaf TLB invalidation for a + * virtual address range. This function exists purely as an + * optimisation for IOMMUs that cannot batch TLB invalidation + * operations efficiently and are therefore better suited to + * issuing them early rather than deferring them until + * iommu_tlb_sync(). + * @tlb_sync: Ensure any queued TLB invalidation has taken effect, and + * any corresponding page table updates are visible to the + * IOMMU. * * Note that these can all be called in atomic context and must therefore * not block. */ struct iommu_flush_ops { void (*tlb_flush_all)(void *cookie); + void (*tlb_flush_walk)(unsigned long iova, size_t size, size_t granule, + void *cookie); + void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule, + void *cookie); void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule, bool leaf, void *cookie); void (*tlb_sync)(void *cookie); -- cgit v1.2.3-71-gd317 From 10b7a7d912697afd681a0bcfced9e05543aded35 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:44:32 +0100 Subject: iommu/io-pgtable-arm: Call ->tlb_flush_walk() and ->tlb_flush_leaf() Now that all IOMMU drivers using the io-pgtable API implement the ->tlb_flush_walk() and ->tlb_flush_leaf() callbacks, we can use them in the io-pgtable code instead of ->tlb_add_flush() immediately followed by ->tlb_sync(). Signed-off-by: Will Deacon --- drivers/iommu/io-pgtable-arm-v7s.c | 25 +++++++++++++++---------- drivers/iommu/io-pgtable-arm.c | 17 ++++++++++++----- include/linux/io-pgtable.h | 14 ++++++++++++++ 3 files changed, 41 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 116f97ee991e..8d4914fe73bc 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -493,9 +493,8 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, * a chance for anything to kick off a table walk for the new iova. */ if (iop->cfg.quirks & IO_PGTABLE_QUIRK_TLBI_ON_MAP) { - io_pgtable_tlb_add_flush(iop, iova, size, - ARM_V7S_BLOCK_SIZE(2), false); - io_pgtable_tlb_sync(iop); + io_pgtable_tlb_flush_walk(iop, iova, size, + ARM_V7S_BLOCK_SIZE(2)); } else { wmb(); } @@ -541,8 +540,7 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data, __arm_v7s_pte_sync(ptep, ARM_V7S_CONT_PAGES, &iop->cfg); size *= ARM_V7S_CONT_PAGES; - io_pgtable_tlb_add_flush(iop, iova, size, size, true); - io_pgtable_tlb_sync(iop); + io_pgtable_tlb_flush_leaf(iop, iova, size, size); return pte; } @@ -637,9 +635,8 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, for (i = 0; i < num_entries; i++) { if (ARM_V7S_PTE_IS_TABLE(pte[i], lvl)) { /* Also flush any partial walks */ - io_pgtable_tlb_add_flush(iop, iova, blk_size, - ARM_V7S_BLOCK_SIZE(lvl + 1), false); - io_pgtable_tlb_sync(iop); + io_pgtable_tlb_flush_walk(iop, iova, blk_size, + ARM_V7S_BLOCK_SIZE(lvl + 1)); ptep = iopte_deref(pte[i], lvl); __arm_v7s_free_table(ptep, lvl + 1, data); } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { @@ -805,13 +802,19 @@ static void dummy_tlb_flush_all(void *cookie) WARN_ON(cookie != cfg_cookie); } -static void dummy_tlb_add_flush(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) +static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule, + void *cookie) { WARN_ON(cookie != cfg_cookie); WARN_ON(!(size & cfg_cookie->pgsize_bitmap)); } +static void dummy_tlb_add_flush(unsigned long iova, size_t size, + size_t granule, bool leaf, void *cookie) +{ + dummy_tlb_flush(iova, size, granule, cookie); +} + static void dummy_tlb_sync(void *cookie) { WARN_ON(cookie != cfg_cookie); @@ -819,6 +822,8 @@ static void dummy_tlb_sync(void *cookie) static const struct iommu_flush_ops dummy_tlb_ops = { .tlb_flush_all = dummy_tlb_flush_all, + .tlb_flush_walk = dummy_tlb_flush, + .tlb_flush_leaf = dummy_tlb_flush, .tlb_add_flush = dummy_tlb_add_flush, .tlb_sync = dummy_tlb_sync, }; diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 402f913b6f6d..b58338c86323 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -611,9 +611,8 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, if (!iopte_leaf(pte, lvl, iop->fmt)) { /* Also flush any partial walks */ - io_pgtable_tlb_add_flush(iop, iova, size, - ARM_LPAE_GRANULE(data), false); - io_pgtable_tlb_sync(iop); + io_pgtable_tlb_flush_walk(iop, iova, size, + ARM_LPAE_GRANULE(data)); ptep = iopte_deref(pte, data); __arm_lpae_free_pgtable(data, lvl + 1, ptep); } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { @@ -1069,13 +1068,19 @@ static void dummy_tlb_flush_all(void *cookie) WARN_ON(cookie != cfg_cookie); } -static void dummy_tlb_add_flush(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) +static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule, + void *cookie) { WARN_ON(cookie != cfg_cookie); WARN_ON(!(size & cfg_cookie->pgsize_bitmap)); } +static void dummy_tlb_add_flush(unsigned long iova, size_t size, + size_t granule, bool leaf, void *cookie) +{ + dummy_tlb_flush(iova, size, granule, cookie); +} + static void dummy_tlb_sync(void *cookie) { WARN_ON(cookie != cfg_cookie); @@ -1083,6 +1088,8 @@ static void dummy_tlb_sync(void *cookie) static const struct iommu_flush_ops dummy_tlb_ops __initconst = { .tlb_flush_all = dummy_tlb_flush_all, + .tlb_flush_walk = dummy_tlb_flush, + .tlb_flush_leaf = dummy_tlb_flush, .tlb_add_flush = dummy_tlb_add_flush, .tlb_sync = dummy_tlb_sync, }; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 27275575b305..0618aac59e74 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -198,6 +198,20 @@ static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop) iop->cfg.tlb->tlb_flush_all(iop->cookie); } +static inline void +io_pgtable_tlb_flush_walk(struct io_pgtable *iop, unsigned long iova, + size_t size, size_t granule) +{ + iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie); +} + +static inline void +io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova, + size_t size, size_t granule) +{ + iop->cfg.tlb->tlb_flush_leaf(iova, size, granule, iop->cookie); +} + static inline void io_pgtable_tlb_add_flush(struct io_pgtable *iop, unsigned long iova, size_t size, size_t granule, bool leaf) { -- cgit v1.2.3-71-gd317 From abfd6fe0cd535d31ee83b668be6eb59ce6a8469d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:44:41 +0100 Subject: iommu/io-pgtable: Replace ->tlb_add_flush() with ->tlb_add_page() The ->tlb_add_flush() callback in the io-pgtable API now looks a bit silly: - It takes a size and a granule, which are always the same - It takes a 'bool leaf', which is always true - It only ever flushes a single page With that in mind, replace it with an optional ->tlb_add_page() callback that drops the useless parameters. Signed-off-by: Will Deacon --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 5 -- drivers/iommu/arm-smmu-v3.c | 8 ++- drivers/iommu/arm-smmu.c | 88 +++++++++++++++++++++------------ drivers/iommu/io-pgtable-arm-v7s.c | 12 ++--- drivers/iommu/io-pgtable-arm.c | 11 ++--- drivers/iommu/ipmmu-vmsa.c | 7 --- drivers/iommu/msm_iommu.c | 7 ++- drivers/iommu/mtk_iommu.c | 8 ++- drivers/iommu/qcom_iommu.c | 8 ++- include/linux/io-pgtable.h | 22 ++++----- 10 files changed, 105 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 651858147bd6..ff9af320cacc 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -247,10 +247,6 @@ static void mmu_tlb_inv_context_s1(void *cookie) mmu_hw_do_operation(pfdev, 0, 0, ~0UL, AS_COMMAND_FLUSH_MEM); } -static void mmu_tlb_inv_range_nosync(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) -{} - static void mmu_tlb_sync_context(void *cookie) { //struct panfrost_device *pfdev = cookie; @@ -273,7 +269,6 @@ static const struct iommu_flush_ops mmu_tlb_ops = { .tlb_flush_all = mmu_tlb_inv_context_s1, .tlb_flush_walk = mmu_tlb_flush_walk, .tlb_flush_leaf = mmu_tlb_flush_leaf, - .tlb_add_flush = mmu_tlb_inv_range_nosync, .tlb_sync = mmu_tlb_sync_context, }; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 79819b003b07..98c90a1b4b22 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1603,6 +1603,12 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, } while (size -= granule); } +static void arm_smmu_tlb_inv_page_nosync(unsigned long iova, size_t granule, + void *cookie) +{ + arm_smmu_tlb_inv_range_nosync(iova, granule, granule, true, cookie); +} + static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { @@ -1627,7 +1633,7 @@ static const struct iommu_flush_ops arm_smmu_flush_ops = { .tlb_flush_all = arm_smmu_tlb_inv_context, .tlb_flush_walk = arm_smmu_tlb_inv_walk, .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, - .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, + .tlb_add_page = arm_smmu_tlb_inv_page_nosync, .tlb_sync = arm_smmu_tlb_sync, }; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index e9f01b860ae3..f056164a94b0 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -248,10 +248,16 @@ enum arm_smmu_domain_stage { ARM_SMMU_DOMAIN_BYPASS, }; +struct arm_smmu_flush_ops { + struct iommu_flush_ops tlb; + void (*tlb_inv_range)(unsigned long iova, size_t size, size_t granule, + bool leaf, void *cookie) +}; + struct arm_smmu_domain { struct arm_smmu_device *smmu; struct io_pgtable_ops *pgtbl_ops; - const struct iommu_flush_ops *tlb_ops; + const struct arm_smmu_flush_ops *flush_ops; struct arm_smmu_cfg cfg; enum arm_smmu_domain_stage stage; bool non_strict; @@ -551,42 +557,62 @@ static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; + const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops; - smmu_domain->tlb_ops->tlb_add_flush(iova, size, granule, false, cookie); - smmu_domain->tlb_ops->tlb_sync(cookie); + ops->tlb_inv_range(iova, size, granule, false, cookie); + ops->tlb.tlb_sync(cookie); } static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size, size_t granule, void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; + const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops; + + ops->tlb_inv_range(iova, size, granule, true, cookie); + ops->tlb.tlb_sync(cookie); +} + +static void arm_smmu_tlb_add_page(unsigned long iova, size_t granule, + void *cookie) +{ + struct arm_smmu_domain *smmu_domain = cookie; + const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops; - smmu_domain->tlb_ops->tlb_add_flush(iova, size, granule, true, cookie); - smmu_domain->tlb_ops->tlb_sync(cookie); + ops->tlb_inv_range(iova, granule, granule, true, cookie); } -static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = { - .tlb_flush_all = arm_smmu_tlb_inv_context_s1, - .tlb_flush_walk = arm_smmu_tlb_inv_walk, - .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, - .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, - .tlb_sync = arm_smmu_tlb_sync_context, +static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = { + .tlb = { + .tlb_flush_all = arm_smmu_tlb_inv_context_s1, + .tlb_flush_walk = arm_smmu_tlb_inv_walk, + .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, + .tlb_add_page = arm_smmu_tlb_add_page, + .tlb_sync = arm_smmu_tlb_sync_context, + }, + .tlb_inv_range = arm_smmu_tlb_inv_range_nosync, }; -static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = { - .tlb_flush_all = arm_smmu_tlb_inv_context_s2, - .tlb_flush_walk = arm_smmu_tlb_inv_walk, - .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, - .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, - .tlb_sync = arm_smmu_tlb_sync_context, +static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = { + .tlb = { + .tlb_flush_all = arm_smmu_tlb_inv_context_s2, + .tlb_flush_walk = arm_smmu_tlb_inv_walk, + .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, + .tlb_add_page = arm_smmu_tlb_add_page, + .tlb_sync = arm_smmu_tlb_sync_context, + }, + .tlb_inv_range = arm_smmu_tlb_inv_range_nosync, }; -static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = { - .tlb_flush_all = arm_smmu_tlb_inv_context_s2, - .tlb_flush_walk = arm_smmu_tlb_inv_walk, - .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, - .tlb_add_flush = arm_smmu_tlb_inv_vmid_nosync, - .tlb_sync = arm_smmu_tlb_sync_vmid, +static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = { + .tlb = { + .tlb_flush_all = arm_smmu_tlb_inv_context_s2, + .tlb_flush_walk = arm_smmu_tlb_inv_walk, + .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, + .tlb_add_page = arm_smmu_tlb_add_page, + .tlb_sync = arm_smmu_tlb_sync_vmid, + }, + .tlb_inv_range = arm_smmu_tlb_inv_vmid_nosync, }; static irqreturn_t arm_smmu_context_fault(int irq, void *dev) @@ -866,7 +892,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, ias = min(ias, 32UL); oas = min(oas, 32UL); } - smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops; + smmu_domain->flush_ops = &arm_smmu_s1_tlb_ops; break; case ARM_SMMU_DOMAIN_NESTED: /* @@ -886,9 +912,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, oas = min(oas, 40UL); } if (smmu->version == ARM_SMMU_V2) - smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2; + smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v2; else - smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1; + smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v1; break; default: ret = -EINVAL; @@ -917,7 +943,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, .ias = ias, .oas = oas, .coherent_walk = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK, - .tlb = smmu_domain->tlb_ops, + .tlb = &smmu_domain->flush_ops->tlb, .iommu_dev = smmu->dev, }; @@ -1346,9 +1372,9 @@ static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; - if (smmu_domain->tlb_ops) { + if (smmu_domain->flush_ops) { arm_smmu_rpm_get(smmu); - smmu_domain->tlb_ops->tlb_flush_all(smmu_domain); + smmu_domain->flush_ops->tlb.tlb_flush_all(smmu_domain); arm_smmu_rpm_put(smmu); } } @@ -1359,9 +1385,9 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; - if (smmu_domain->tlb_ops) { + if (smmu_domain->flush_ops) { arm_smmu_rpm_get(smmu); - smmu_domain->tlb_ops->tlb_sync(smmu_domain); + smmu_domain->flush_ops->tlb.tlb_sync(smmu_domain); arm_smmu_rpm_put(smmu); } } diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 8d4914fe73bc..b3f975c95f76 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -584,7 +584,7 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, return __arm_v7s_unmap(data, iova, size, 2, tablep); } - io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true); + io_pgtable_tlb_add_page(&data->iop, iova, size); return size; } @@ -647,8 +647,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, */ smp_wmb(); } else { - io_pgtable_tlb_add_flush(iop, iova, blk_size, - blk_size, true); + io_pgtable_tlb_add_page(iop, iova, blk_size); } iova += blk_size; } @@ -809,10 +808,9 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule, WARN_ON(!(size & cfg_cookie->pgsize_bitmap)); } -static void dummy_tlb_add_flush(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) +static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie) { - dummy_tlb_flush(iova, size, granule, cookie); + dummy_tlb_flush(iova, granule, granule, cookie); } static void dummy_tlb_sync(void *cookie) @@ -824,7 +822,7 @@ static const struct iommu_flush_ops dummy_tlb_ops = { .tlb_flush_all = dummy_tlb_flush_all, .tlb_flush_walk = dummy_tlb_flush, .tlb_flush_leaf = dummy_tlb_flush, - .tlb_add_flush = dummy_tlb_add_flush, + .tlb_add_page = dummy_tlb_add_page, .tlb_sync = dummy_tlb_sync, }; diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index b58338c86323..a5c0db01533e 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -582,7 +582,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, tablep = iopte_deref(pte, data); } else if (unmap_idx >= 0) { - io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true); + io_pgtable_tlb_add_page(&data->iop, iova, size); return size; } @@ -623,7 +623,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, */ smp_wmb(); } else { - io_pgtable_tlb_add_flush(iop, iova, size, size, true); + io_pgtable_tlb_add_page(iop, iova, size); } return size; @@ -1075,10 +1075,9 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule, WARN_ON(!(size & cfg_cookie->pgsize_bitmap)); } -static void dummy_tlb_add_flush(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) +static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie) { - dummy_tlb_flush(iova, size, granule, cookie); + dummy_tlb_flush(iova, granule, granule, cookie); } static void dummy_tlb_sync(void *cookie) @@ -1090,7 +1089,7 @@ static const struct iommu_flush_ops dummy_tlb_ops __initconst = { .tlb_flush_all = dummy_tlb_flush_all, .tlb_flush_walk = dummy_tlb_flush, .tlb_flush_leaf = dummy_tlb_flush, - .tlb_add_flush = dummy_tlb_add_flush, + .tlb_add_page = dummy_tlb_add_page, .tlb_sync = dummy_tlb_sync, }; diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 9cc7bcb7e39d..c4da271af90e 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -367,17 +367,10 @@ static void ipmmu_tlb_flush(unsigned long iova, size_t size, ipmmu_tlb_flush_all(cookie); } -static void ipmmu_tlb_add_flush(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) -{ - /* The hardware doesn't support selective TLB flush. */ -} - static const struct iommu_flush_ops ipmmu_flush_ops = { .tlb_flush_all = ipmmu_tlb_flush_all, .tlb_flush_walk = ipmmu_tlb_flush, .tlb_flush_leaf = ipmmu_tlb_flush, - .tlb_add_flush = ipmmu_tlb_add_flush, .tlb_sync = ipmmu_tlb_flush_all, }; diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 64132093751a..2cd83295a841 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -192,11 +192,16 @@ static void __flush_iotlb_leaf(unsigned long iova, size_t size, __flush_iotlb_sync(cookie); } +static void __flush_iotlb_page(unsigned long iova, size_t granule, void *cookie) +{ + __flush_iotlb_range(iova, granule, granule, true, cookie); +} + static const struct iommu_flush_ops msm_iommu_flush_ops = { .tlb_flush_all = __flush_iotlb, .tlb_flush_walk = __flush_iotlb_walk, .tlb_flush_leaf = __flush_iotlb_leaf, - .tlb_add_flush = __flush_iotlb_range, + .tlb_add_page = __flush_iotlb_page, .tlb_sync = __flush_iotlb_sync, }; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 85a7176bf9ae..a0b4b4dc4b90 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -202,11 +202,17 @@ static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size, mtk_iommu_tlb_sync(cookie); } +static void mtk_iommu_tlb_flush_page_nosync(unsigned long iova, size_t granule, + void *cookie) +{ + mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie); +} + static const struct iommu_flush_ops mtk_iommu_flush_ops = { .tlb_flush_all = mtk_iommu_tlb_flush_all, .tlb_flush_walk = mtk_iommu_tlb_flush_walk, .tlb_flush_leaf = mtk_iommu_tlb_flush_leaf, - .tlb_add_flush = mtk_iommu_tlb_add_flush_nosync, + .tlb_add_page = mtk_iommu_tlb_flush_page_nosync, .tlb_sync = mtk_iommu_tlb_sync, }; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 643079e52e69..7d8411dee4cf 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -178,11 +178,17 @@ static void qcom_iommu_tlb_flush_leaf(unsigned long iova, size_t size, qcom_iommu_tlb_sync(cookie); } +static void qcom_iommu_tlb_add_page(unsigned long iova, size_t granule, + void *cookie) +{ + qcom_iommu_tlb_inv_range_nosync(iova, granule, granule, true, cookie); +} + static const struct iommu_flush_ops qcom_flush_ops = { .tlb_flush_all = qcom_iommu_tlb_inv_context, .tlb_flush_walk = qcom_iommu_tlb_flush_walk, .tlb_flush_leaf = qcom_iommu_tlb_flush_leaf, - .tlb_add_flush = qcom_iommu_tlb_inv_range_nosync, + .tlb_add_page = qcom_iommu_tlb_add_page, .tlb_sync = qcom_iommu_tlb_sync, }; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 0618aac59e74..99e04bd2baa1 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -25,12 +25,11 @@ enum io_pgtable_fmt { * address range. * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual * address range. - * @tlb_add_flush: Optional callback to queue up leaf TLB invalidation for a - * virtual address range. This function exists purely as an - * optimisation for IOMMUs that cannot batch TLB invalidation - * operations efficiently and are therefore better suited to - * issuing them early rather than deferring them until - * iommu_tlb_sync(). + * @tlb_add_page: Optional callback to queue up leaf TLB invalidation for a + * single page. This function exists purely as an optimisation + * for IOMMUs that cannot batch TLB invalidation operations + * efficiently and are therefore better suited to issuing them + * early rather than deferring them until iommu_tlb_sync(). * @tlb_sync: Ensure any queued TLB invalidation has taken effect, and * any corresponding page table updates are visible to the * IOMMU. @@ -44,8 +43,7 @@ struct iommu_flush_ops { void *cookie); void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule, void *cookie); - void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule, - bool leaf, void *cookie); + void (*tlb_add_page)(unsigned long iova, size_t granule, void *cookie); void (*tlb_sync)(void *cookie); }; @@ -212,10 +210,12 @@ io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova, iop->cfg.tlb->tlb_flush_leaf(iova, size, granule, iop->cookie); } -static inline void io_pgtable_tlb_add_flush(struct io_pgtable *iop, - unsigned long iova, size_t size, size_t granule, bool leaf) +static inline void +io_pgtable_tlb_add_page(struct io_pgtable *iop, unsigned long iova, + size_t granule) { - iop->cfg.tlb->tlb_add_flush(iova, size, granule, leaf, iop->cookie); + if (iop->cfg.tlb->tlb_add_page) + iop->cfg.tlb->tlb_add_page(iova, granule, iop->cookie); } static inline void io_pgtable_tlb_sync(struct io_pgtable *iop) -- cgit v1.2.3-71-gd317 From e953f7f2fa78d1c7fd064171f88457c6b1e21af9 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:44:50 +0100 Subject: iommu/io-pgtable: Remove unused ->tlb_sync() callback The ->tlb_sync() callback is no longer used, so it can be removed. Signed-off-by: Will Deacon --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 1 - drivers/iommu/arm-smmu-v3.c | 8 -------- drivers/iommu/arm-smmu.c | 17 +++++++++-------- drivers/iommu/io-pgtable-arm-v7s.c | 6 ------ drivers/iommu/io-pgtable-arm.c | 6 ------ drivers/iommu/ipmmu-vmsa.c | 1 - drivers/iommu/msm_iommu.c | 20 +++++++------------- drivers/iommu/mtk_iommu.c | 1 - drivers/iommu/qcom_iommu.c | 1 - include/linux/io-pgtable.h | 9 --------- 10 files changed, 16 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index ff9af320cacc..de22a2276e00 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -269,7 +269,6 @@ static const struct iommu_flush_ops mmu_tlb_ops = { .tlb_flush_all = mmu_tlb_inv_context_s1, .tlb_flush_walk = mmu_tlb_flush_walk, .tlb_flush_leaf = mmu_tlb_flush_leaf, - .tlb_sync = mmu_tlb_sync_context, }; static const char *access_type_name(struct panfrost_device *pfdev, diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 98c90a1b4b22..231093413ff9 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1545,13 +1545,6 @@ static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, } /* IO_PGTABLE API */ -static void arm_smmu_tlb_sync(void *cookie) -{ - struct arm_smmu_domain *smmu_domain = cookie; - - arm_smmu_cmdq_issue_sync(smmu_domain->smmu); -} - static void arm_smmu_tlb_inv_context(void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; @@ -1634,7 +1627,6 @@ static const struct iommu_flush_ops arm_smmu_flush_ops = { .tlb_flush_walk = arm_smmu_tlb_inv_walk, .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, .tlb_add_page = arm_smmu_tlb_inv_page_nosync, - .tlb_sync = arm_smmu_tlb_sync, }; /* IOMMU API */ diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index f056164a94b0..07a267c437d6 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -251,7 +251,8 @@ enum arm_smmu_domain_stage { struct arm_smmu_flush_ops { struct iommu_flush_ops tlb; void (*tlb_inv_range)(unsigned long iova, size_t size, size_t granule, - bool leaf, void *cookie) + bool leaf, void *cookie); + void (*tlb_sync)(void *cookie); }; struct arm_smmu_domain { @@ -539,7 +540,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears * almost negligible, but the benefit of getting the first one in as far ahead * of the sync as possible is significant, hence we don't just make this a - * no-op and set .tlb_sync to arm_smmu_inv_context_s2() as you might think. + * no-op and set .tlb_sync to arm_smmu_tlb_inv_context_s2() as you might think. */ static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size, size_t granule, bool leaf, void *cookie) @@ -560,7 +561,7 @@ static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size, const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops; ops->tlb_inv_range(iova, size, granule, false, cookie); - ops->tlb.tlb_sync(cookie); + ops->tlb_sync(cookie); } static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size, @@ -570,7 +571,7 @@ static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size, const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops; ops->tlb_inv_range(iova, size, granule, true, cookie); - ops->tlb.tlb_sync(cookie); + ops->tlb_sync(cookie); } static void arm_smmu_tlb_add_page(unsigned long iova, size_t granule, @@ -588,9 +589,9 @@ static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = { .tlb_flush_walk = arm_smmu_tlb_inv_walk, .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, .tlb_add_page = arm_smmu_tlb_add_page, - .tlb_sync = arm_smmu_tlb_sync_context, }, .tlb_inv_range = arm_smmu_tlb_inv_range_nosync, + .tlb_sync = arm_smmu_tlb_sync_context, }; static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = { @@ -599,9 +600,9 @@ static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = { .tlb_flush_walk = arm_smmu_tlb_inv_walk, .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, .tlb_add_page = arm_smmu_tlb_add_page, - .tlb_sync = arm_smmu_tlb_sync_context, }, .tlb_inv_range = arm_smmu_tlb_inv_range_nosync, + .tlb_sync = arm_smmu_tlb_sync_context, }; static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = { @@ -610,9 +611,9 @@ static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = { .tlb_flush_walk = arm_smmu_tlb_inv_walk, .tlb_flush_leaf = arm_smmu_tlb_inv_leaf, .tlb_add_page = arm_smmu_tlb_add_page, - .tlb_sync = arm_smmu_tlb_sync_vmid, }, .tlb_inv_range = arm_smmu_tlb_inv_vmid_nosync, + .tlb_sync = arm_smmu_tlb_sync_vmid, }; static irqreturn_t arm_smmu_context_fault(int irq, void *dev) @@ -1387,7 +1388,7 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, if (smmu_domain->flush_ops) { arm_smmu_rpm_get(smmu); - smmu_domain->flush_ops->tlb.tlb_sync(smmu_domain); + smmu_domain->flush_ops->tlb_sync(smmu_domain); arm_smmu_rpm_put(smmu); } } diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index b3f975c95f76..203894fb6765 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -813,17 +813,11 @@ static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie) dummy_tlb_flush(iova, granule, granule, cookie); } -static void dummy_tlb_sync(void *cookie) -{ - WARN_ON(cookie != cfg_cookie); -} - static const struct iommu_flush_ops dummy_tlb_ops = { .tlb_flush_all = dummy_tlb_flush_all, .tlb_flush_walk = dummy_tlb_flush, .tlb_flush_leaf = dummy_tlb_flush, .tlb_add_page = dummy_tlb_add_page, - .tlb_sync = dummy_tlb_sync, }; #define __FAIL(ops) ({ \ diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index a5c0db01533e..f35516744965 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -1080,17 +1080,11 @@ static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie) dummy_tlb_flush(iova, granule, granule, cookie); } -static void dummy_tlb_sync(void *cookie) -{ - WARN_ON(cookie != cfg_cookie); -} - static const struct iommu_flush_ops dummy_tlb_ops __initconst = { .tlb_flush_all = dummy_tlb_flush_all, .tlb_flush_walk = dummy_tlb_flush, .tlb_flush_leaf = dummy_tlb_flush, .tlb_add_page = dummy_tlb_add_page, - .tlb_sync = dummy_tlb_sync, }; static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index c4da271af90e..a2b8eff4c1f7 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -371,7 +371,6 @@ static const struct iommu_flush_ops ipmmu_flush_ops = { .tlb_flush_all = ipmmu_tlb_flush_all, .tlb_flush_walk = ipmmu_tlb_flush, .tlb_flush_leaf = ipmmu_tlb_flush, - .tlb_sync = ipmmu_tlb_flush_all, }; /* ----------------------------------------------------------------------------- diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 2cd83295a841..ccfc7ed230ef 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -168,28 +168,16 @@ fail: return; } -static void __flush_iotlb_sync(void *cookie) -{ - /* - * Nothing is needed here, the barrier to guarantee - * completion of the tlb sync operation is implicitly - * taken care when the iommu client does a writel before - * kick starting the other master. - */ -} - static void __flush_iotlb_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { __flush_iotlb_range(iova, size, granule, false, cookie); - __flush_iotlb_sync(cookie); } static void __flush_iotlb_leaf(unsigned long iova, size_t size, size_t granule, void *cookie) { __flush_iotlb_range(iova, size, granule, true, cookie); - __flush_iotlb_sync(cookie); } static void __flush_iotlb_page(unsigned long iova, size_t granule, void *cookie) @@ -202,7 +190,6 @@ static const struct iommu_flush_ops msm_iommu_flush_ops = { .tlb_flush_walk = __flush_iotlb_walk, .tlb_flush_leaf = __flush_iotlb_leaf, .tlb_add_page = __flush_iotlb_page, - .tlb_sync = __flush_iotlb_sync, }; static int msm_iommu_alloc_ctx(unsigned long *map, int start, int end) @@ -712,6 +699,13 @@ static struct iommu_ops msm_iommu_ops = { .detach_dev = msm_iommu_detach_dev, .map = msm_iommu_map, .unmap = msm_iommu_unmap, + /* + * Nothing is needed here, the barrier to guarantee + * completion of the tlb sync operation is implicitly + * taken care when the iommu client does a writel before + * kick starting the other master. + */ + .iotlb_sync = NULL, .iova_to_phys = msm_iommu_iova_to_phys, .add_device = msm_iommu_add_device, .remove_device = msm_iommu_remove_device, diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index a0b4b4dc4b90..3785750bdb44 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -213,7 +213,6 @@ static const struct iommu_flush_ops mtk_iommu_flush_ops = { .tlb_flush_walk = mtk_iommu_tlb_flush_walk, .tlb_flush_leaf = mtk_iommu_tlb_flush_leaf, .tlb_add_page = mtk_iommu_tlb_flush_page_nosync, - .tlb_sync = mtk_iommu_tlb_sync, }; static irqreturn_t mtk_iommu_isr(int irq, void *dev_id) diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 7d8411dee4cf..0b8a6d6bb475 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -189,7 +189,6 @@ static const struct iommu_flush_ops qcom_flush_ops = { .tlb_flush_walk = qcom_iommu_tlb_flush_walk, .tlb_flush_leaf = qcom_iommu_tlb_flush_leaf, .tlb_add_page = qcom_iommu_tlb_add_page, - .tlb_sync = qcom_iommu_tlb_sync, }; static irqreturn_t qcom_iommu_fault(int irq, void *dev) diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 99e04bd2baa1..843310484fe2 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -30,9 +30,6 @@ enum io_pgtable_fmt { * for IOMMUs that cannot batch TLB invalidation operations * efficiently and are therefore better suited to issuing them * early rather than deferring them until iommu_tlb_sync(). - * @tlb_sync: Ensure any queued TLB invalidation has taken effect, and - * any corresponding page table updates are visible to the - * IOMMU. * * Note that these can all be called in atomic context and must therefore * not block. @@ -44,7 +41,6 @@ struct iommu_flush_ops { void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule, void *cookie); void (*tlb_add_page)(unsigned long iova, size_t granule, void *cookie); - void (*tlb_sync)(void *cookie); }; /** @@ -218,11 +214,6 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop, unsigned long iova, iop->cfg.tlb->tlb_add_page(iova, granule, iop->cookie); } -static inline void io_pgtable_tlb_sync(struct io_pgtable *iop) -{ - iop->cfg.tlb->tlb_sync(iop->cookie); -} - /** * struct io_pgtable_init_fns - Alloc/free a set of page tables for a * particular format. -- cgit v1.2.3-71-gd317 From a2d3a382d6c682e22b263c9e7f0d857c3fa6c9d6 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:44:58 +0100 Subject: iommu/io-pgtable: Pass struct iommu_iotlb_gather to ->unmap() Update the io-pgtable ->unmap() function to take an iommu_iotlb_gather pointer as an argument, and update the callers as appropriate. Signed-off-by: Will Deacon --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 2 +- drivers/iommu/arm-smmu-v3.c | 2 +- drivers/iommu/arm-smmu.c | 2 +- drivers/iommu/io-pgtable-arm-v7s.c | 6 +++--- drivers/iommu/io-pgtable-arm.c | 7 +++---- drivers/iommu/ipmmu-vmsa.c | 2 +- drivers/iommu/msm_iommu.c | 2 +- drivers/iommu/mtk_iommu.c | 2 +- drivers/iommu/qcom_iommu.c | 2 +- include/linux/io-pgtable.h | 4 +++- 10 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index de22a2276e00..6e8145c36e93 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -222,7 +222,7 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo) size_t unmapped_page; size_t pgsize = get_pgsize(iova, len - unmapped_len); - unmapped_page = ops->unmap(ops, iova, pgsize); + unmapped_page = ops->unmap(ops, iova, pgsize, NULL); if (!unmapped_page) break; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 231093413ff9..8e2e53079f48 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2015,7 +2015,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, if (!ops) return 0; - ret = ops->unmap(ops, iova, size); + ret = ops->unmap(ops, iova, size, gather); if (ret && arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size)) return 0; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 07a267c437d6..f6689956ab6e 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1362,7 +1362,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, return 0; arm_smmu_rpm_get(smmu); - ret = ops->unmap(ops, iova, size); + ret = ops->unmap(ops, iova, size, gather); arm_smmu_rpm_put(smmu); return ret; diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 203894fb6765..a7776e982b6c 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -666,7 +666,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, } static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops); @@ -892,7 +892,7 @@ static int __init arm_v7s_do_selftests(void) size = 1UL << __ffs(cfg.pgsize_bitmap); while (i < loopnr) { iova_start = i * SZ_16M; - if (ops->unmap(ops, iova_start + size, size) != size) + if (ops->unmap(ops, iova_start + size, size, NULL) != size) return __FAIL(ops); /* Remap of partial unmap */ @@ -910,7 +910,7 @@ static int __init arm_v7s_do_selftests(void) for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) { size = 1UL << i; - if (ops->unmap(ops, iova, size) != size) + if (ops->unmap(ops, iova, size, NULL) != size) return __FAIL(ops); if (ops->iova_to_phys(ops, iova + 42)) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index f35516744965..325430f8a0a1 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -642,7 +641,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, } static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size) + size_t size, struct iommu_iotlb_gather *gather) { struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); arm_lpae_iopte *ptep = data->pgd; @@ -1167,7 +1166,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) /* Partial unmap */ size = 1UL << __ffs(cfg->pgsize_bitmap); - if (ops->unmap(ops, SZ_1G + size, size) != size) + if (ops->unmap(ops, SZ_1G + size, size, NULL) != size) return __FAIL(ops, i); /* Remap of partial unmap */ @@ -1182,7 +1181,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) { size = 1UL << j; - if (ops->unmap(ops, iova, size) != size) + if (ops->unmap(ops, iova, size, NULL) != size) return __FAIL(ops, i); if (ops->iova_to_phys(ops, iova + 42)) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index a2b8eff4c1f7..76a8ec343d53 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -737,7 +737,7 @@ static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova, { struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); - return domain->iop->unmap(domain->iop, iova, size); + return domain->iop->unmap(domain->iop, iova, size, gather); } static void ipmmu_flush_iotlb_all(struct iommu_domain *io_domain) diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index ccfc7ed230ef..8a0dcaf0a9e9 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -523,7 +523,7 @@ static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova, unsigned long flags; spin_lock_irqsave(&priv->pgtlock, flags); - len = priv->iop->unmap(priv->iop, iova, len); + len = priv->iop->unmap(priv->iop, iova, len, gather); spin_unlock_irqrestore(&priv->pgtlock, flags); return len; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 3785750bdb44..b73cffd63262 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -400,7 +400,7 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain, size_t unmapsz; spin_lock_irqsave(&dom->pgtlock, flags); - unmapsz = dom->iop->unmap(dom->iop, iova, size); + unmapsz = dom->iop->unmap(dom->iop, iova, size, gather); spin_unlock_irqrestore(&dom->pgtlock, flags); return unmapsz; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 0b8a6d6bb475..48b288ef74b4 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -455,7 +455,7 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova, */ pm_runtime_get_sync(qcom_domain->iommu->dev); spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags); - ret = ops->unmap(ops, iova, size); + ret = ops->unmap(ops, iova, size, gather); spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags); pm_runtime_put_sync(qcom_domain->iommu->dev); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 843310484fe2..fe27d93c8ad9 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -1,7 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __IO_PGTABLE_H #define __IO_PGTABLE_H + #include +#include /* * Public API for use by IOMMU drivers @@ -136,7 +138,7 @@ struct io_pgtable_ops { int (*map)(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t paddr, size_t size, int prot); size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, - size_t size); + size_t size, struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); }; -- cgit v1.2.3-71-gd317 From 3951c41af4a65ba418e6b1b973d398552bedb84f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 2 Jul 2019 16:45:15 +0100 Subject: iommu/io-pgtable: Pass struct iommu_iotlb_gather to ->tlb_add_page() With all the pieces in place, we can finally propagate the iommu_iotlb_gather structure from the call to unmap() down to the IOMMU drivers' implementation of ->tlb_add_page(). Currently everybody ignores it, but the machinery is now there to defer invalidation. Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 3 ++- drivers/iommu/arm-smmu.c | 3 ++- drivers/iommu/io-pgtable-arm-v7s.c | 23 ++++++++++++++--------- drivers/iommu/io-pgtable-arm.c | 22 ++++++++++++++-------- drivers/iommu/msm_iommu.c | 3 ++- drivers/iommu/mtk_iommu.c | 3 ++- drivers/iommu/qcom_iommu.c | 3 ++- include/linux/io-pgtable.h | 16 +++++++++------- 8 files changed, 47 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8e2e53079f48..d1ebc7103065 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1596,7 +1596,8 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, } while (size -= granule); } -static void arm_smmu_tlb_inv_page_nosync(unsigned long iova, size_t granule, +static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) { arm_smmu_tlb_inv_range_nosync(iova, granule, granule, true, cookie); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index f6689956ab6e..5598d0ff71a8 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -574,7 +574,8 @@ static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size, ops->tlb_sync(cookie); } -static void arm_smmu_tlb_add_page(unsigned long iova, size_t granule, +static void arm_smmu_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index a7776e982b6c..18e7d212c7de 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -362,7 +362,8 @@ static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl) return false; } -static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long, +static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, + struct iommu_iotlb_gather *, unsigned long, size_t, int, arm_v7s_iopte *); static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data, @@ -383,7 +384,7 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data, size_t sz = ARM_V7S_BLOCK_SIZE(lvl); tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl); - if (WARN_ON(__arm_v7s_unmap(data, iova + i * sz, + if (WARN_ON(__arm_v7s_unmap(data, NULL, iova + i * sz, sz, lvl, tblp) != sz)) return -EINVAL; } else if (ptep[i]) { @@ -545,6 +546,7 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data, } static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, + struct iommu_iotlb_gather *gather, unsigned long iova, size_t size, arm_v7s_iopte blk_pte, arm_v7s_iopte *ptep) @@ -581,14 +583,15 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, return 0; tablep = iopte_deref(pte, 1); - return __arm_v7s_unmap(data, iova, size, 2, tablep); + return __arm_v7s_unmap(data, gather, iova, size, 2, tablep); } - io_pgtable_tlb_add_page(&data->iop, iova, size); + io_pgtable_tlb_add_page(&data->iop, gather, iova, size); return size; } static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, + struct iommu_iotlb_gather *gather, unsigned long iova, size_t size, int lvl, arm_v7s_iopte *ptep) { @@ -647,7 +650,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, */ smp_wmb(); } else { - io_pgtable_tlb_add_page(iop, iova, blk_size); + io_pgtable_tlb_add_page(iop, gather, iova, blk_size); } iova += blk_size; } @@ -657,12 +660,13 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, * Insert a table at the next level to map the old region, * minus the part we want to unmap */ - return arm_v7s_split_blk_unmap(data, iova, size, pte[0], ptep); + return arm_v7s_split_blk_unmap(data, gather, iova, size, pte[0], + ptep); } /* Keep on walkin' */ ptep = iopte_deref(pte[0], lvl); - return __arm_v7s_unmap(data, iova, size, lvl + 1, ptep); + return __arm_v7s_unmap(data, gather, iova, size, lvl + 1, ptep); } static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, @@ -673,7 +677,7 @@ static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, if (WARN_ON(upper_32_bits(iova))) return 0; - return __arm_v7s_unmap(data, iova, size, 1, data->pgd); + return __arm_v7s_unmap(data, gather, iova, size, 1, data->pgd); } static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops, @@ -808,7 +812,8 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule, WARN_ON(!(size & cfg_cookie->pgsize_bitmap)); } -static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie) +static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) { dummy_tlb_flush(iova, granule, granule, cookie); } diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 325430f8a0a1..4c91359057c5 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -289,6 +289,7 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte, } static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, + struct iommu_iotlb_gather *gather, unsigned long iova, size_t size, int lvl, arm_lpae_iopte *ptep); @@ -334,8 +335,10 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data); tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data); - if (WARN_ON(__arm_lpae_unmap(data, iova, sz, lvl, tblp) != sz)) + if (__arm_lpae_unmap(data, NULL, iova, sz, lvl, tblp) != sz) { + WARN_ON(1); return -EINVAL; + } } __arm_lpae_init_pte(data, paddr, prot, lvl, ptep); @@ -536,6 +539,7 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop) } static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, + struct iommu_iotlb_gather *gather, unsigned long iova, size_t size, arm_lpae_iopte blk_pte, int lvl, arm_lpae_iopte *ptep) @@ -581,14 +585,15 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, tablep = iopte_deref(pte, data); } else if (unmap_idx >= 0) { - io_pgtable_tlb_add_page(&data->iop, iova, size); + io_pgtable_tlb_add_page(&data->iop, gather, iova, size); return size; } - return __arm_lpae_unmap(data, iova, size, lvl, tablep); + return __arm_lpae_unmap(data, gather, iova, size, lvl, tablep); } static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, + struct iommu_iotlb_gather *gather, unsigned long iova, size_t size, int lvl, arm_lpae_iopte *ptep) { @@ -622,7 +627,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, */ smp_wmb(); } else { - io_pgtable_tlb_add_page(iop, iova, size); + io_pgtable_tlb_add_page(iop, gather, iova, size); } return size; @@ -631,13 +636,13 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, * Insert a table at the next level to map the old region, * minus the part we want to unmap */ - return arm_lpae_split_blk_unmap(data, iova, size, pte, + return arm_lpae_split_blk_unmap(data, gather, iova, size, pte, lvl + 1, ptep); } /* Keep on walkin' */ ptep = iopte_deref(pte, data); - return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep); + return __arm_lpae_unmap(data, gather, iova, size, lvl + 1, ptep); } static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, @@ -650,7 +655,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias))) return 0; - return __arm_lpae_unmap(data, iova, size, lvl, ptep); + return __arm_lpae_unmap(data, gather, iova, size, lvl, ptep); } static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, @@ -1074,7 +1079,8 @@ static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule, WARN_ON(!(size & cfg_cookie->pgsize_bitmap)); } -static void dummy_tlb_add_page(unsigned long iova, size_t granule, void *cookie) +static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) { dummy_tlb_flush(iova, granule, granule, cookie); } diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 8a0dcaf0a9e9..4c0be5b75c28 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -180,7 +180,8 @@ static void __flush_iotlb_leaf(unsigned long iova, size_t size, __flush_iotlb_range(iova, size, granule, true, cookie); } -static void __flush_iotlb_page(unsigned long iova, size_t granule, void *cookie) +static void __flush_iotlb_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) { __flush_iotlb_range(iova, granule, granule, true, cookie); } diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index b73cffd63262..0827d51936fa 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -202,7 +202,8 @@ static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size, mtk_iommu_tlb_sync(cookie); } -static void mtk_iommu_tlb_flush_page_nosync(unsigned long iova, size_t granule, +static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) { mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie); diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 48b288ef74b4..eac760cdbb28 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -178,7 +178,8 @@ static void qcom_iommu_tlb_flush_leaf(unsigned long iova, size_t size, qcom_iommu_tlb_sync(cookie); } -static void qcom_iommu_tlb_add_page(unsigned long iova, size_t granule, +static void qcom_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) { qcom_iommu_tlb_inv_range_nosync(iova, granule, granule, true, cookie); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index fe27d93c8ad9..6b1b8be3ebec 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -28,10 +28,10 @@ enum io_pgtable_fmt { * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual * address range. * @tlb_add_page: Optional callback to queue up leaf TLB invalidation for a - * single page. This function exists purely as an optimisation - * for IOMMUs that cannot batch TLB invalidation operations - * efficiently and are therefore better suited to issuing them - * early rather than deferring them until iommu_tlb_sync(). + * single page. IOMMUs that cannot batch TLB invalidation + * operations efficiently will typically issue them here, but + * others may decide to update the iommu_iotlb_gather structure + * and defer the invalidation until iommu_tlb_sync() instead. * * Note that these can all be called in atomic context and must therefore * not block. @@ -42,7 +42,8 @@ struct iommu_flush_ops { void *cookie); void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule, void *cookie); - void (*tlb_add_page)(unsigned long iova, size_t granule, void *cookie); + void (*tlb_add_page)(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie); }; /** @@ -209,11 +210,12 @@ io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova, } static inline void -io_pgtable_tlb_add_page(struct io_pgtable *iop, unsigned long iova, +io_pgtable_tlb_add_page(struct io_pgtable *iop, + struct iommu_iotlb_gather * gather, unsigned long iova, size_t granule) { if (iop->cfg.tlb->tlb_add_page) - iop->cfg.tlb->tlb_add_page(iova, granule, iop->cookie); + iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie); } /** -- cgit v1.2.3-71-gd317 From 156189a6d7a797d6fa0b13dd6b4f32b11d234a99 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 29 Jul 2019 01:40:15 +0900 Subject: leds: netxbig: remove legacy board-file support Since commit ebc278f15759 ("ARM: mvebu: remove static LED setup for netxbig boards"), no one in upstream passes in the platform data to this driver. Squash leds-kirkwood-netxbig.h into the driver, and remove the legacy board-file support. Link: https://lkml.org/lkml/2019/7/20/83 Suggested-by: Arnd Bergmann Signed-off-by: Masahiro Yamada Signed-off-by: Jacek Anaszewski --- drivers/leds/Kconfig | 1 + drivers/leds/leds-netxbig.c | 70 +++++++++++++++------- .../linux/platform_data/leds-kirkwood-netxbig.h | 54 ----------------- 3 files changed, 51 insertions(+), 74 deletions(-) delete mode 100644 include/linux/platform_data/leds-kirkwood-netxbig.h (limited to 'include/linux') diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index f7a3dd7ecf3d..1988de1d64c0 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -590,6 +590,7 @@ config LEDS_NETXBIG tristate "LED support for Big Network series LEDs" depends on LEDS_CLASS depends on MACH_KIRKWOOD + depends on OF_GPIO default y help This option enables support for LEDs found on the LaCie 2Big diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c index 10497a466775..0944cb111c34 100644 --- a/drivers/leds/leds-netxbig.c +++ b/drivers/leds/leds-netxbig.c @@ -15,7 +15,48 @@ #include #include #include -#include + +struct netxbig_gpio_ext { + unsigned int *addr; + int num_addr; + unsigned int *data; + int num_data; + unsigned int enable; +}; + +enum netxbig_led_mode { + NETXBIG_LED_OFF, + NETXBIG_LED_ON, + NETXBIG_LED_SATA, + NETXBIG_LED_TIMER1, + NETXBIG_LED_TIMER2, + NETXBIG_LED_MODE_NUM, +}; + +#define NETXBIG_LED_INVALID_MODE NETXBIG_LED_MODE_NUM + +struct netxbig_led_timer { + unsigned long delay_on; + unsigned long delay_off; + enum netxbig_led_mode mode; +}; + +struct netxbig_led { + const char *name; + const char *default_trigger; + int mode_addr; + int *mode_val; + int bright_addr; + int bright_max; +}; + +struct netxbig_led_platform_data { + struct netxbig_gpio_ext *gpio_ext; + struct netxbig_led_timer *timer; + int num_timer; + struct netxbig_led *leds; + int num_leds; +}; /* * GPIO extension bus. @@ -306,7 +347,6 @@ static int create_netxbig_led(struct platform_device *pdev, return devm_led_classdev_register(&pdev->dev, &led_dat->cdev); } -#ifdef CONFIG_OF_GPIO static int gpio_ext_get_of_pdata(struct device *dev, struct device_node *np, struct netxbig_gpio_ext *gpio_ext) { @@ -522,30 +562,20 @@ static const struct of_device_id of_netxbig_leds_match[] = { {}, }; MODULE_DEVICE_TABLE(of, of_netxbig_leds_match); -#else -static inline int -netxbig_leds_get_of_pdata(struct device *dev, - struct netxbig_led_platform_data *pdata) -{ - return -ENODEV; -} -#endif /* CONFIG_OF_GPIO */ static int netxbig_led_probe(struct platform_device *pdev) { - struct netxbig_led_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct netxbig_led_platform_data *pdata; struct netxbig_led_data *leds_data; int i; int ret; - if (!pdata) { - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return -ENOMEM; - ret = netxbig_leds_get_of_pdata(&pdev->dev, pdata); - if (ret) - return ret; - } + pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; + ret = netxbig_leds_get_of_pdata(&pdev->dev, pdata); + if (ret) + return ret; leds_data = devm_kcalloc(&pdev->dev, pdata->num_leds, sizeof(*leds_data), @@ -571,7 +601,7 @@ static struct platform_driver netxbig_led_driver = { .probe = netxbig_led_probe, .driver = { .name = "leds-netxbig", - .of_match_table = of_match_ptr(of_netxbig_leds_match), + .of_match_table = of_netxbig_leds_match, }, }; diff --git a/include/linux/platform_data/leds-kirkwood-netxbig.h b/include/linux/platform_data/leds-kirkwood-netxbig.h deleted file mode 100644 index 3c85a735c380..000000000000 --- a/include/linux/platform_data/leds-kirkwood-netxbig.h +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Platform data structure for netxbig LED driver - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - */ - -#ifndef __LEDS_KIRKWOOD_NETXBIG_H -#define __LEDS_KIRKWOOD_NETXBIG_H - -struct netxbig_gpio_ext { - unsigned *addr; - int num_addr; - unsigned *data; - int num_data; - unsigned enable; -}; - -enum netxbig_led_mode { - NETXBIG_LED_OFF, - NETXBIG_LED_ON, - NETXBIG_LED_SATA, - NETXBIG_LED_TIMER1, - NETXBIG_LED_TIMER2, - NETXBIG_LED_MODE_NUM, -}; - -#define NETXBIG_LED_INVALID_MODE NETXBIG_LED_MODE_NUM - -struct netxbig_led_timer { - unsigned long delay_on; - unsigned long delay_off; - enum netxbig_led_mode mode; -}; - -struct netxbig_led { - const char *name; - const char *default_trigger; - int mode_addr; - int *mode_val; - int bright_addr; - int bright_max; -}; - -struct netxbig_led_platform_data { - struct netxbig_gpio_ext *gpio_ext; - struct netxbig_led_timer *timer; - int num_timer; - struct netxbig_led *leds; - int num_leds; -}; - -#endif /* __LEDS_KIRKWOOD_NETXBIG_H */ -- cgit v1.2.3-71-gd317 From 6dbff13ca8a2ad2fddd904c2e789dd5e59a8644c Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 26 Jul 2019 18:06:52 +0200 Subject: include/bpf.h: Remove map_insert_ctx() stubs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we changed the device and CPU maps to use linked lists instead of bitmaps, we also removed the need for the map_insert_ctx() helpers to keep track of the bitmaps inside each map. However, it seems I forgot to remove the function definitions stubs, so remove those here. Signed-off-by: Toke Høiland-Jørgensen Acked-by: Yonghong Song Acked-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 18f4cc2c6acd..bfdb54dd2ad1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -713,7 +713,6 @@ struct xdp_buff; struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -721,7 +720,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); -void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); void __cpu_map_flush(struct bpf_map *map); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -801,10 +799,6 @@ static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, return NULL; } -static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) -{ -} - static inline void __dev_map_flush(struct bpf_map *map) { } @@ -834,10 +828,6 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) return NULL; } -static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) -{ -} - static inline void __cpu_map_flush(struct bpf_map *map) { } -- cgit v1.2.3-71-gd317 From 6f9d451ab1a33728adb72d7ff66a7b374d665176 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 26 Jul 2019 18:06:55 +0200 Subject: xdp: Add devmap_hash map type for looking up devices by hashed index MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen Acked-by: Yonghong Song Acked-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 ++ include/linux/bpf_types.h | 1 + include/trace/events/xdp.h | 3 +- include/uapi/linux/bpf.h | 1 + kernel/bpf/devmap.c | 200 +++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 2 + net/core/filter.c | 9 +- 7 files changed, 220 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bfdb54dd2ad1..f9a506147c8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -713,6 +713,7 @@ struct xdp_buff; struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -799,6 +800,12 @@ static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, return NULL; } +static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + static inline void __dev_map_flush(struct bpf_map *map) { } diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index eec5aeeeaf92..36a9c2325176 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -62,6 +62,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 68899fdc985b..8c8420230a10 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -175,7 +175,8 @@ struct _bpf_dtab_netdev { #endif /* __DEVMAP_OBJ_TYPE */ #define devmap_ifindex(fwd, map) \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((map->map_type == BPF_MAP_TYPE_DEVMAP || \ + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \ ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e985f07a98ed..6bbef0c7f585 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -134,6 +134,7 @@ enum bpf_map_type { BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, }; /* Note that tracing related programs such as diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index a0501266bdb8..9af048a932b5 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -37,6 +37,12 @@ * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. + * + * The devmap_hash type is a map type which interprets keys as ifindexes and + * indexes these using a hashmap. This allows maps that use ifindex as key to be + * densely packed instead of having holes in the lookup array for unused + * ifindexes. The setup and packet enqueue/send code is shared between the two + * types of devmap; only the lookup and insertion is different. */ #include #include @@ -59,6 +65,7 @@ struct xdp_bulk_queue { struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ + struct hlist_node index_hlist; struct bpf_dtab *dtab; struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; @@ -70,11 +77,30 @@ struct bpf_dtab { struct bpf_dtab_netdev **netdev_map; struct list_head __percpu *flush_list; struct list_head list; + + /* these are only used for DEVMAP_HASH type maps */ + struct hlist_head *dev_index_head; + spinlock_t index_lock; + unsigned int items; + u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); +static struct hlist_head *dev_map_create_hash(unsigned int entries) +{ + int i; + struct hlist_head *hash; + + hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + if (hash != NULL) + for (i = 0; i < entries; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; +} + static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { int err, cpu; @@ -97,6 +123,14 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); cost += sizeof(struct list_head) * num_possible_cpus(); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + + if (!dtab->n_buckets) /* Overflow check */ + return -EINVAL; + cost += sizeof(struct hlist_head) * dtab->n_buckets; + } + /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) @@ -115,8 +149,18 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) if (!dtab->netdev_map) goto free_percpu; + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + if (!dtab->dev_index_head) + goto free_map_area; + + spin_lock_init(&dtab->index_lock); + } + return 0; +free_map_area: + bpf_map_area_free(dtab->netdev_map); free_percpu: free_percpu(dtab->flush_list); free_charge: @@ -198,6 +242,7 @@ static void dev_map_free(struct bpf_map *map) free_percpu(dtab->flush_list); bpf_map_area_free(dtab->netdev_map); + kfree(dtab->dev_index_head); kfree(dtab); } @@ -218,6 +263,70 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, + int idx) +{ + return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; +} + +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct hlist_head *head = dev_map_index_hash(dtab, key); + struct bpf_dtab_netdev *dev; + + hlist_for_each_entry_rcu(dev, head, index_hlist) + if (dev->idx == key) + return dev; + + return NULL; +} + +static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 idx, *next = next_key; + struct bpf_dtab_netdev *dev, *next_dev; + struct hlist_head *head; + int i = 0; + + if (!key) + goto find_first; + + idx = *(u32 *)key; + + dev = __dev_map_hash_lookup_elem(map, idx); + if (!dev) + goto find_first; + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), + struct bpf_dtab_netdev, index_hlist); + + if (next_dev) { + *next = next_dev->idx; + return 0; + } + + i = idx & (dtab->n_buckets - 1); + i++; + + find_first: + for (; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_dtab_netdev, + index_hlist); + if (next_dev) { + *next = next_dev->idx; + return 0; + } + } + + return -ENOENT; +} + static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, bool in_napi_ctx) { @@ -373,6 +482,15 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key) return dev ? &dev->ifindex : NULL; } +static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, + *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; + + return dev ? &dev->ifindex : NULL; +} + static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { if (dev->dev->netdev_ops->ndo_xdp_xmit) { @@ -422,6 +540,28 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return 0; } +static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + unsigned long flags; + int ret = -ENOENT; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, k); + if (old_dev) { + dtab->items--; + hlist_del_init_rcu(&old_dev->index_hlist); + call_rcu(&old_dev->rcu, __dev_map_entry_free); + ret = 0; + } + spin_unlock_irqrestore(&dtab->index_lock, flags); + + return ret; +} + static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, u32 ifindex, @@ -502,6 +642,56 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, map, key, value, map_flags); } +static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev, *old_dev; + u32 ifindex = *(u32 *)value; + u32 idx = *(u32 *)key; + unsigned long flags; + + if (unlikely(map_flags > BPF_EXIST || !ifindex)) + return -EINVAL; + + old_dev = __dev_map_hash_lookup_elem(map, idx); + if (old_dev && (map_flags & BPF_NOEXIST)) + return -EEXIST; + + dev = __dev_map_alloc_node(net, dtab, ifindex, idx); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + spin_lock_irqsave(&dtab->index_lock, flags); + + if (old_dev) { + hlist_del_rcu(&old_dev->index_hlist); + } else { + if (dtab->items >= dtab->map.max_entries) { + spin_unlock_irqrestore(&dtab->index_lock, flags); + call_rcu(&dev->rcu, __dev_map_entry_free); + return -E2BIG; + } + dtab->items++; + } + + hlist_add_head_rcu(&dev->index_hlist, + dev_map_index_hash(dtab, idx)); + spin_unlock_irqrestore(&dtab->index_lock, flags); + + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; +} + +static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_hash_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + const struct bpf_map_ops dev_map_ops = { .map_alloc = dev_map_alloc, .map_free = dev_map_free, @@ -512,6 +702,16 @@ const struct bpf_map_ops dev_map_ops = { .map_check_btf = map_check_no_btf, }; +const struct bpf_map_ops dev_map_hash_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_hash_get_next_key, + .map_lookup_elem = dev_map_hash_lookup_elem, + .map_update_elem = dev_map_hash_update_elem, + .map_delete_elem = dev_map_hash_delete_elem, + .map_check_btf = map_check_no_btf, +}; + static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5900cbb966b1..cef851cd5c36 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3457,6 +3457,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; @@ -3539,6 +3540,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; diff --git a/net/core/filter.c b/net/core/filter.c index 3961437ccc50..1eee70f80fba 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3517,7 +3517,8 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, int err; switch (map->map_type) { - case BPF_MAP_TYPE_DEVMAP: { + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: { struct bpf_dtab_netdev *dst = fwd; err = dev_map_enqueue(dst, xdp, dev_rx); @@ -3554,6 +3555,7 @@ void xdp_do_flush_map(void) if (map) { switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: __dev_map_flush(map); break; case BPF_MAP_TYPE_CPUMAP: @@ -3574,6 +3576,8 @@ static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: return __dev_map_lookup_elem(map, index); + case BPF_MAP_TYPE_DEVMAP_HASH: + return __dev_map_hash_lookup_elem(map, index); case BPF_MAP_TYPE_CPUMAP: return __cpu_map_lookup_elem(map, index); case BPF_MAP_TYPE_XSKMAP: @@ -3655,7 +3659,8 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + if (map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { struct bpf_dtab_netdev *dst = fwd; err = dev_map_generic_redirect(dst, skb, xdp_prog); -- cgit v1.2.3-71-gd317 From 9091373ab7ea27cad381ce71aa37de6b9e687e81 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 30 Jul 2019 14:43:47 +0900 Subject: gpio: remove less important #ifdef around declarations The whole struct/function declarations in this header are surrounded by #ifdef. As far as I understood, the motivation of this is probably to break the build earlier if a driver misses to select or depend on correct CONFIG options in Kconfig. Since commit 94bed2a9c4ae ("Add -Werror-implicit-function-declaration") no one cannot call functions that have not been declared. So, I see some benefit in doing this in the cost of uglier headers. In reality, it would not be so easy to catch missed 'select' or 'depends on' because GPIOLIB, GPIOLIB_IRQCHIP etc. are already selected by someone else eventually. So, this kind of error, if any, will be caught by randconfig bots. In summary, I am not a big fan of cluttered #ifdef nesting, and this does not matter for normal developers. The code readability wins. Signed-off-by: Masahiro Yamada Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 27 ++++++++------------------- 1 file changed, 8 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 6a0e420915a3..f28f534f451a 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -20,9 +20,6 @@ struct module; enum gpiod_flags; enum gpio_lookup_flags; -#ifdef CONFIG_GPIOLIB - -#ifdef CONFIG_GPIOLIB_IRQCHIP /** * struct gpio_irq_chip - GPIO interrupt controller */ @@ -161,7 +158,6 @@ struct gpio_irq_chip { */ void (*irq_disable)(struct irq_data *data); }; -#endif /* CONFIG_GPIOLIB_IRQCHIP */ /** * struct gpio_chip - abstract a GPIO controller @@ -441,16 +437,12 @@ bool gpiochip_line_is_valid(const struct gpio_chip *chip, unsigned int offset); /* get driver data */ void *gpiochip_get_data(struct gpio_chip *chip); -struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc); - struct bgpio_pdata { const char *label; int base; int ngpio; }; -#if IS_ENABLED(CONFIG_GPIO_GENERIC) - int bgpio_init(struct gpio_chip *gc, struct device *dev, unsigned long sz, void __iomem *dat, void __iomem *set, void __iomem *clr, void __iomem *dirout, void __iomem *dirin, @@ -463,10 +455,6 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev, #define BGPIOF_READ_OUTPUT_REG_SET BIT(4) /* reg_set stores output value */ #define BGPIOF_NO_OUTPUT BIT(5) /* only input */ -#endif /* CONFIG_GPIO_GENERIC */ - -#ifdef CONFIG_GPIOLIB_IRQCHIP - int gpiochip_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq); void gpiochip_irq_unmap(struct irq_domain *d, unsigned int irq); @@ -555,15 +543,11 @@ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, } #endif /* CONFIG_LOCKDEP */ -#endif /* CONFIG_GPIOLIB_IRQCHIP */ - int gpiochip_generic_request(struct gpio_chip *chip, unsigned offset); void gpiochip_generic_free(struct gpio_chip *chip, unsigned offset); int gpiochip_generic_config(struct gpio_chip *chip, unsigned offset, unsigned long config); -#ifdef CONFIG_PINCTRL - /** * struct gpio_pin_range - pin range controlled by a gpio chip * @node: list for maintaining set of pin ranges, used internally @@ -576,6 +560,8 @@ struct gpio_pin_range { struct pinctrl_gpio_range range; }; +#ifdef CONFIG_PINCTRL + int gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, unsigned int gpio_offset, unsigned int pin_offset, unsigned int npins); @@ -586,8 +572,6 @@ void gpiochip_remove_pin_ranges(struct gpio_chip *chip); #else /* ! CONFIG_PINCTRL */ -struct pinctrl_dev; - static inline int gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, unsigned int gpio_offset, unsigned int pin_offset, @@ -619,6 +603,11 @@ void gpiochip_free_own_desc(struct gpio_desc *desc); void devprop_gpiochip_set_names(struct gpio_chip *chip, const struct fwnode_handle *fwnode); + +#ifdef CONFIG_GPIOLIB + +struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc); + #else /* CONFIG_GPIOLIB */ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) @@ -630,4 +619,4 @@ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) #endif /* CONFIG_GPIOLIB */ -#endif +#endif /* __LINUX_GPIO_DRIVER_H */ -- cgit v1.2.3-71-gd317 From 10a08fd65ec1a68ccd86b19ec822ed5f2e50113f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 30 Jul 2019 11:55:59 +0200 Subject: ACPI: PM: Set up EC GPE for system wakeup from drivers that need it The EC GPE needs to be set up for system wakeup only if there is a driver depending on it, either intel-hid or intel-vbtn, bound to a button device that is expected to wake up the system from sleep (such as the power button on some Dell systems, like the XPS13 9360). It doesn't need to be set up for waking up the system from sleep in any other cases and whether or not it is expected to wake up the system from sleep doesn't depend on whether or not the LPS0 device is present in the ACPI namespace. For this reason, rearrange the ACPI suspend-to-idle code to make the drivers depending on the EC GPE wakeup take care of setting it up and decouple that from the LPS0 device handling. While at it, make intel-hid and intel-vbtn prepare for system wakeup only if they are allowed to wake up the system from sleep by user space (via sysfs). [Note that acpi_ec_mark_gpe_for_wake() and acpi_ec_set_gpe_wake_mask() are there to prevent the EC GPE from being disabled by the acpi_enable_all_wakeup_gpes() call in acpi_s2idle_prepare(), so on systems with either intel-hid or intel-vbtn this change doesn't affect any interactions with the hardware or platform firmware.] Signed-off-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko --- drivers/acpi/ec.c | 7 ++++++- drivers/acpi/internal.h | 2 -- drivers/acpi/sleep.c | 13 ++----------- drivers/platform/x86/intel-hid.c | 20 ++++++++++++++++---- drivers/platform/x86/intel-vbtn.c | 20 ++++++++++++++++---- include/linux/acpi.h | 4 ++++ include/linux/suspend.h | 1 + 7 files changed, 45 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 58c7ad402d8d..b996ca5f253f 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -1048,17 +1049,21 @@ void acpi_ec_unblock_transactions(void) acpi_ec_start(first_ec, true); } +#ifdef CONFIG_PM_SLEEP void acpi_ec_mark_gpe_for_wake(void) { if (first_ec && !ec_no_wakeup) acpi_mark_gpe_for_wake(NULL, first_ec->gpe); } +EXPORT_SYMBOL_GPL(acpi_ec_mark_gpe_for_wake); void acpi_ec_set_gpe_wake_mask(u8 action) { - if (first_ec && !ec_no_wakeup) + if (pm_suspend_no_platform() && first_ec && !ec_no_wakeup) acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); } +EXPORT_SYMBOL_GPL(acpi_ec_set_gpe_wake_mask); +#endif bool acpi_ec_dispatch_gpe(void) { diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 1b5f9ac06ea8..bcc080511197 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -194,8 +194,6 @@ void acpi_ec_ecdt_probe(void); void acpi_ec_dsdt_probe(void); void acpi_ec_block_transactions(void); void acpi_ec_unblock_transactions(void); -void acpi_ec_mark_gpe_for_wake(void); -void acpi_ec_set_gpe_wake_mask(u8 action); bool acpi_ec_dispatch_gpe(void); int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 970ae7c7a3f7..9cb0532f7471 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -930,8 +930,6 @@ static int lps0_device_attach(struct acpi_device *adev, acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n", bitmask); - - acpi_ec_mark_gpe_for_wake(); } else { acpi_handle_debug(adev->handle, "_DSM function 0 evaluation failed\n"); @@ -960,8 +958,6 @@ static int acpi_s2idle_prepare(void) if (lps0_device_handle) { acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF); acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY); - - acpi_ec_set_gpe_wake_mask(ACPI_GPE_ENABLE); } if (acpi_sci_irq_valid()) @@ -979,10 +975,7 @@ static int acpi_s2idle_prepare(void) static void acpi_s2idle_wake(void) { - if (!lps0_device_handle) - return; - - if (pm_debug_messages_on) + if (lps0_device_handle && pm_debug_messages_on) lpi_check_constraints(); /* @@ -1031,8 +1024,6 @@ static void acpi_s2idle_restore(void) disable_irq_wake(acpi_sci_irq); if (lps0_device_handle) { - acpi_ec_set_gpe_wake_mask(ACPI_GPE_DISABLE); - acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT); acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON); } @@ -1081,7 +1072,7 @@ bool acpi_s2idle_wakeup(void) bool acpi_sleep_no_ec_events(void) { - return !s2idle_in_progress || !lps0_device_handle; + return !s2idle_in_progress; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index bc0d55a59015..e51c72b92cbd 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -253,9 +253,12 @@ static void intel_button_array_enable(struct device *device, bool enable) static int intel_hid_pm_prepare(struct device *device) { - struct intel_hid_priv *priv = dev_get_drvdata(device); + if (device_may_wakeup(device)) { + struct intel_hid_priv *priv = dev_get_drvdata(device); - priv->wakeup_mode = true; + priv->wakeup_mode = true; + acpi_ec_set_gpe_wake_mask(ACPI_GPE_ENABLE); + } return 0; } @@ -270,9 +273,12 @@ static int intel_hid_pl_suspend_handler(struct device *device) static int intel_hid_pl_resume_handler(struct device *device) { - struct intel_hid_priv *priv = dev_get_drvdata(device); + if (device_may_wakeup(device)) { + struct intel_hid_priv *priv = dev_get_drvdata(device); - priv->wakeup_mode = false; + acpi_ec_set_gpe_wake_mask(ACPI_GPE_DISABLE); + priv->wakeup_mode = false; + } if (pm_resume_via_firmware()) { intel_hid_set_enable(device, true); intel_button_array_enable(device, true); @@ -491,6 +497,12 @@ static int intel_hid_probe(struct platform_device *device) } device_init_wakeup(&device->dev, true); + /* + * In order for system wakeup to work, the EC GPE has to be marked as + * a wakeup one, so do that here (this setting will persist, but it has + * no effect until the wakeup mask is set for the EC GPE). + */ + acpi_ec_mark_gpe_for_wake(); return 0; err_remove_notify: diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index a0d0cecff55f..ab84e1bbdedd 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -176,6 +176,12 @@ static int intel_vbtn_probe(struct platform_device *device) return -EBUSY; device_init_wakeup(&device->dev, true); + /* + * In order for system wakeup to work, the EC GPE has to be marked as + * a wakeup one, so do that here (this setting will persist, but it has + * no effect until the wakeup mask is set for the EC GPE). + */ + acpi_ec_mark_gpe_for_wake(); return 0; } @@ -195,17 +201,23 @@ static int intel_vbtn_remove(struct platform_device *device) static int intel_vbtn_pm_prepare(struct device *dev) { - struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + if (device_may_wakeup(dev)) { + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); - priv->wakeup_mode = true; + priv->wakeup_mode = true; + acpi_ec_set_gpe_wake_mask(ACPI_GPE_ENABLE); + } return 0; } static int intel_vbtn_pm_resume(struct device *dev) { - struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + if (device_may_wakeup(dev)) { + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); - priv->wakeup_mode = false; + acpi_ec_set_gpe_wake_mask(ACPI_GPE_DISABLE); + priv->wakeup_mode = false; + } return 0; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 9426b9aaed86..e65a4c5bbeae 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -931,6 +931,8 @@ int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); +void acpi_ec_mark_gpe_for_wake(void); +void acpi_ec_set_gpe_wake_mask(u8 action); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} @@ -939,6 +941,8 @@ static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } +static inline void acpi_ec_mark_gpe_for_wake(void) {} +static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 66ce3871ed61..f0c4a8445140 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -335,6 +335,7 @@ static inline void pm_set_suspend_via_firmware(void) {} static inline void pm_set_resume_via_firmware(void) {} static inline bool pm_suspend_via_firmware(void) { return false; } static inline bool pm_resume_via_firmware(void) { return false; } +static inline bool pm_suspend_no_platform(void) { return false; } static inline bool pm_suspend_default_s2idle(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} -- cgit v1.2.3-71-gd317 From 6cda08a20dbde45b021091230c8a359fa08c5103 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 23 Jul 2019 23:18:32 +0100 Subject: drivers: Introduce device lookup variants by name Add a helper to match the device name for device lookup. Also reuse this generic exported helper for the existing bus_find_device_by_name(). and add similar variants for driver/class. Cc: Alessandro Zummo Cc: Alexander Aring Cc: Alexander Shishkin Cc: Arnd Bergmann Cc: Dan Murphy Cc: Harald Freudenberger Cc: Heiko Carstens Cc: Jacek Anaszewski Cc: Lee Jones Cc: linux-leds@vger.kernel.org Cc: linux-rtc@vger.kernel.org Cc: linux-usb@vger.kernel.org Cc: linux-wpan@vger.kernel.org Cc: Maxime Coquelin Cc: Pavel Machek Cc: Peter Oberparleiter Cc: "Rafael J. Wysocki" Cc: Stefan Schmidt Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Signed-off-by: Suzuki K Poulose Reviewed-by: Heikki Krogerus Acked-by: Alexandre Belloni Link: https://lore.kernel.org/r/20190723221838.12024-2-suzuki.poulose@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 24 ----------------------- drivers/base/core.c | 6 ++++++ drivers/hwtracing/stm/core.c | 9 +-------- drivers/leds/led-class.c | 9 +-------- drivers/rtc/interface.c | 11 +---------- drivers/s390/cio/ccwgroup.c | 10 +--------- drivers/s390/cio/device.c | 15 +------------- drivers/s390/crypto/zcrypt_api.c | 11 +---------- drivers/usb/roles/class.c | 8 +------- drivers/usb/typec/class.c | 8 +------- include/linux/device.h | 42 +++++++++++++++++++++++++++++++++++++--- net/ieee802154/core.c | 7 +------ 12 files changed, 54 insertions(+), 106 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index df3cac739813..a1d1e8256324 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -342,30 +342,6 @@ struct device *bus_find_device(struct bus_type *bus, } EXPORT_SYMBOL_GPL(bus_find_device); -static int match_name(struct device *dev, const void *data) -{ - const char *name = data; - - return sysfs_streq(name, dev_name(dev)); -} - -/** - * bus_find_device_by_name - device iterator for locating a particular device of a specific name - * @bus: bus type - * @start: Device to begin with - * @name: name of the device to match - * - * This is similar to the bus_find_device() function above, but it handles - * searching by a name automatically, no need to write another strcmp matching - * function. - */ -struct device *bus_find_device_by_name(struct bus_type *bus, - struct device *start, const char *name) -{ - return bus_find_device(bus, start, (void *)name, match_name); -} -EXPORT_SYMBOL_GPL(bus_find_device_by_name); - /** * subsys_find_device_by_id - find a device with a specific enumeration number * @subsys: subsystem diff --git a/drivers/base/core.c b/drivers/base/core.c index da84a73f2ba6..fb83647d685a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3357,6 +3357,12 @@ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2) } EXPORT_SYMBOL_GPL(device_set_of_node_from_dev); +int device_match_name(struct device *dev, const void *name) +{ + return sysfs_streq(dev_name(dev), name); +} +EXPORT_SYMBOL_GPL(device_match_name); + int device_match_of_node(struct device *dev, const void *np) { return dev->of_node == np; diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index e55b902560de..2b6bd42632e8 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -89,13 +89,6 @@ static struct class stm_class = { .dev_groups = stm_groups, }; -static int stm_dev_match(struct device *dev, const void *data) -{ - const char *name = data; - - return sysfs_streq(name, dev_name(dev)); -} - /** * stm_find_device() - find stm device by name * @buf: character buffer containing the name @@ -116,7 +109,7 @@ struct stm_device *stm_find_device(const char *buf) if (!stm_core_up) return NULL; - dev = class_find_device(&stm_class, NULL, buf, stm_dev_match); + dev = class_find_device_by_name(&stm_class, buf); if (!dev) return NULL; diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 4793e77808e2..d54c8e4d8954 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -213,13 +213,6 @@ static int led_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(leds_class_dev_pm_ops, led_suspend, led_resume); -static int match_name(struct device *dev, const void *data) -{ - if (!dev_name(dev)) - return 0; - return !strcmp(dev_name(dev), (char *)data); -} - static int led_classdev_next_name(const char *init_name, char *name, size_t len) { @@ -230,7 +223,7 @@ static int led_classdev_next_name(const char *init_name, char *name, strlcpy(name, init_name, len); while ((ret < len) && - (dev = class_find_device(leds_class, NULL, name, match_name))) { + (dev = class_find_device_by_name(leds_class, name))) { put_device(dev); ret = snprintf(name, len, "%s_%u", init_name, ++i); } diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 72b7ddc43116..c93ef33b01d3 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -663,21 +663,12 @@ void rtc_update_irq(struct rtc_device *rtc, } EXPORT_SYMBOL_GPL(rtc_update_irq); -static int __rtc_match(struct device *dev, const void *data) -{ - const char *name = data; - - if (strcmp(dev_name(dev), name) == 0) - return 1; - return 0; -} - struct rtc_device *rtc_class_open(const char *name) { struct device *dev; struct rtc_device *rtc = NULL; - dev = class_find_device(rtc_class, NULL, name, __rtc_match); + dev = class_find_device_by_name(rtc_class, name); if (dev) rtc = to_rtc_device(dev); diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index c522e9313c50..d843e362c167 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -608,13 +608,6 @@ void ccwgroup_driver_unregister(struct ccwgroup_driver *cdriver) } EXPORT_SYMBOL(ccwgroup_driver_unregister); -static int __ccwgroupdev_check_busid(struct device *dev, const void *id) -{ - const char *bus_id = id; - - return (strcmp(bus_id, dev_name(dev)) == 0); -} - /** * get_ccwgroupdev_by_busid() - obtain device from a bus id * @gdrv: driver the device is owned by @@ -631,8 +624,7 @@ struct ccwgroup_device *get_ccwgroupdev_by_busid(struct ccwgroup_driver *gdrv, { struct device *dev; - dev = driver_find_device(&gdrv->driver, NULL, bus_id, - __ccwgroupdev_check_busid); + dev = driver_find_device_by_name(&gdrv->driver, bus_id); return dev ? to_ccwgroupdev(dev) : NULL; } diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index c421899be20f..131430bd48d9 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1695,18 +1695,6 @@ int ccw_device_force_console(struct ccw_device *cdev) EXPORT_SYMBOL_GPL(ccw_device_force_console); #endif -/* - * get ccw_device matching the busid, but only if owned by cdrv - */ -static int -__ccwdev_check_busid(struct device *dev, const void *id) -{ - const char *bus_id = id; - - return (strcmp(bus_id, dev_name(dev)) == 0); -} - - /** * get_ccwdev_by_busid() - obtain device from a bus id * @cdrv: driver the device is owned by @@ -1723,8 +1711,7 @@ struct ccw_device *get_ccwdev_by_busid(struct ccw_driver *cdrv, { struct device *dev; - dev = driver_find_device(&cdrv->driver, NULL, (void *)bus_id, - __ccwdev_check_busid); + dev = driver_find_device_by_name(&cdrv->driver, bus_id); return dev ? to_ccwdev(dev) : NULL; } diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 1058b4b5cc1e..38a5a47b8c9c 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -133,12 +133,6 @@ struct zcdn_device { static int zcdn_create(const char *name); static int zcdn_destroy(const char *name); -/* helper function, matches the name for find_zcdndev_by_name() */ -static int __match_zcdn_name(struct device *dev, const void *data) -{ - return strcmp(dev_name(dev), (const char *)data) == 0; -} - /* helper function, matches the devt value for find_zcdndev_by_devt() */ static int __match_zcdn_devt(struct device *dev, const void *data) { @@ -152,10 +146,7 @@ static int __match_zcdn_devt(struct device *dev, const void *data) */ static inline struct zcdn_device *find_zcdndev_by_name(const char *name) { - struct device *dev = - class_find_device(zcrypt_class, NULL, - (void *) name, - __match_zcdn_name); + struct device *dev = class_find_device_by_name(zcrypt_class, name); return dev ? to_zcdn_dev(dev) : NULL; } diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 86defca6623e..c8efe60e2465 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -90,11 +90,6 @@ static int switch_fwnode_match(struct device *dev, const void *fwnode) return dev_fwnode(dev) == fwnode; } -static int switch_name_match(struct device *dev, const void *name) -{ - return !strcmp((const char *)name, dev_name(dev)); -} - static void *usb_role_switch_match(struct device_connection *con, int ep, void *data) { @@ -107,8 +102,7 @@ static void *usb_role_switch_match(struct device_connection *con, int ep, dev = class_find_device(role_class, NULL, con->fwnode, switch_fwnode_match); } else { - dev = class_find_device(role_class, NULL, con->endpoint[ep], - switch_name_match); + dev = class_find_device_by_name(role_class, con->endpoint[ep]); } return dev ? to_role_switch(dev) : ERR_PTR(-EPROBE_DEFER); diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index a18285a990a8..9b0d15b487e5 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -210,11 +210,6 @@ static int typec_port_fwnode_match(struct device *dev, const void *fwnode) return dev_fwnode(dev) == fwnode; } -static int typec_port_name_match(struct device *dev, const void *name) -{ - return !strcmp((const char *)name, dev_name(dev)); -} - static void *typec_port_match(struct device_connection *con, int ep, void *data) { struct device *dev; @@ -227,8 +222,7 @@ static void *typec_port_match(struct device_connection *con, int ep, void *data) return class_find_device(typec_class, NULL, con->fwnode, typec_port_fwnode_match); - dev = class_find_device(typec_class, NULL, con->endpoint[ep], - typec_port_name_match); + dev = class_find_device_by_name(typec_class, con->endpoint[ep]); return dev ? dev : ERR_PTR(-EPROBE_DEFER); } diff --git a/include/linux/device.h b/include/linux/device.h index c330b75c6c57..3ba376b8b456 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -164,6 +164,7 @@ void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter); void subsys_dev_iter_exit(struct subsys_dev_iter *iter); +int device_match_name(struct device *dev, const void *name); int device_match_of_node(struct device *dev, const void *np); int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, @@ -171,9 +172,20 @@ int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, struct device *bus_find_device(struct bus_type *bus, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); -struct device *bus_find_device_by_name(struct bus_type *bus, - struct device *start, - const char *name); +/** + * bus_find_device_by_name - device iterator for locating a particular device + * of a specific name. + * @bus: bus type + * @start: Device to begin with + * @name: name of the device to match + */ +static inline struct device *bus_find_device_by_name(struct bus_type *bus, + struct device *start, + const char *name) +{ + return bus_find_device(bus, start, name, device_match_name); +} + struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, struct device *hint); int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, @@ -342,6 +354,18 @@ struct device *driver_find_device(struct device_driver *drv, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); +/** + * driver_find_device_by_name - device iterator for locating a particular device + * of a specific name. + * @driver: the driver we're iterating + * @name: name of the device to match + */ +static inline struct device *driver_find_device_by_name(struct device_driver *drv, + const char *name) +{ + return driver_find_device(drv, NULL, name, device_match_name); +} + void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); int driver_deferred_probe_check_state_continue(struct device *dev); @@ -471,6 +495,18 @@ extern struct device *class_find_device(struct class *class, struct device *start, const void *data, int (*match)(struct device *, const void *)); +/** + * class_find_device_by_name - device iterator for locating a particular device + * of a specific name. + * @class: class type + * @name: name of the device to match + */ +static inline struct device *class_find_device_by_name(struct class *class, + const char *name) +{ + return class_find_device(class, NULL, name, device_match_name); +} + struct class_attribute { struct attribute attr; ssize_t (*show)(struct class *class, struct class_attribute *attr, diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index 60b7ac56a1f5..de259b5170ab 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -23,11 +23,6 @@ LIST_HEAD(cfg802154_rdev_list); int cfg802154_rdev_list_generation; -static int wpan_phy_match(struct device *dev, const void *data) -{ - return !strcmp(dev_name(dev), (const char *)data); -} - struct wpan_phy *wpan_phy_find(const char *str) { struct device *dev; @@ -35,7 +30,7 @@ struct wpan_phy *wpan_phy_find(const char *str) if (WARN_ON(!str)) return NULL; - dev = class_find_device(&wpan_phy_class, NULL, str, wpan_phy_match); + dev = class_find_device_by_name(&wpan_phy_class, str); if (!dev) return NULL; -- cgit v1.2.3-71-gd317 From cfba5de9b99f8bbb8b4ea11b3049784e78b8759b Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 23 Jul 2019 23:18:33 +0100 Subject: drivers: Introduce device lookup variants by of_node Introduce wrappers for {bus/driver/class}_find_device() to locate devices by its of_node. Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Daniel Vetter Cc: devicetree@vger.kernel.org Cc: Florian Fainelli Cc: Frank Rowand Cc: Heiko Stuebner Cc: Liam Girdwood Cc: linux-i2c@vger.kernel.org Cc: linux-rockchip@lists.infradead.org Cc: linux-spi@vger.kernel.org Cc: Mathieu Poirier Cc: Rob Herring Cc: Srinivas Kandagatla Cc: Takashi Iwai Cc: Alan Tull Cc: linux-fpga@vger.kernel.org Cc: Peter Rosin Cc: Florian Fainelli Cc: Heiner Kallweit Cc: "David S. Miller" Cc: Andrew Lunn Cc: Liam Girdwood Cc: "Rafael J. Wysocki" Cc: Thor Thayer Cc: Jiri Slaby Cc: Andrew Lunn Cc: Peter Rosin Signed-off-by: Suzuki K Poulose Acked-by: Lee Jones Acked-by: Wolfram Sang # I2C part Acked-by: Moritz Fischer # For FPGA part Acked-by: Mark Brown Link: https://lore.kernel.org/r/20190723221838.12024-3-suzuki.poulose@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/amba/tegra-ahb.c | 11 +---------- drivers/fpga/fpga-bridge.c | 8 +------- drivers/fpga/fpga-mgr.c | 8 +------- drivers/gpu/drm/drm_mipi_dsi.c | 7 +------ drivers/i2c/i2c-core-of.c | 7 +------ drivers/mfd/altera-sysmgr.c | 14 ++----------- drivers/mux/core.c | 7 +------ drivers/net/phy/mdio_bus.c | 9 +-------- drivers/nvmem/core.c | 7 +------ drivers/of/of_mdio.c | 8 +------- drivers/of/platform.c | 7 +------ drivers/regulator/of_regulator.c | 7 +------ drivers/spi/spi.c | 20 ++++--------------- include/linux/device.h | 37 +++++++++++++++++++++++++++++++++++ sound/soc/rockchip/rk3399_gru_sound.c | 9 ++------- 15 files changed, 56 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/drivers/amba/tegra-ahb.c b/drivers/amba/tegra-ahb.c index aa64eece77a6..57d3b2e2d007 100644 --- a/drivers/amba/tegra-ahb.c +++ b/drivers/amba/tegra-ahb.c @@ -134,22 +134,13 @@ static inline void gizmo_writel(struct tegra_ahb *ahb, u32 value, u32 offset) } #ifdef CONFIG_TEGRA_IOMMU_SMMU -static int tegra_ahb_match_by_smmu(struct device *dev, const void *data) -{ - struct tegra_ahb *ahb = dev_get_drvdata(dev); - const struct device_node *dn = data; - - return (ahb->dev->of_node == dn) ? 1 : 0; -} - int tegra_ahb_enable_smmu(struct device_node *dn) { struct device *dev; u32 val; struct tegra_ahb *ahb; - dev = driver_find_device(&tegra_ahb_driver.driver, NULL, dn, - tegra_ahb_match_by_smmu); + dev = driver_find_device_by_of_node(&tegra_ahb_driver.driver, dn); if (!dev) return -EPROBE_DEFER; ahb = dev_get_drvdata(dev); diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index 80bd8f1b2aa6..4bab9028940a 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -19,11 +19,6 @@ static struct class *fpga_bridge_class; /* Lock for adding/removing bridges to linked lists*/ static spinlock_t bridge_list_lock; -static int fpga_bridge_of_node_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /** * fpga_bridge_enable - Enable transactions on the bridge * @@ -104,8 +99,7 @@ struct fpga_bridge *of_fpga_bridge_get(struct device_node *np, { struct device *dev; - dev = class_find_device(fpga_bridge_class, NULL, np, - fpga_bridge_of_node_match); + dev = class_find_device_by_of_node(fpga_bridge_class, np); if (!dev) return ERR_PTR(-ENODEV); diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c index c3866816456a..e05104f5e40c 100644 --- a/drivers/fpga/fpga-mgr.c +++ b/drivers/fpga/fpga-mgr.c @@ -482,11 +482,6 @@ struct fpga_manager *fpga_mgr_get(struct device *dev) } EXPORT_SYMBOL_GPL(fpga_mgr_get); -static int fpga_mgr_of_node_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /** * of_fpga_mgr_get - Given a device node, get a reference to a fpga mgr. * @@ -498,8 +493,7 @@ struct fpga_manager *of_fpga_mgr_get(struct device_node *node) { struct device *dev; - dev = class_find_device(fpga_mgr_class, NULL, node, - fpga_mgr_of_node_match); + dev = class_find_device_by_of_node(fpga_mgr_class, node); if (!dev) return ERR_PTR(-ENODEV); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index ad19df0686c9..bd2498bbd74a 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -93,11 +93,6 @@ static struct bus_type mipi_dsi_bus_type = { .pm = &mipi_dsi_device_pm_ops, }; -static int of_device_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /** * of_find_mipi_dsi_device_by_node() - find the MIPI DSI device matching a * device tree node @@ -110,7 +105,7 @@ struct mipi_dsi_device *of_find_mipi_dsi_device_by_node(struct device_node *np) { struct device *dev; - dev = bus_find_device(&mipi_dsi_bus_type, NULL, np, of_device_match); + dev = bus_find_device_by_of_node(&mipi_dsi_bus_type, np); return dev ? to_mipi_dsi_device(dev) : NULL; } diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index d1c48dec7118..6f632d543fcc 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -113,11 +113,6 @@ void of_i2c_register_devices(struct i2c_adapter *adap) of_node_put(bus); } -static int of_dev_node_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - static int of_dev_or_parent_node_match(struct device *dev, const void *data) { if (dev->of_node == data) @@ -135,7 +130,7 @@ struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) struct device *dev; struct i2c_client *client; - dev = bus_find_device(&i2c_bus_type, NULL, node, of_dev_node_match); + dev = bus_find_device_by_of_node(&i2c_bus_type, node); if (!dev) return NULL; diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c index 2ee14d8a6d31..d2a13a547a3c 100644 --- a/drivers/mfd/altera-sysmgr.c +++ b/drivers/mfd/altera-sysmgr.c @@ -87,16 +87,6 @@ static struct regmap_config altr_sysmgr_regmap_cfg = { .use_single_write = true, }; -/** - * sysmgr_match_phandle - * Matching function used by driver_find_device(). - * Return: True if match is found, otherwise false. - */ -static int sysmgr_match_phandle(struct device *dev, const void *data) -{ - return dev->of_node == (const struct device_node *)data; -} - /** * altr_sysmgr_regmap_lookup_by_phandle * Find the sysmgr previous configured in probe() and return regmap property. @@ -117,8 +107,8 @@ struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np, if (!sysmgr_np) return ERR_PTR(-ENODEV); - dev = driver_find_device(&altr_sysmgr_driver.driver, NULL, - (void *)sysmgr_np, sysmgr_match_phandle); + dev = driver_find_device_by_of_node(&altr_sysmgr_driver.driver, + (void *)sysmgr_np); of_node_put(sysmgr_np); if (!dev) return ERR_PTR(-EPROBE_DEFER); diff --git a/drivers/mux/core.c b/drivers/mux/core.c index d1271c1ee23c..1fb22388e7e0 100644 --- a/drivers/mux/core.c +++ b/drivers/mux/core.c @@ -405,17 +405,12 @@ int mux_control_deselect(struct mux_control *mux) } EXPORT_SYMBOL_GPL(mux_control_deselect); -static int of_dev_node_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /* Note this function returns a reference to the mux_chip dev. */ static struct mux_chip *of_find_mux_chip_by_node(struct device_node *np) { struct device *dev; - dev = class_find_device(&mux_class, NULL, np, of_dev_node_match); + dev = class_find_device_by_of_node(&mux_class, np); return dev ? to_mux_chip(dev) : NULL; } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index bd04fe762056..ce940871331e 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -262,11 +262,6 @@ static struct class mdio_bus_class = { }; #if IS_ENABLED(CONFIG_OF_MDIO) -/* Helper function for of_mdio_find_bus */ -static int of_mdio_bus_match(struct device *dev, const void *mdio_bus_np) -{ - return dev->of_node == mdio_bus_np; -} /** * of_mdio_find_bus - Given an mii_bus node, find the mii_bus. * @mdio_bus_np: Pointer to the mii_bus. @@ -287,9 +282,7 @@ struct mii_bus *of_mdio_find_bus(struct device_node *mdio_bus_np) if (!mdio_bus_np) return NULL; - d = class_find_device(&mdio_bus_class, NULL, mdio_bus_np, - of_mdio_bus_match); - + d = class_find_device_by_of_node(&mdio_bus_class, mdio_bus_np); return d ? to_mii_bus(d) : NULL; } EXPORT_SYMBOL(of_mdio_find_bus); diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index ac5d945be88a..057d1ff87d5d 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -76,11 +76,6 @@ static struct bus_type nvmem_bus_type = { .name = "nvmem", }; -static int of_nvmem_match(struct device *dev, const void *nvmem_np) -{ - return dev->of_node == nvmem_np; -} - static struct nvmem_device *of_nvmem_find(struct device_node *nvmem_np) { struct device *d; @@ -88,7 +83,7 @@ static struct nvmem_device *of_nvmem_find(struct device_node *nvmem_np) if (!nvmem_np) return NULL; - d = bus_find_device(&nvmem_bus_type, NULL, nvmem_np, of_nvmem_match); + d = bus_find_device_by_of_node(&nvmem_bus_type, nvmem_np); if (!d) return NULL; diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 44f53496cab1..000b95787df1 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -280,12 +280,6 @@ unregister: } EXPORT_SYMBOL(of_mdiobus_register); -/* Helper function for of_phy_find_device */ -static int of_phy_match(struct device *dev, const void *phy_np) -{ - return dev->of_node == phy_np; -} - /** * of_phy_find_device - Give a PHY node, find the phy_device * @phy_np: Pointer to the phy's device tree node @@ -301,7 +295,7 @@ struct phy_device *of_phy_find_device(struct device_node *phy_np) if (!phy_np) return NULL; - d = bus_find_device(&mdio_bus_type, NULL, phy_np, of_phy_match); + d = bus_find_device_by_of_node(&mdio_bus_type, phy_np); if (d) { mdiodev = to_mdio_device(d); if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 7801e25e6895..b47a2292fe8e 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -37,11 +37,6 @@ static const struct of_device_id of_skipped_node_table[] = { {} /* Empty terminated list */ }; -static int of_dev_node_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /** * of_find_device_by_node - Find the platform_device associated with a node * @np: Pointer to device tree node @@ -55,7 +50,7 @@ struct platform_device *of_find_device_by_node(struct device_node *np) { struct device *dev; - dev = bus_find_device(&platform_bus_type, NULL, np, of_dev_node_match); + dev = bus_find_device_by_of_node(&platform_bus_type, np); return dev ? to_platform_device(dev) : NULL; } EXPORT_SYMBOL(of_find_device_by_node); diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 397918ebba55..20dcc9c03adc 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -460,16 +460,11 @@ error: return NULL; } -static int of_node_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - struct regulator_dev *of_find_regulator_by_node(struct device_node *np) { struct device *dev; - dev = class_find_device(®ulator_class, NULL, np, of_node_match); + dev = class_find_device_by_of_node(®ulator_class, np); return dev ? dev_to_rdev(dev) : NULL; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 75ac046cae52..a591da87981a 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3652,37 +3652,25 @@ EXPORT_SYMBOL_GPL(spi_write_then_read); /*-------------------------------------------------------------------------*/ #if IS_ENABLED(CONFIG_OF) -static int __spi_of_device_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /* must call put_device() when done with returned spi_device device */ struct spi_device *of_find_spi_device_by_node(struct device_node *node) { - struct device *dev = bus_find_device(&spi_bus_type, NULL, node, - __spi_of_device_match); + struct device *dev = bus_find_device_by_of_node(&spi_bus_type, node); + return dev ? to_spi_device(dev) : NULL; } EXPORT_SYMBOL_GPL(of_find_spi_device_by_node); #endif /* IS_ENABLED(CONFIG_OF) */ #if IS_ENABLED(CONFIG_OF_DYNAMIC) -static int __spi_of_controller_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /* the spi controllers are not using spi_bus, so we find it with another way */ static struct spi_controller *of_find_spi_controller_by_node(struct device_node *node) { struct device *dev; - dev = class_find_device(&spi_master_class, NULL, node, - __spi_of_controller_match); + dev = class_find_device_by_of_node(&spi_master_class, node); if (!dev && IS_ENABLED(CONFIG_SPI_SLAVE)) - dev = class_find_device(&spi_slave_class, NULL, node, - __spi_of_controller_match); + dev = class_find_device_by_of_node(&spi_slave_class, node); if (!dev) return NULL; diff --git a/include/linux/device.h b/include/linux/device.h index 3ba376b8b456..29d8d7ad41e6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -186,6 +186,18 @@ static inline struct device *bus_find_device_by_name(struct bus_type *bus, return bus_find_device(bus, start, name, device_match_name); } +/** + * bus_find_device_by_of_node : device iterator for locating a particular device + * matching the of_node. + * @bus: bus type + * @np: of_node of the device to match. + */ +static inline struct device * +bus_find_device_by_of_node(struct bus_type *bus, const struct device_node *np) +{ + return bus_find_device(bus, NULL, np, device_match_of_node); +} + struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, struct device *hint); int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, @@ -366,6 +378,19 @@ static inline struct device *driver_find_device_by_name(struct device_driver *dr return driver_find_device(drv, NULL, name, device_match_name); } +/** + * driver_find_device_by_of_node- device iterator for locating a particular device + * by of_node pointer. + * @driver: the driver we're iterating + * @np: of_node pointer to match. + */ +static inline struct device * +driver_find_device_by_of_node(struct device_driver *drv, + const struct device_node *np) +{ + return driver_find_device(drv, NULL, np, device_match_of_node); +} + void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); int driver_deferred_probe_check_state_continue(struct device *dev); @@ -507,6 +532,18 @@ static inline struct device *class_find_device_by_name(struct class *class, return class_find_device(class, NULL, name, device_match_name); } +/** + * class_find_device_by_of_node : device iterator for locating a particular device + * matching the of_node. + * @class: class type + * @np: of_node of the device to match. + */ +static inline struct device * +class_find_device_by_of_node(struct class *class, const struct device_node *np) +{ + return class_find_device(class, NULL, np, device_match_of_node); +} + struct class_attribute { struct attribute attr; ssize_t (*show)(struct class *class, struct class_attribute *attr, diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c index c16b0ffe8cfc..d951100bf770 100644 --- a/sound/soc/rockchip/rk3399_gru_sound.c +++ b/sound/soc/rockchip/rk3399_gru_sound.c @@ -422,11 +422,6 @@ static const struct dailink_match_data dailink_match[] = { }, }; -static int of_dev_node_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - static int rockchip_sound_codec_node_match(struct device_node *np_codec) { struct device *dev; @@ -438,8 +433,8 @@ static int rockchip_sound_codec_node_match(struct device_node *np_codec) continue; if (dailink_match[i].bus_type) { - dev = bus_find_device(dailink_match[i].bus_type, NULL, - np_codec, of_dev_node_match); + dev = bus_find_device_by_of_node(dailink_match[i].bus_type, + np_codec); if (!dev) continue; put_device(dev); -- cgit v1.2.3-71-gd317 From 67843bbaf36eb087714f40e783ee78e99e9e4b86 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 23 Jul 2019 23:18:34 +0100 Subject: drivers: Introduce device lookup variants by fwnode Add a helper to match the firmware node handle of a device and provide wrappers for {bus/class/driver}_find_device() APIs to avoid proliferation of duplicate custom match functions. Cc: "David S. Miller" Cc: Doug Ledford Cc: Jason Gunthorpe Cc: linux-usb@vger.kernel.org Cc: "Rafael J. Wysocki" Cc: Ulf Hansson Cc: Joe Perches Cc: Will Deacon Cc: Joerg Roedel Signed-off-by: Suzuki K Poulose Acked-by: Robin Murphy Reviewed-by: Mathieu Poirier Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20190723221838.12024-4-suzuki.poulose@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 6 ++++ drivers/base/devcon.c | 8 +---- drivers/hwtracing/coresight/coresight-platform.c | 11 ++---- drivers/hwtracing/coresight/coresight-priv.h | 2 -- drivers/hwtracing/coresight/coresight.c | 4 +-- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 8 +---- drivers/iommu/arm-smmu-v3.c | 9 ++--- drivers/iommu/arm-smmu.c | 9 ++--- drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c | 8 +---- drivers/usb/roles/class.c | 8 +---- drivers/usb/typec/class.c | 8 +---- include/linux/device.h | 39 ++++++++++++++++++++++ 12 files changed, 57 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index fb83647d685a..e8f81a667545 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3368,3 +3368,9 @@ int device_match_of_node(struct device *dev, const void *np) return dev->of_node == np; } EXPORT_SYMBOL_GPL(device_match_of_node); + +int device_match_fwnode(struct device *dev, const void *fwnode) +{ + return dev_fwnode(dev) == fwnode; +} +EXPORT_SYMBOL_GPL(device_match_fwnode); diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c index 09f28479b243..1d488dc5dd0c 100644 --- a/drivers/base/devcon.c +++ b/drivers/base/devcon.c @@ -133,19 +133,13 @@ static struct bus_type *generic_match_buses[] = { NULL, }; -static int device_fwnode_match(struct device *dev, const void *fwnode) -{ - return dev_fwnode(dev) == fwnode; -} - static void *device_connection_fwnode_match(struct device_connection *con) { struct bus_type *bus; struct device *dev; for (bus = generic_match_buses[0]; bus; bus++) { - dev = bus_find_device(bus, NULL, (void *)con->fwnode, - device_fwnode_match); + dev = bus_find_device_by_fwnode(bus, con->fwnode); if (dev && !strncmp(dev_name(dev), con->id, strlen(con->id))) return dev; diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c index dad7d96c5943..3c5bee429105 100644 --- a/drivers/hwtracing/coresight/coresight-platform.c +++ b/drivers/hwtracing/coresight/coresight-platform.c @@ -37,11 +37,6 @@ static int coresight_alloc_conns(struct device *dev, return 0; } -int coresight_device_fwnode_match(struct device *dev, const void *fwnode) -{ - return dev_fwnode(dev) == fwnode; -} - static struct device * coresight_find_device_by_fwnode(struct fwnode_handle *fwnode) { @@ -51,8 +46,7 @@ coresight_find_device_by_fwnode(struct fwnode_handle *fwnode) * If we have a non-configurable replicator, it will be found on the * platform bus. */ - dev = bus_find_device(&platform_bus_type, NULL, - fwnode, coresight_device_fwnode_match); + dev = bus_find_device_by_fwnode(&platform_bus_type, fwnode); if (dev) return dev; @@ -60,8 +54,7 @@ coresight_find_device_by_fwnode(struct fwnode_handle *fwnode) * We have a configurable component - circle through the AMBA bus * looking for the device that matches the endpoint node. */ - return bus_find_device(&amba_bustype, NULL, - fwnode, coresight_device_fwnode_match); + return bus_find_device_by_fwnode(&amba_bustype, fwnode); } #ifdef CONFIG_OF diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 7d401790dd7e..61d7f9ff054d 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -202,6 +202,4 @@ static inline void *coresight_get_uci_data(const struct amba_id *id) void coresight_release_platform_data(struct coresight_platform_data *pdata); -int coresight_device_fwnode_match(struct device *dev, const void *fwnode); - #endif diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 55db77f6410b..6453c67a4d01 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -1046,9 +1046,7 @@ static void coresight_fixup_device_conns(struct coresight_device *csdev) struct coresight_connection *conn = &csdev->pdata->conns[i]; struct device *dev = NULL; - dev = bus_find_device(&coresight_bustype, NULL, - (void *)conn->child_fwnode, - coresight_device_fwnode_match); + dev = bus_find_device_by_fwnode(&coresight_bustype, conn->child_fwnode); if (dev) { conn->child_dev = to_coresight_device(dev); /* and put reference from 'bus_find_device()' */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 81e6dedb1e02..fa05e943038a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -4499,19 +4499,13 @@ static const struct acpi_device_id hns_roce_acpi_match[] = { }; MODULE_DEVICE_TABLE(acpi, hns_roce_acpi_match); -static int hns_roce_node_match(struct device *dev, const void *fwnode) -{ - return dev->fwnode == fwnode; -} - static struct platform_device *hns_roce_find_pdev(struct fwnode_handle *fwnode) { struct device *dev; /* get the 'device' corresponding to the matching 'fwnode' */ - dev = bus_find_device(&platform_bus_type, NULL, - fwnode, hns_roce_node_match); + dev = bus_find_device_by_fwnode(&platform_bus_type, fwnode); /* get the platform device */ return dev ? to_platform_device(dev) : NULL; } diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index a9a9fabd3968..6f0e13fa5e1a 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2034,16 +2034,11 @@ arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) static struct platform_driver arm_smmu_driver; -static int arm_smmu_match_node(struct device *dev, const void *data) -{ - return dev->fwnode == data; -} - static struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { - struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL, - fwnode, arm_smmu_match_node); + struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver, + fwnode); put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 64977c131ee6..aa06498f291d 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1426,16 +1426,11 @@ static bool arm_smmu_capable(enum iommu_cap cap) } } -static int arm_smmu_match_node(struct device *dev, const void *data) -{ - return dev->fwnode == data; -} - static struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { - struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL, - fwnode, arm_smmu_match_node); + struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver, + fwnode); put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index bb6586d0e5af..ed3829ae4ef1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -754,17 +754,11 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) return (void *)misc_op; } -static int hns_dsaf_dev_match(struct device *dev, const void *fwnode) -{ - return dev->fwnode == fwnode; -} - struct platform_device *hns_dsaf_find_platform_device(struct fwnode_handle *fwnode) { struct device *dev; - dev = bus_find_device(&platform_bus_type, NULL, - fwnode, hns_dsaf_dev_match); + dev = bus_find_device_by_fwnode(&platform_bus_type, fwnode); return dev ? to_platform_device(dev) : NULL; } diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index c8efe60e2465..0526efbc4922 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -85,11 +85,6 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw) } EXPORT_SYMBOL_GPL(usb_role_switch_get_role); -static int switch_fwnode_match(struct device *dev, const void *fwnode) -{ - return dev_fwnode(dev) == fwnode; -} - static void *usb_role_switch_match(struct device_connection *con, int ep, void *data) { @@ -99,8 +94,7 @@ static void *usb_role_switch_match(struct device_connection *con, int ep, if (con->id && !fwnode_property_present(con->fwnode, con->id)) return NULL; - dev = class_find_device(role_class, NULL, con->fwnode, - switch_fwnode_match); + dev = class_find_device_by_fwnode(role_class, con->fwnode); } else { dev = class_find_device_by_name(role_class, con->endpoint[ep]); } diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 9b0d15b487e5..94a3eda62add 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -205,11 +205,6 @@ static void typec_altmode_put_partner(struct altmode *altmode) put_device(&adev->dev); } -static int typec_port_fwnode_match(struct device *dev, const void *fwnode) -{ - return dev_fwnode(dev) == fwnode; -} - static void *typec_port_match(struct device_connection *con, int ep, void *data) { struct device *dev; @@ -219,8 +214,7 @@ static void *typec_port_match(struct device_connection *con, int ep, void *data) * we need to return ERR_PTR(-PROBE_DEFER) when there is no device. */ if (con->fwnode) - return class_find_device(typec_class, NULL, con->fwnode, - typec_port_fwnode_match); + return class_find_device_by_fwnode(typec_class, con->fwnode); dev = class_find_device_by_name(typec_class, con->endpoint[ep]); diff --git a/include/linux/device.h b/include/linux/device.h index 29d8d7ad41e6..7133fc1c285d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -166,6 +166,7 @@ void subsys_dev_iter_exit(struct subsys_dev_iter *iter); int device_match_name(struct device *dev, const void *name); int device_match_of_node(struct device *dev, const void *np); +int device_match_fwnode(struct device *dev, const void *fwnode); int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); @@ -198,6 +199,18 @@ bus_find_device_by_of_node(struct bus_type *bus, const struct device_node *np) return bus_find_device(bus, NULL, np, device_match_of_node); } +/** + * bus_find_device_by_fwnode : device iterator for locating a particular device + * matching the fwnode. + * @bus: bus type + * @fwnode: fwnode of the device to match. + */ +static inline struct device * +bus_find_device_by_fwnode(struct bus_type *bus, const struct fwnode_handle *fwnode) +{ + return bus_find_device(bus, NULL, fwnode, device_match_fwnode); +} + struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, struct device *hint); int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, @@ -391,6 +404,19 @@ driver_find_device_by_of_node(struct device_driver *drv, return driver_find_device(drv, NULL, np, device_match_of_node); } +/** + * driver_find_device_by_fwnode- device iterator for locating a particular device + * by fwnode pointer. + * @driver: the driver we're iterating + * @fwnode: fwnode pointer to match. + */ +static inline struct device * +driver_find_device_by_fwnode(struct device_driver *drv, + const struct fwnode_handle *fwnode) +{ + return driver_find_device(drv, NULL, fwnode, device_match_fwnode); +} + void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); int driver_deferred_probe_check_state_continue(struct device *dev); @@ -544,6 +570,19 @@ class_find_device_by_of_node(struct class *class, const struct device_node *np) return class_find_device(class, NULL, np, device_match_of_node); } +/** + * class_find_device_by_fwnode : device iterator for locating a particular device + * matching the fwnode. + * @class: class type + * @fwnode: fwnode of the device to match. + */ +static inline struct device * +class_find_device_by_fwnode(struct class *class, + const struct fwnode_handle *fwnode) +{ + return class_find_device(class, NULL, fwnode, device_match_fwnode); +} + struct class_attribute { struct attribute attr; ssize_t (*show)(struct class *class, struct class_attribute *attr, -- cgit v1.2.3-71-gd317 From 4495dfdd6193d9712b7b8f5d699d89d5996e6aaa Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 23 Jul 2019 23:18:35 +0100 Subject: drivers: Introduce device lookup variants by device type Add a helper to match a device by its type and provide wrappers for {bus/class/driver}_find_device() APIs. Cc: Alexander Shishkin Cc: Arnd Bergmann Cc: Harald Freudenberger Cc: Heiko Carstens Cc: linux-usb@vger.kernel.org Cc: Oliver Neukum Cc: Sebastian Andrzej Siewior Cc: Tomas Winkler Cc: "Rafael J. Wysocki" Cc: Greg Kroah-Hartman Cc: Ulf Hansson Cc: Joe Perches Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20190723221838.12024-5-suzuki.poulose@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 15 +++++++-------- drivers/hwtracing/intel_th/core.c | 10 +--------- drivers/misc/mei/main.c | 9 +-------- drivers/s390/crypto/zcrypt_api.c | 11 +---------- drivers/tty/tty_io.c | 8 +------- drivers/usb/core/devio.c | 8 +------- include/linux/device.h | 37 +++++++++++++++++++++++++++++++++++++ 7 files changed, 49 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index e8f81a667545..3abc32b60c0a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2867,13 +2867,6 @@ struct device *device_create_with_groups(struct class *class, } EXPORT_SYMBOL_GPL(device_create_with_groups); -static int __match_devt(struct device *dev, const void *data) -{ - const dev_t *devt = data; - - return dev->devt == *devt; -} - /** * device_destroy - removes a device that was created with device_create() * @class: pointer to the struct class that this device was registered with @@ -2886,7 +2879,7 @@ void device_destroy(struct class *class, dev_t devt) { struct device *dev; - dev = class_find_device(class, NULL, &devt, __match_devt); + dev = class_find_device_by_devt(class, devt); if (dev) { put_device(dev); device_unregister(dev); @@ -3374,3 +3367,9 @@ int device_match_fwnode(struct device *dev, const void *fwnode) return dev_fwnode(dev) == fwnode; } EXPORT_SYMBOL_GPL(device_match_fwnode); + +int device_match_devt(struct device *dev, const void *pdevt) +{ + return dev->devt == *(dev_t *)pdevt; +} +EXPORT_SYMBOL_GPL(device_match_devt); diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 55922896d862..d5c1821b31c6 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -789,12 +789,6 @@ static int intel_th_populate(struct intel_th *th) return 0; } -static int match_devt(struct device *dev, const void *data) -{ - dev_t devt = (dev_t)(unsigned long)(void *)data; - return dev->devt == devt; -} - static int intel_th_output_open(struct inode *inode, struct file *file) { const struct file_operations *fops; @@ -802,9 +796,7 @@ static int intel_th_output_open(struct inode *inode, struct file *file) struct device *dev; int err; - dev = bus_find_device(&intel_th_bus, NULL, - (void *)(unsigned long)inode->i_rdev, - match_devt); + dev = bus_find_device_by_devt(&intel_th_bus, inode->i_rdev); if (!dev || !dev->driver) return -ENODEV; diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index f894d1f8a53e..7310b476323c 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -858,13 +858,6 @@ static ssize_t dev_state_show(struct device *device, } static DEVICE_ATTR_RO(dev_state); -static int match_devt(struct device *dev, const void *data) -{ - const dev_t *devt = data; - - return dev->devt == *devt; -} - /** * dev_set_devstate: set to new device state and notify sysfs file. * @@ -880,7 +873,7 @@ void mei_set_devstate(struct mei_device *dev, enum mei_dev_state state) dev->dev_state = state; - clsdev = class_find_device(mei_class, NULL, &dev->cdev.dev, match_devt); + clsdev = class_find_device_by_devt(mei_class, dev->cdev.dev); if (clsdev) { sysfs_notify(&clsdev->kobj, NULL, "dev_state"); put_device(clsdev); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 38a5a47b8c9c..150f6236c9bb 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -133,12 +133,6 @@ struct zcdn_device { static int zcdn_create(const char *name); static int zcdn_destroy(const char *name); -/* helper function, matches the devt value for find_zcdndev_by_devt() */ -static int __match_zcdn_devt(struct device *dev, const void *data) -{ - return dev->devt == *((dev_t *) data); -} - /* * Find zcdn device by name. * Returns reference to the zcdn device which needs to be released @@ -158,10 +152,7 @@ static inline struct zcdn_device *find_zcdndev_by_name(const char *name) */ static inline struct zcdn_device *find_zcdndev_by_devt(dev_t devt) { - struct device *dev = - class_find_device(zcrypt_class, NULL, - (void *) &devt, - __match_zcdn_devt); + struct device *dev = class_find_device_by_devt(zcrypt_class, devt); return dev ? to_zcdn_dev(dev) : NULL; } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 566728fbaf3c..802c1210558f 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2952,17 +2952,11 @@ void do_SAK(struct tty_struct *tty) EXPORT_SYMBOL(do_SAK); -static int dev_match_devt(struct device *dev, const void *data) -{ - const dev_t *devt = data; - return dev->devt == *devt; -} - /* Must put_device() after it's unused! */ static struct device *tty_get_device(struct tty_struct *tty) { dev_t devt = tty_devnum(tty); - return class_find_device(tty_class, NULL, &devt, dev_match_devt); + return class_find_device_by_devt(tty_class, devt); } diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index b265ab5405f9..60268aee93a8 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -942,17 +942,11 @@ error: return ret; } -static int match_devt(struct device *dev, const void *data) -{ - return dev->devt == (dev_t)(unsigned long)(void *)data; -} - static struct usb_device *usbdev_lookup_by_devt(dev_t devt) { struct device *dev; - dev = bus_find_device(&usb_bus_type, NULL, - (void *) (unsigned long) devt, match_devt); + dev = bus_find_device_by_devt(&usb_bus_type, devt); if (!dev) return NULL; return to_usb_device(dev); diff --git a/include/linux/device.h b/include/linux/device.h index 7133fc1c285d..93b2f55ef44e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -167,6 +167,7 @@ void subsys_dev_iter_exit(struct subsys_dev_iter *iter); int device_match_name(struct device *dev, const void *name); int device_match_of_node(struct device *dev, const void *np); int device_match_fwnode(struct device *dev, const void *fwnode); +int device_match_devt(struct device *dev, const void *pdevt); int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); @@ -211,6 +212,18 @@ bus_find_device_by_fwnode(struct bus_type *bus, const struct fwnode_handle *fwno return bus_find_device(bus, NULL, fwnode, device_match_fwnode); } +/** + * bus_find_device_by_devt : device iterator for locating a particular device + * matching the device type. + * @bus: bus type + * @devt: device type of the device to match. + */ +static inline struct device *bus_find_device_by_devt(struct bus_type *bus, + dev_t devt) +{ + return bus_find_device(bus, NULL, &devt, device_match_devt); +} + struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, struct device *hint); int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, @@ -417,6 +430,18 @@ driver_find_device_by_fwnode(struct device_driver *drv, return driver_find_device(drv, NULL, fwnode, device_match_fwnode); } +/** + * driver_find_device_by_devt- device iterator for locating a particular device + * by devt. + * @driver: the driver we're iterating + * @devt: devt pointer to match. + */ +static inline struct device *driver_find_device_by_devt(struct device_driver *drv, + dev_t devt) +{ + return driver_find_device(drv, NULL, &devt, device_match_devt); +} + void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); int driver_deferred_probe_check_state_continue(struct device *dev); @@ -583,6 +608,18 @@ class_find_device_by_fwnode(struct class *class, return class_find_device(class, NULL, fwnode, device_match_fwnode); } +/** + * class_find_device_by_devt : device iterator for locating a particular device + * matching the device type. + * @class: class type + * @devt: device type of the device to match. + */ +static inline struct device *class_find_device_by_devt(struct class *class, + dev_t devt) +{ + return class_find_device(class, NULL, &devt, device_match_devt); +} + struct class_attribute { struct attribute attr; ssize_t (*show)(struct class *class, struct class_attribute *attr, -- cgit v1.2.3-71-gd317 From 00500147cbd3fc51353d0d003eaa9d31c72c0d50 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 23 Jul 2019 23:18:36 +0100 Subject: drivers: Introduce device lookup variants by ACPI_COMPANION device Add a generic helper to match a device by the ACPI_COMPANION device and provide wrappers for the device lookup APIs. Cc: Len Brown Cc: linux-acpi@vger.kernel.org Cc: linux-spi@vger.kernel.org Cc: Mika Westerberg Cc: linux-i2c@vger.kernel.org Cc: "Rafael J. Wysocki" Signed-off-by: Suzuki K Poulose Acked-by: Mark Brown Acked-by: Wolfram Sang # I2C parts Link: https://lore.kernel.org/r/20190723221838.12024-6-suzuki.poulose@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 6 +++++ drivers/i2c/i2c-core-acpi.c | 11 ++------ drivers/spi/spi.c | 8 +----- include/linux/device.h | 65 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 74 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 3abc32b60c0a..57d71bc2c559 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3373,3 +3373,9 @@ int device_match_devt(struct device *dev, const void *pdevt) return dev->devt == *(dev_t *)pdevt; } EXPORT_SYMBOL_GPL(device_match_devt); + +int device_match_acpi_dev(struct device *dev, const void *adev) +{ + return ACPI_COMPANION(dev) == adev; +} +EXPORT_SYMBOL(device_match_acpi_dev); diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 4dbbc9a35f65..bc80aafb521f 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -354,17 +354,11 @@ static int i2c_acpi_find_match_adapter(struct device *dev, const void *data) return ACPI_HANDLE(dev) == (acpi_handle)data; } -static int i2c_acpi_find_match_device(struct device *dev, const void *data) -{ - return ACPI_COMPANION(dev) == data; -} struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) { - struct device *dev; + struct device *dev = bus_find_device_by_acpi_dev(&i2c_bus_type, handle); - dev = bus_find_device(&i2c_bus_type, NULL, handle, - i2c_acpi_find_match_adapter); return dev ? i2c_verify_adapter(dev) : NULL; } EXPORT_SYMBOL_GPL(i2c_acpi_find_adapter_by_handle); @@ -373,8 +367,7 @@ static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev) { struct device *dev; - dev = bus_find_device(&i2c_bus_type, NULL, adev, - i2c_acpi_find_match_device); + dev = bus_find_device_by_acpi_dev(&i2c_bus_type, adev); return dev ? i2c_verify_client(dev) : NULL; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index a591da87981a..c486a6f84c2c 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3741,11 +3741,6 @@ static int spi_acpi_controller_match(struct device *dev, const void *data) return ACPI_COMPANION(dev->parent) == data; } -static int spi_acpi_device_match(struct device *dev, const void *data) -{ - return ACPI_COMPANION(dev) == data; -} - static struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev) { struct device *dev; @@ -3765,8 +3760,7 @@ static struct spi_device *acpi_spi_find_device_by_adev(struct acpi_device *adev) { struct device *dev; - dev = bus_find_device(&spi_bus_type, NULL, adev, spi_acpi_device_match); - + dev = bus_find_device_by_acpi_dev(&spi_bus_type, adev); return dev ? to_spi_device(dev) : NULL; } diff --git a/include/linux/device.h b/include/linux/device.h index 93b2f55ef44e..7514ef3d3f1a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -168,6 +168,7 @@ int device_match_name(struct device *dev, const void *name); int device_match_of_node(struct device *dev, const void *np); int device_match_fwnode(struct device *dev, const void *fwnode); int device_match_devt(struct device *dev, const void *pdevt); +int device_match_acpi_dev(struct device *dev, const void *adev); int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); @@ -224,6 +225,28 @@ static inline struct device *bus_find_device_by_devt(struct bus_type *bus, return bus_find_device(bus, NULL, &devt, device_match_devt); } +#ifdef CONFIG_ACPI +struct acpi_device; + +/** + * bus_find_device_by_acpi_dev : device iterator for locating a particular device + * matching the ACPI COMPANION device. + * @bus: bus type + * @adev: ACPI COMPANION device to match. + */ +static inline struct device * +bus_find_device_by_acpi_dev(struct bus_type *bus, const struct acpi_device *adev) +{ + return bus_find_device(bus, NULL, adev, device_match_acpi_dev); +} +#else +static inline struct device * +bus_find_device_by_acpi_dev(struct bus_type *bus, const void *adev) +{ + return NULL; +} +#endif + struct device *subsys_find_device_by_id(struct bus_type *bus, unsigned int id, struct device *hint); int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, @@ -442,6 +465,27 @@ static inline struct device *driver_find_device_by_devt(struct device_driver *dr return driver_find_device(drv, NULL, &devt, device_match_devt); } +#ifdef CONFIG_ACPI +/** + * driver_find_device_by_acpi_dev : device iterator for locating a particular + * device matching the ACPI_COMPANION device. + * @driver: the driver we're iterating + * @adev: ACPI_COMPANION device to match. + */ +static inline struct device * +driver_find_device_by_acpi_dev(struct device_driver *drv, + const struct acpi_device *adev) +{ + return driver_find_device(drv, NULL, adev, device_match_acpi_dev); +} +#else +static inline struct device * +driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev) +{ + return NULL; +} +#endif + void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); int driver_deferred_probe_check_state_continue(struct device *dev); @@ -620,6 +664,27 @@ static inline struct device *class_find_device_by_devt(struct class *class, return class_find_device(class, NULL, &devt, device_match_devt); } +#ifdef CONFIG_ACPI +struct acpi_device; +/** + * class_find_device_by_acpi_dev : device iterator for locating a particular + * device matching the ACPI_COMPANION device. + * @class: class type + * @adev: ACPI_COMPANION device to match. + */ +static inline struct device * +class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) +{ + return class_find_device(class, NULL, adev, device_match_acpi_dev); +} +#else +static inline struct device * +class_find_device_by_acpi_dev(struct class *class, const void *adev) +{ + return NULL; +} +#endif + struct class_attribute { struct attribute attr; ssize_t (*show)(struct class *class, struct class_attribute *attr, -- cgit v1.2.3-71-gd317 From 6bf85ba9e55f659ddc0747bf1bb504ec6d15f525 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 23 Jul 2019 23:18:37 +0100 Subject: drivers: Add generic helper to match any device Add a generic helper to match any/all devices. Using this introduce new wrappers {bus/driver/class}_find_next_device(). Cc: Elie Morisse Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Nehal Shah Cc: "Rafael J. Wysocki" Cc: Shyam Sundar S K Signed-off-by: Suzuki K Poulose Acked-by: Bjorn Helgaas # PCI Link: https://lore.kernel.org/r/20190723221838.12024-7-suzuki.poulose@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 6 ++++++ drivers/i2c/busses/i2c-amd-mp2-pci.c | 8 +------- drivers/pci/probe.c | 7 +------ drivers/s390/cio/ccwgroup.c | 8 +------- drivers/scsi/scsi_proc.c | 9 ++------- include/linux/device.h | 17 +++++++++++++++++ 6 files changed, 28 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 57d71bc2c559..e22e29b3dc97 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3379,3 +3379,9 @@ int device_match_acpi_dev(struct device *dev, const void *adev) return ACPI_COMPANION(dev) == adev; } EXPORT_SYMBOL(device_match_acpi_dev); + +int device_match_any(struct device *dev, const void *unused) +{ + return 1; +} +EXPORT_SYMBOL_GPL(device_match_any); diff --git a/drivers/i2c/busses/i2c-amd-mp2-pci.c b/drivers/i2c/busses/i2c-amd-mp2-pci.c index c7fe3b44a860..5e4800d72e00 100644 --- a/drivers/i2c/busses/i2c-amd-mp2-pci.c +++ b/drivers/i2c/busses/i2c-amd-mp2-pci.c @@ -457,18 +457,12 @@ static struct pci_driver amd_mp2_pci_driver = { }; module_pci_driver(amd_mp2_pci_driver); -static int amd_mp2_device_match(struct device *dev, const void *data) -{ - return 1; -} - struct amd_mp2_dev *amd_mp2_find_device(void) { struct device *dev; struct pci_dev *pci_dev; - dev = driver_find_device(&amd_mp2_pci_driver.driver, NULL, NULL, - amd_mp2_device_match); + dev = driver_find_next_device(&amd_mp2_pci_driver.driver, NULL); if (!dev) return NULL; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index a3c7338fad86..dbeeb385fb9f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -64,11 +64,6 @@ static struct resource *get_pci_domain_busn_res(int domain_nr) return &r->res; } -static int find_anything(struct device *dev, const void *data) -{ - return 1; -} - /* * Some device drivers need know if PCI is initiated. * Basically, we think PCI is not initiated when there @@ -79,7 +74,7 @@ int no_pci_devices(void) struct device *dev; int no_devices; - dev = bus_find_device(&pci_bus_type, NULL, NULL, find_anything); + dev = bus_find_next_device(&pci_bus_type, NULL); no_devices = (dev == NULL); put_device(dev); return no_devices; diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index d843e362c167..0005ec9285aa 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -581,11 +581,6 @@ int ccwgroup_driver_register(struct ccwgroup_driver *cdriver) } EXPORT_SYMBOL(ccwgroup_driver_register); -static int __ccwgroup_match_all(struct device *dev, const void *data) -{ - return 1; -} - /** * ccwgroup_driver_unregister() - deregister a ccw group driver * @cdriver: driver to be deregistered @@ -597,8 +592,7 @@ void ccwgroup_driver_unregister(struct ccwgroup_driver *cdriver) struct device *dev; /* We don't want ccwgroup devices to live longer than their driver. */ - while ((dev = driver_find_device(&cdriver->driver, NULL, NULL, - __ccwgroup_match_all))) { + while ((dev = driver_find_next_device(&cdriver->driver, NULL))) { struct ccwgroup_device *gdev = to_ccwgroupdev(dev); ccwgroup_ungroup(gdev); diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c index c074631086a4..5b313226f11c 100644 --- a/drivers/scsi/scsi_proc.c +++ b/drivers/scsi/scsi_proc.c @@ -372,15 +372,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, return err; } -static int always_match(struct device *dev, const void *data) -{ - return 1; -} - static inline struct device *next_scsi_device(struct device *start) { - struct device *next = bus_find_device(&scsi_bus_type, start, NULL, - always_match); + struct device *next = bus_find_next_device(&scsi_bus_type, start); + put_device(start); return next; } diff --git a/include/linux/device.h b/include/linux/device.h index 7514ef3d3f1a..8ae3f4b47293 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -169,6 +169,7 @@ int device_match_of_node(struct device *dev, const void *np); int device_match_fwnode(struct device *dev, const void *fwnode); int device_match_devt(struct device *dev, const void *pdevt); int device_match_acpi_dev(struct device *dev, const void *adev); +int device_match_any(struct device *dev, const void *unused); int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); @@ -225,6 +226,16 @@ static inline struct device *bus_find_device_by_devt(struct bus_type *bus, return bus_find_device(bus, NULL, &devt, device_match_devt); } +/** + * bus_find_next_device - Find the next device after a given device in a + * given bus. + */ +static inline struct device * +bus_find_next_device(struct bus_type *bus,struct device *cur) +{ + return bus_find_device(bus, cur, NULL, device_match_any); +} + #ifdef CONFIG_ACPI struct acpi_device; @@ -465,6 +476,12 @@ static inline struct device *driver_find_device_by_devt(struct device_driver *dr return driver_find_device(drv, NULL, &devt, device_match_devt); } +static inline struct device *driver_find_next_device(struct device_driver *drv, + struct device *start) +{ + return driver_find_device(drv, start, NULL, device_match_any); +} + #ifdef CONFIG_ACPI /** * driver_find_device_by_acpi_dev : device iterator for locating a particular -- cgit v1.2.3-71-gd317 From 36f3313d6bff91ab2a9e47698c27d15363640a4e Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 23 Jul 2019 23:18:38 +0100 Subject: platform: Add platform_find_device_by_driver() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Provide a helper to lookup platform devices by matching device driver in order to avoid drivers trying to use platform bus internals. Cc: Eric Anholt Cc: Greg Kroah-Hartman Cc: "Heiko Stübner" Cc: Inki Dae Cc: "Rafael J. Wysocki" Cc: Sandy Huang Cc: Seung-Woo Kim Tested-by: Heiko Stuebner Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20190723221838.12024-8-suzuki.poulose@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/platform.c | 14 ++++++++++++++ drivers/gpu/drm/exynos/exynos_drm_drv.c | 9 +++------ drivers/gpu/drm/mcde/mcde_drv.c | 3 +-- drivers/gpu/drm/rockchip/rockchip_drm_drv.c | 3 +-- drivers/gpu/drm/vc4/vc4_drv.c | 3 +-- include/linux/platform_device.h | 3 +++ 6 files changed, 23 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 506a0175a5a7..a174ce5ea17c 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1197,6 +1197,20 @@ struct bus_type platform_bus_type = { }; EXPORT_SYMBOL_GPL(platform_bus_type); +/** + * platform_find_device_by_driver - Find a platform device with a given + * driver. + * @start: The device to start the search from. + * @drv: The device driver to look for. + */ +struct device *platform_find_device_by_driver(struct device *start, + const struct device_driver *drv) +{ + return bus_find_device(&platform_bus_type, start, drv, + (void *)platform_match); +} +EXPORT_SYMBOL_GPL(platform_find_device_by_driver); + int __init platform_bus_init(void) { int error; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 58baf49d9926..badab94be2d6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -242,9 +242,7 @@ static struct component_match *exynos_drm_match_add(struct device *dev) if (!info->driver || !(info->flags & DRM_COMPONENT_DRIVER)) continue; - while ((d = bus_find_device(&platform_bus_type, p, - &info->driver->driver, - (void *)platform_bus_type.match))) { + while ((d = platform_find_device_by_driver(p, &info->driver->driver))) { put_device(p); if (!(info->flags & DRM_FIMC_DEVICE) || @@ -412,9 +410,8 @@ static void exynos_drm_unregister_devices(void) if (!info->driver || !(info->flags & DRM_VIRTUAL_DEVICE)) continue; - while ((dev = bus_find_device(&platform_bus_type, NULL, - &info->driver->driver, - (void *)platform_bus_type.match))) { + while ((dev = platform_find_device_by_driver(NULL, + &info->driver->driver))) { put_device(dev); platform_device_unregister(to_platform_device(dev)); } diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index baf63fb6850a..c07abf9e201c 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -477,8 +477,7 @@ static int mcde_probe(struct platform_device *pdev) struct device_driver *drv = &mcde_component_drivers[i]->driver; struct device *p = NULL, *d; - while ((d = bus_find_device(&platform_bus_type, p, drv, - (void *)platform_bus_type.match))) { + while ((d = platform_find_device_by_driver(p, drv))) { put_device(p); component_match_add(dev, &match, mcde_compare_dev, d); p = d; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 53d2c5bd61dc..38dc26376961 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -330,8 +330,7 @@ static struct component_match *rockchip_drm_match_add(struct device *dev) struct device *p = NULL, *d; do { - d = bus_find_device(&platform_bus_type, p, &drv->driver, - (void *)platform_bus_type.match); + d = platform_find_device_by_driver(p, &drv->driver); put_device(p); p = d; diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index bf11930e40e1..1551c8253bec 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -237,8 +237,7 @@ static void vc4_match_add_drivers(struct device *dev, struct device_driver *drv = &drivers[i]->driver; struct device *p = NULL, *d; - while ((d = bus_find_device(&platform_bus_type, p, drv, - (void *)platform_bus_type.match))) { + while ((d = platform_find_device_by_driver(p, drv))) { put_device(p); component_match_add(dev, match, compare_dev, d); p = d; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 9bc36b589827..37e15a935a42 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -51,6 +51,9 @@ extern struct device platform_bus; extern void arch_setup_pdev_archdata(struct platform_device *); extern struct resource *platform_get_resource(struct platform_device *, unsigned int, unsigned int); +extern struct device * +platform_find_device_by_driver(struct device *start, + const struct device_driver *drv); extern void __iomem * devm_platform_ioremap_resource(struct platform_device *pdev, unsigned int index); -- cgit v1.2.3-71-gd317 From 2889ffcfc2522d6d25e5bda704275064062bbb21 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Mon, 29 Jul 2019 16:27:37 +0800 Subject: platform/x86: asus-wmi: cleanup AGFN fan handling The asus-wmi driver currently uses the "AGFN" interface and the FAN_CTRL device for fan control. According to the spec, this interface is very dated and marked as pending removal from products currently in development. Clean up the way that the AGFN fan is detected and handled, also preparing the driver for the introduction of an alternate fan control method needed to support recent Asus products. Not anticipating further development of this interface, simplify the code by dropping any notion of being able to control multiple AGFN fans (this was already limited to just a single fan through only exposing a single fan in sysfs). Check for the presence of AGFN fans at probe time, simplifying the code flow in asus_hwmon_sysfs_is_visible(). Signed-off-by: Daniel Drake Signed-off-by: Andy Shevchenko --- drivers/platform/x86/asus-wmi.c | 238 +++++++++++++---------------- include/linux/platform_data/x86/asus-wmi.h | 4 +- 2 files changed, 109 insertions(+), 133 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 0c6a810fcb72..fc2939ac1cfe 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -65,6 +65,8 @@ MODULE_LICENSE("GPL"); #define ASUS_FAN_MFUN 0x13 #define ASUS_FAN_SFUN_READ 0x06 #define ASUS_FAN_SFUN_WRITE 0x07 + +/* Based on standard hwmon pwmX_enable values */ #define ASUS_FAN_CTRL_MANUAL 1 #define ASUS_FAN_CTRL_AUTO 2 @@ -120,7 +122,7 @@ struct agfn_args { } __packed; /* struct used for calling fan read and write methods */ -struct fan_args { +struct agfn_fan_args { struct agfn_args agfn; /* common fields */ u8 fan; /* fan number: 0: set auto mode 1: 1st fan */ u32 speed; /* read: RPM/100 - write: 0-255 */ @@ -148,6 +150,11 @@ struct asus_rfkill { u32 dev_id; }; +enum fan_type { + FAN_TYPE_NONE = 0, + FAN_TYPE_AGFN, /* deprecated on newer platforms */ +}; + struct asus_wmi { int dsts_id; int spec; @@ -178,9 +185,9 @@ struct asus_wmi { struct asus_rfkill gps; struct asus_rfkill uwb; - bool asus_hwmon_fan_manual_mode; - int asus_hwmon_num_fans; - int asus_hwmon_pwm; + enum fan_type fan_type; + int fan_pwm_mode; + int agfn_pwm; bool fan_boost_mode_available; u8 fan_boost_mode_mask; @@ -1125,10 +1132,10 @@ static void asus_wmi_set_als(void) /* Hwmon device ***************************************************************/ -static int asus_hwmon_agfn_fan_speed_read(struct asus_wmi *asus, int fan, +static int asus_agfn_fan_speed_read(struct asus_wmi *asus, int fan, int *speed) { - struct fan_args args = { + struct agfn_fan_args args = { .agfn.len = sizeof(args), .agfn.mfun = ASUS_FAN_MFUN, .agfn.sfun = ASUS_FAN_SFUN_READ, @@ -1152,10 +1159,10 @@ static int asus_hwmon_agfn_fan_speed_read(struct asus_wmi *asus, int fan, return 0; } -static int asus_hwmon_agfn_fan_speed_write(struct asus_wmi *asus, int fan, +static int asus_agfn_fan_speed_write(struct asus_wmi *asus, int fan, int *speed) { - struct fan_args args = { + struct agfn_fan_args args = { .agfn.len = sizeof(args), .agfn.mfun = ASUS_FAN_MFUN, .agfn.sfun = ASUS_FAN_SFUN_WRITE, @@ -1175,7 +1182,7 @@ static int asus_hwmon_agfn_fan_speed_write(struct asus_wmi *asus, int fan, return -ENXIO; if (speed && fan == 1) - asus->asus_hwmon_pwm = *speed; + asus->agfn_pwm = *speed; return 0; } @@ -1184,87 +1191,75 @@ static int asus_hwmon_agfn_fan_speed_write(struct asus_wmi *asus, int fan, * Check if we can read the speed of one fan. If true we assume we can also * control it. */ -static int asus_hwmon_get_fan_number(struct asus_wmi *asus, int *num_fans) +static bool asus_wmi_has_agfn_fan(struct asus_wmi *asus) { int status; - int speed = 0; + int speed; + u32 value; - *num_fans = 0; + status = asus_agfn_fan_speed_read(asus, 1, &speed); + if (status != 0) + return false; - status = asus_hwmon_agfn_fan_speed_read(asus, 1, &speed); - if (!status) - *num_fans = 1; + status = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_FAN_CTRL, &value); + if (status != 0) + return false; - return 0; + /* + * We need to find a better way, probably using sfun, + * bits or spec ... + * Currently we disable it if: + * - ASUS_WMI_UNSUPPORTED_METHOD is returned + * - reverved bits are non-zero + * - sfun and presence bit are not set + */ + return !(value == ASUS_WMI_UNSUPPORTED_METHOD || value & 0xFFF80000 + || (!asus->sfun && !(value & ASUS_WMI_DSTS_PRESENCE_BIT))); } -static int asus_hwmon_fan_set_auto(struct asus_wmi *asus) +static int asus_fan_set_auto(struct asus_wmi *asus) { int status; - status = asus_hwmon_agfn_fan_speed_write(asus, 0, NULL); + status = asus_agfn_fan_speed_write(asus, 0, NULL); if (status) return -ENXIO; - asus->asus_hwmon_fan_manual_mode = false; - return 0; } -static int asus_hwmon_fan_rpm_show(struct device *dev, int fan) +static ssize_t pwm1_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct asus_wmi *asus = dev_get_drvdata(dev); - int value; - int ret; - - /* no speed readable on manual mode */ - if (asus->asus_hwmon_fan_manual_mode) - return -ENXIO; - - ret = asus_hwmon_agfn_fan_speed_read(asus, fan+1, &value); - if (ret) { - pr_warn("reading fan speed failed: %d\n", ret); - return -ENXIO; - } - - return value; -} - -static void asus_hwmon_pwm_show(struct asus_wmi *asus, int fan, int *value) -{ int err; + int value; - if (asus->asus_hwmon_pwm >= 0) { - *value = asus->asus_hwmon_pwm; - return; - } + /* If we already set a value then just return it */ + if (asus->agfn_pwm >= 0) + return sprintf(buf, "%d\n", asus->agfn_pwm); - err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_FAN_CTRL, value); + /* + * If we haven't set already set a value through the AGFN interface, + * we read a current value through the (now-deprecated) FAN_CTRL device. + */ + err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_FAN_CTRL, &value); if (err < 0) - return; + return err; - *value &= 0xFF; - - if (*value == 1) /* Low Speed */ - *value = 85; - else if (*value == 2) - *value = 170; - else if (*value == 3) - *value = 255; - else if (*value) { - pr_err("Unknown fan speed %#x\n", *value); - *value = -1; + value &= 0xFF; + + if (value == 1) /* Low Speed */ + value = 85; + else if (value == 2) + value = 170; + else if (value == 3) + value = 255; + else if (value) { + pr_err("Unknown fan speed %#x\n", value); + value = -1; } -} - -static ssize_t pwm1_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct asus_wmi *asus = dev_get_drvdata(dev); - int value; - - asus_hwmon_pwm_show(asus, 0, &value); return sprintf(buf, "%d\n", value); } @@ -1284,11 +1279,11 @@ static ssize_t pwm1_store(struct device *dev, value = clamp(value, 0, 255); - state = asus_hwmon_agfn_fan_speed_write(asus, 1, &value); + state = asus_agfn_fan_speed_write(asus, 1, &value); if (state) pr_warn("Setting fan speed failed: %d\n", state); else - asus->asus_hwmon_fan_manual_mode = true; + asus->fan_pwm_mode = ASUS_FAN_CTRL_MANUAL; return count; } @@ -1297,10 +1292,21 @@ static ssize_t fan1_input_show(struct device *dev, struct device_attribute *attr, char *buf) { - int value = asus_hwmon_fan_rpm_show(dev, 0); + struct asus_wmi *asus = dev_get_drvdata(dev); + int value; + int ret; - return sprintf(buf, "%d\n", value < 0 ? -1 : value*100); + /* no speed readable on manual mode */ + if (asus->fan_pwm_mode == ASUS_FAN_CTRL_MANUAL) + return -ENXIO; + + ret = asus_agfn_fan_speed_read(asus, 1, &value); + if (ret) { + pr_warn("reading fan speed failed: %d\n", ret); + return -ENXIO; + } + return sprintf(buf, "%d\n", value < 0 ? -1 : value*100); } static ssize_t pwm1_enable_show(struct device *dev, @@ -1309,10 +1315,7 @@ static ssize_t pwm1_enable_show(struct device *dev, { struct asus_wmi *asus = dev_get_drvdata(dev); - if (asus->asus_hwmon_fan_manual_mode) - return sprintf(buf, "%d\n", ASUS_FAN_CTRL_MANUAL); - - return sprintf(buf, "%d\n", ASUS_FAN_CTRL_AUTO); + return sprintf(buf, "%d\n", asus->fan_pwm_mode); } static ssize_t pwm1_enable_store(struct device *dev, @@ -1329,14 +1332,21 @@ static ssize_t pwm1_enable_store(struct device *dev, if (ret) return ret; - if (state == ASUS_FAN_CTRL_MANUAL) - asus->asus_hwmon_fan_manual_mode = true; - else - status = asus_hwmon_fan_set_auto(asus); + switch (state) { + case ASUS_FAN_CTRL_MANUAL: + break; - if (status) - return status; + case ASUS_FAN_CTRL_AUTO: + status = asus_fan_set_auto(asus); + if (status) + return status; + break; + default: + return -EINVAL; + } + + asus->fan_pwm_mode = state; return count; } @@ -1389,59 +1399,31 @@ static umode_t asus_hwmon_sysfs_is_visible(struct kobject *kobj, { struct device *dev = container_of(kobj, struct device, kobj); struct asus_wmi *asus = dev_get_drvdata(dev->parent); - int dev_id = -1; - int fan_attr = -1; u32 value = ASUS_WMI_UNSUPPORTED_METHOD; - bool ok = true; - - if (attr == &dev_attr_pwm1.attr) - dev_id = ASUS_WMI_DEVID_FAN_CTRL; - else if (attr == &dev_attr_temp1_input.attr) - dev_id = ASUS_WMI_DEVID_THERMAL_CTRL; - if (attr == &dev_attr_fan1_input.attr || attr == &dev_attr_fan1_label.attr || attr == &dev_attr_pwm1.attr || attr == &dev_attr_pwm1_enable.attr) { - fan_attr = 1; - } - - if (dev_id != -1) { - int err = asus_wmi_get_devstate(asus, dev_id, &value); + if (asus->fan_type == FAN_TYPE_NONE) + return 0; + } else if (attr == &dev_attr_temp1_input.attr) { + int err = asus_wmi_get_devstate(asus, + ASUS_WMI_DEVID_THERMAL_CTRL, + &value); - if (err < 0 && fan_attr == -1) + if (err < 0) return 0; /* can't return negative here */ - } - if (dev_id == ASUS_WMI_DEVID_FAN_CTRL) { - /* - * We need to find a better way, probably using sfun, - * bits or spec ... - * Currently we disable it if: - * - ASUS_WMI_UNSUPPORTED_METHOD is returned - * - reverved bits are non-zero - * - sfun and presence bit are not set - */ - if (value == ASUS_WMI_UNSUPPORTED_METHOD || value & 0xFFF80000 - || (!asus->sfun && !(value & ASUS_WMI_DSTS_PRESENCE_BIT))) - ok = false; - else - ok = fan_attr <= asus->asus_hwmon_num_fans; - } else if (dev_id == ASUS_WMI_DEVID_THERMAL_CTRL) { /* * If the temperature value in deci-Kelvin is near the absolute * zero temperature, something is clearly wrong */ if (value == 0 || value == 1) - ok = false; - } else if (fan_attr <= asus->asus_hwmon_num_fans && fan_attr != -1) { - ok = true; - } else { - ok = false; + return 0; } - return ok ? attr->mode : 0; + return attr->mode; } static const struct attribute_group hwmon_attribute_group = { @@ -1467,21 +1449,16 @@ static int asus_wmi_hwmon_init(struct asus_wmi *asus) static int asus_wmi_fan_init(struct asus_wmi *asus) { - int status; - - asus->asus_hwmon_pwm = -1; - asus->asus_hwmon_num_fans = -1; - asus->asus_hwmon_fan_manual_mode = false; + asus->fan_type = FAN_TYPE_NONE; + asus->agfn_pwm = -1; - status = asus_hwmon_get_fan_number(asus, &asus->asus_hwmon_num_fans); - if (status) { - asus->asus_hwmon_num_fans = 0; - pr_warn("Could not determine number of fans: %d\n", status); - return -ENXIO; + if (asus_wmi_has_agfn_fan(asus)) { + asus->fan_type = FAN_TYPE_AGFN; + asus_fan_set_auto(asus); + asus->fan_pwm_mode = ASUS_FAN_CTRL_AUTO; } - pr_info("Number of fans: %d\n", asus->asus_hwmon_num_fans); - return 0; + return asus->fan_type != FAN_TYPE_NONE; } /* Fan mode *******************************************************************/ @@ -2333,7 +2310,6 @@ static int asus_wmi_add(struct platform_device *pdev) goto fail_input; err = asus_wmi_fan_init(asus); /* probably no problems on error */ - asus_hwmon_fan_set_auto(asus); err = asus_wmi_hwmon_init(asus); if (err) @@ -2425,7 +2401,7 @@ static int asus_wmi_remove(struct platform_device *device) asus_wmi_rfkill_exit(asus); asus_wmi_debugfs_exit(asus); asus_wmi_sysfs_exit(asus->platform_device); - asus_hwmon_fan_set_auto(asus); + asus_fan_set_auto(asus); kfree(asus); return 0; diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 4802cd2c7309..5ae9c062a1f6 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -12,7 +12,7 @@ #define ASUS_WMI_METHODID_GPID 0x44495047 /* Get Panel ID?? (Resol) */ #define ASUS_WMI_METHODID_QMOD 0x444F4D51 /* Quiet MODe */ #define ASUS_WMI_METHODID_SPLV 0x4C425053 /* Set Panel Light Value */ -#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* FaN? */ +#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* Atk Generic FuNction */ #define ASUS_WMI_METHODID_SFUN 0x4E554653 /* FUNCtionalities */ #define ASUS_WMI_METHODID_SDSP 0x50534453 /* Set DiSPlay output */ #define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ @@ -72,7 +72,7 @@ /* Fan, Thermal */ #define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 -#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 +#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 /* deprecated */ /* Power */ #define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 -- cgit v1.2.3-71-gd317 From e3168b874321d04c160c9eb937919eb926ae232f Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Mon, 29 Jul 2019 16:27:39 +0800 Subject: platform/x86: asus-wmi: fix CPU fan control on recent products Previously, asus-wmi was using the AGFN interface and FAN_CTRL device for CPU fan control. However, this code has been found to be not fully working on some recent products, and having checked the spec, these interfaces are marked as being removed from future products currently in development. The replacement appears to be the CPU_FAN device, added in spec version 8.3 (March 2014) and present on many modern Asus laptops. Add support for this device, and use it whenever it is detected. The older approach based on AGFN and FAN_CTRL is used as a fallback on products that do not have such device. Other than switching between automatic and full speed, there is no fan speed control through this new interface. Signed-off-by: Daniel Drake Signed-off-by: Andy Shevchenko --- drivers/platform/x86/asus-wmi.c | 125 +++++++++++++++++++++++------ include/linux/platform_data/x86/asus-wmi.h | 1 + 2 files changed, 101 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 25f1e256c442..34dfbed65332 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -67,6 +67,7 @@ MODULE_LICENSE("GPL"); #define ASUS_FAN_SFUN_WRITE 0x07 /* Based on standard hwmon pwmX_enable values */ +#define ASUS_FAN_CTRL_FULLSPEED 0 #define ASUS_FAN_CTRL_MANUAL 1 #define ASUS_FAN_CTRL_AUTO 2 @@ -153,6 +154,7 @@ struct asus_rfkill { enum fan_type { FAN_TYPE_NONE = 0, FAN_TYPE_AGFN, /* deprecated on newer platforms */ + FAN_TYPE_SPEC83, /* starting in Spec 8.3, use CPU_FAN_CTRL */ }; struct asus_wmi { @@ -1211,10 +1213,29 @@ static bool asus_wmi_has_agfn_fan(struct asus_wmi *asus) static int asus_fan_set_auto(struct asus_wmi *asus) { int status; + u32 retval; - status = asus_agfn_fan_speed_write(asus, 0, NULL); - if (status) + switch (asus->fan_type) { + case FAN_TYPE_SPEC83: + status = asus_wmi_set_devstate(ASUS_WMI_DEVID_CPU_FAN_CTRL, + 0, &retval); + if (status) + return status; + + if (retval != 1) + return -EIO; + break; + + case FAN_TYPE_AGFN: + status = asus_agfn_fan_speed_write(asus, 0, NULL); + if (status) + return -ENXIO; + break; + + default: return -ENXIO; + } + return 0; } @@ -1287,13 +1308,29 @@ static ssize_t fan1_input_show(struct device *dev, int value; int ret; - /* no speed readable on manual mode */ - if (asus->fan_pwm_mode == ASUS_FAN_CTRL_MANUAL) - return -ENXIO; + switch (asus->fan_type) { + case FAN_TYPE_SPEC83: + ret = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL, + &value); + if (ret < 0) + return ret; - ret = asus_agfn_fan_speed_read(asus, 1, &value); - if (ret) { - pr_warn("reading fan speed failed: %d\n", ret); + value &= 0xffff; + break; + + case FAN_TYPE_AGFN: + /* no speed readable on manual mode */ + if (asus->fan_pwm_mode == ASUS_FAN_CTRL_MANUAL) + return -ENXIO; + + ret = asus_agfn_fan_speed_read(asus, 1, &value); + if (ret) { + pr_warn("reading fan speed failed: %d\n", ret); + return -ENXIO; + } + break; + + default: return -ENXIO; } @@ -1306,6 +1343,15 @@ static ssize_t pwm1_enable_show(struct device *dev, { struct asus_wmi *asus = dev_get_drvdata(dev); + /* + * Just read back the cached pwm mode. + * + * For the CPU_FAN device, the spec indicates that we should be + * able to read the device status and consult bit 19 to see if we + * are in Full On or Automatic mode. However, this does not work + * in practice on X532FL at least (the bit is always 0) and there's + * also nothing in the DSDT to indicate that this behaviour exists. + */ return sprintf(buf, "%d\n", asus->fan_pwm_mode); } @@ -1316,25 +1362,48 @@ static ssize_t pwm1_enable_store(struct device *dev, struct asus_wmi *asus = dev_get_drvdata(dev); int status = 0; int state; + int value; int ret; + u32 retval; ret = kstrtouint(buf, 10, &state); if (ret) return ret; - switch (state) { - case ASUS_FAN_CTRL_MANUAL: - break; + if (asus->fan_type == FAN_TYPE_SPEC83) { + switch (state) { /* standard documented hwmon values */ + case ASUS_FAN_CTRL_FULLSPEED: + value = 1; + break; + case ASUS_FAN_CTRL_AUTO: + value = 0; + break; + default: + return -EINVAL; + } - case ASUS_FAN_CTRL_AUTO: - status = asus_fan_set_auto(asus); - if (status) - return status; - break; + ret = asus_wmi_set_devstate(ASUS_WMI_DEVID_CPU_FAN_CTRL, + value, &retval); + if (ret) + return ret; - default: - return -EINVAL; + if (retval != 1) + return -EIO; + } else if (asus->fan_type == FAN_TYPE_AGFN) { + switch (state) { + case ASUS_FAN_CTRL_MANUAL: + break; + + case ASUS_FAN_CTRL_AUTO: + status = asus_fan_set_auto(asus); + if (status) + return status; + break; + + default: + return -EINVAL; + } } asus->fan_pwm_mode = state; @@ -1392,9 +1461,11 @@ static umode_t asus_hwmon_sysfs_is_visible(struct kobject *kobj, struct asus_wmi *asus = dev_get_drvdata(dev->parent); u32 value = ASUS_WMI_UNSUPPORTED_METHOD; - if (attr == &dev_attr_fan1_input.attr + if (attr == &dev_attr_pwm1.attr) { + if (asus->fan_type != FAN_TYPE_AGFN) + return 0; + } else if (attr == &dev_attr_fan1_input.attr || attr == &dev_attr_fan1_label.attr - || attr == &dev_attr_pwm1.attr || attr == &dev_attr_pwm1_enable.attr) { if (asus->fan_type == FAN_TYPE_NONE) return 0; @@ -1443,13 +1514,17 @@ static int asus_wmi_fan_init(struct asus_wmi *asus) asus->fan_type = FAN_TYPE_NONE; asus->agfn_pwm = -1; - if (asus_wmi_has_agfn_fan(asus)) { + if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL)) + asus->fan_type = FAN_TYPE_SPEC83; + else if (asus_wmi_has_agfn_fan(asus)) asus->fan_type = FAN_TYPE_AGFN; - asus_fan_set_auto(asus); - asus->fan_pwm_mode = ASUS_FAN_CTRL_AUTO; - } - return asus->fan_type != FAN_TYPE_NONE; + if (asus->fan_type == FAN_TYPE_NONE) + return -ENODEV; + + asus_fan_set_auto(asus); + asus->fan_pwm_mode = ASUS_FAN_CTRL_AUTO; + return 0; } /* Fan mode *******************************************************************/ diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 5ae9c062a1f6..409e16064f4b 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -73,6 +73,7 @@ /* Fan, Thermal */ #define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 #define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 /* deprecated */ +#define ASUS_WMI_DEVID_CPU_FAN_CTRL 0x00110013 /* Power */ #define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 -- cgit v1.2.3-71-gd317 From c776dd50196a07a0ef943fcb74e8c86f9a5a20a8 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:38 -0600 Subject: PCI: Make PCI_PM_* delay times private These delay time definitions: #define PCI_PM_D2_DELAY 200 #define PCI_PM_D3_WAIT 10 #define PCI_PM_D3COLD_WAIT 100 #define PCI_PM_BUS_WAIT 50 are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-2-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 5 +++++ include/linux/pci.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 1be03a97cb92..708413632429 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -39,6 +39,11 @@ int pci_probe_reset_function(struct pci_dev *dev); int pci_bridge_secondary_bus_reset(struct pci_dev *dev); int pci_bus_error_reset(struct pci_dev *dev); +#define PCI_PM_D2_DELAY 200 +#define PCI_PM_D3_WAIT 10 +#define PCI_PM_D3COLD_WAIT 100 +#define PCI_PM_BUS_WAIT 50 + /** * struct pci_platform_pm_ops - Firmware PM callbacks * diff --git a/include/linux/pci.h b/include/linux/pci.h index 61b64fa1b0b1..9c2c6e161cfd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -145,11 +145,6 @@ static inline const char *pci_power_name(pci_power_t state) return pci_power_names[1 + (__force int) state]; } -#define PCI_PM_D2_DELAY 200 -#define PCI_PM_D3_WAIT 10 -#define PCI_PM_D3COLD_WAIT 100 -#define PCI_PM_BUS_WAIT 50 - /** * typedef pci_channel_state_t * -- cgit v1.2.3-71-gd317 From 669696ebbccc40e8096a2ee9809c028fc1538001 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:39 -0600 Subject: PCI: Make pci_check_pme_status(), pci_pme_wakeup_bus() private These interfaces: bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-3-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 2 ++ include/linux/pci.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 708413632429..ad1fe54ab8ee 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -89,6 +89,8 @@ void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); void pcie_clear_root_pme_status(struct pci_dev *dev); +bool pci_check_pme_status(struct pci_dev *dev); +void pci_pme_wakeup_bus(struct pci_bus *bus); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); void pci_pme_restore(struct pci_dev *dev); bool pci_dev_need_resume(struct pci_dev *dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index 9c2c6e161cfd..b13fb829171e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1236,8 +1236,6 @@ int pci_wake_from_d3(struct pci_dev *dev, bool enable); int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); bool pci_dev_run_wake(struct pci_dev *dev); -bool pci_check_pme_status(struct pci_dev *dev); -void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); -- cgit v1.2.3-71-gd317 From 975e1ac173058b8710e5979e97fc1397233301f3 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:40 -0600 Subject: PCI: Make pci_get_host_bridge_device(), pci_put_host_bridge_device() private These interfaces: struct device *pci_get_host_bridge_device(struct pci_dev *dev); void pci_put_host_bridge_device(struct device *dev); are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-4-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 3 +++ include/linux/pci.h | 3 --- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index ad1fe54ab8ee..b06c750e08d7 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -243,6 +243,9 @@ enum pci_bar_type { pci_bar_mem64, /* A 64-bit memory BAR */ }; +struct device *pci_get_host_bridge_device(struct pci_dev *dev); +void pci_put_host_bridge_device(struct device *dev); + int pci_configure_extended_tags(struct pci_dev *dev, void *ign); bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, int crs_timeout); diff --git a/include/linux/pci.h b/include/linux/pci.h index b13fb829171e..ffb904e7895d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -644,9 +644,6 @@ static inline struct pci_dev *pci_upstream_bridge(struct pci_dev *dev) return dev->bus->self; } -struct device *pci_get_host_bridge_device(struct pci_dev *dev); -void pci_put_host_bridge_device(struct device *dev); - #ifdef CONFIG_PCI_MSI static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { -- cgit v1.2.3-71-gd317 From 440589dd1068fb36b2fe10ccddf97e43267e3b8d Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:41 -0600 Subject: PCI: Make pci_save_vc_state(), pci_restore_vc_state(), etc private These Virtual Channel interfaces: int pci_save_vc_state(struct pci_dev *dev); void pci_restore_vc_state(struct pci_dev *dev); void pci_allocate_vc_save_buffers(struct pci_dev *dev); are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-5-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 5 +++++ include/linux/pci.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index b06c750e08d7..19cda6e6fccd 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -130,6 +130,11 @@ void pci_vpd_release(struct pci_dev *dev); void pcie_vpd_create_sysfs_dev_files(struct pci_dev *dev); void pcie_vpd_remove_sysfs_dev_files(struct pci_dev *dev); +/* PCI Virtual Channel */ +int pci_save_vc_state(struct pci_dev *dev); +void pci_restore_vc_state(struct pci_dev *dev); +void pci_allocate_vc_save_buffers(struct pci_dev *dev); + /* PCI /proc functions */ #ifdef CONFIG_PROC_FS int pci_proc_attach_device(struct pci_dev *dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index ffb904e7895d..3ff458f89190 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1239,11 +1239,6 @@ bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); void pci_wakeup_bus(struct pci_bus *bus); void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state); -/* PCI Virtual Channel */ -int pci_save_vc_state(struct pci_dev *dev); -void pci_restore_vc_state(struct pci_dev *dev); -void pci_allocate_vc_save_buffers(struct pci_dev *dev); - /* For use by arch with custom probe code */ void set_pcie_port_type(struct pci_dev *pdev); void set_pcie_hotplug_bridge(struct pci_dev *pdev); -- cgit v1.2.3-71-gd317 From 003d3b2c5f835d897b3b10a13a9e1340630e93f1 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:42 -0600 Subject: PCI: Make pci_hotplug_io_size, mem_size, and bus_size private These symbols: extern unsigned long pci_hotplug_io_size; extern unsigned long pci_hotplug_mem_size; extern unsigned long pci_hotplug_bus_size; are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-6-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 3 +++ include/linux/pci.h | 4 ---- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 19cda6e6fccd..9698fa805e28 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -208,6 +208,9 @@ extern const struct attribute_group *pcibus_groups[]; extern const struct device_type pci_dev_type; extern const struct attribute_group *pci_bus_groups[]; +extern unsigned long pci_hotplug_io_size; +extern unsigned long pci_hotplug_mem_size; +extern unsigned long pci_hotplug_bus_size; /** * pci_match_one_device - Tell if a PCI device structure has a matching diff --git a/include/linux/pci.h b/include/linux/pci.h index 3ff458f89190..b5592b9b7f38 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2010,10 +2010,6 @@ extern unsigned long pci_cardbus_mem_size; extern u8 pci_dfl_cache_line_size; extern u8 pci_cache_line_size; -extern unsigned long pci_hotplug_io_size; -extern unsigned long pci_hotplug_mem_size; -extern unsigned long pci_hotplug_bus_size; - /* Architecture-specific versions may override these (weak) */ void pcibios_disable_device(struct pci_dev *dev); void pcibios_set_master(struct pci_dev *dev); -- cgit v1.2.3-71-gd317 From ecd29c1a38af4ba6e61382591dfe93f06f14ba25 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:43 -0600 Subject: PCI: Make pci_bus_get(), pci_bus_put() private These interfaces: struct pci_bus *pci_bus_get(struct pci_bus *bus); void pci_bus_put(struct pci_bus *bus); are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-7-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 2 ++ include/linux/pci.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9698fa805e28..81e94c9f1c12 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -274,6 +274,8 @@ bool pci_bus_clip_resource(struct pci_dev *dev, int idx); void pci_reassigndev_resource_alignment(struct pci_dev *dev); void pci_disable_bridge_window(struct pci_dev *dev); +struct pci_bus *pci_bus_get(struct pci_bus *bus); +void pci_bus_put(struct pci_bus *bus); /* PCIe link information */ #define PCIE_SPEED2STR(speed) \ diff --git a/include/linux/pci.h b/include/linux/pci.h index b5592b9b7f38..4d1b6f07f8f1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1282,8 +1282,6 @@ int pci_request_selected_regions_exclusive(struct pci_dev *, int, const char *); void pci_release_selected_regions(struct pci_dev *, int); /* drivers/pci/bus.c */ -struct pci_bus *pci_bus_get(struct pci_bus *bus); -void pci_bus_put(struct pci_bus *bus); void pci_add_resource(struct list_head *resources, struct resource *res); void pci_add_resource_offset(struct list_head *resources, struct resource *res, resource_size_t offset); -- cgit v1.2.3-71-gd317 From 5da78d95785daa9454336a88b2f86a8998f6c739 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:44 -0600 Subject: PCI: Make pcie_update_link_speed() private This interface: void pcie_update_link_speed(struct pci_bus *bus, u16 link_status); is only used in drivers/pci/ and does not need to be seen by the rest of the kernel. Move it to drivers/pci/pci.h so it's private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-8-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 1 + include/linux/pci.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 81e94c9f1c12..8459663358c5 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -299,6 +299,7 @@ u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed, enum pcie_link_width *width); void __pcie_print_link_status(struct pci_dev *dev, bool verbose); void pcie_report_downtraining(struct pci_dev *dev); +void pcie_update_link_speed(struct pci_bus *bus, u16 link_status); /* Single Root I/O Virtualization */ struct pci_sriov { diff --git a/include/linux/pci.h b/include/linux/pci.h index 4d1b6f07f8f1..8301352a937f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -987,7 +987,6 @@ struct pci_bus *pci_scan_root_bus(struct device *parent, int bus, int pci_scan_root_bus_bridge(struct pci_host_bridge *bridge); struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr); -void pcie_update_link_speed(struct pci_bus *bus, u16 link_status); struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr, const char *name, struct hotplug_slot *hotplug); -- cgit v1.2.3-71-gd317 From b92b512a435da01b52de07e3dcc2f07a4ad404de Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:45 -0600 Subject: PCI: Make pci_ats_init() private This interface: void pci_ats_init(struct pci_dev *dev); is only used in drivers/pci/ and does not need to be seen by the rest of the kernel. Move it to drivers/pci/pci.h so it's private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-9-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 7 ++++--- include/linux/pci.h | 2 -- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 8459663358c5..2bb59afb540e 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -439,11 +439,12 @@ static inline void pci_restore_dpc_state(struct pci_dev *dev) {} #endif #ifdef CONFIG_PCI_ATS +/* Address Translation Service */ +void pci_ats_init(struct pci_dev *dev); void pci_restore_ats_state(struct pci_dev *dev); #else -static inline void pci_restore_ats_state(struct pci_dev *dev) -{ -} +static inline void pci_ats_init(struct pci_dev *d) { } +static inline void pci_restore_ats_state(struct pci_dev *dev) { } #endif /* CONFIG_PCI_ATS */ #ifdef CONFIG_PCI_IOV diff --git a/include/linux/pci.h b/include/linux/pci.h index 8301352a937f..9b8d0c2a1c9a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1761,13 +1761,11 @@ static inline bool pci_ats_disabled(void) { return true; } #ifdef CONFIG_PCI_ATS /* Address Translation Service */ -void pci_ats_init(struct pci_dev *dev); int pci_enable_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); int pci_ats_page_aligned(struct pci_dev *dev); #else -static inline void pci_ats_init(struct pci_dev *d) { } static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } static inline void pci_disable_ats(struct pci_dev *d) { } static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } -- cgit v1.2.3-71-gd317 From 72bde9ced373ca1e27332fd020d248151319a3d6 Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:46 -0600 Subject: PCI: Make pcie_set_ecrc_checking(), pcie_ecrc_get_policy() private These interfaces: void pcie_set_ecrc_checking(struct pci_dev *dev); void pcie_ecrc_get_policy(char *str); are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-10-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 8 ++++++++ include/linux/pci.h | 8 -------- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 2bb59afb540e..d3d006c95041 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -541,6 +541,14 @@ static inline void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev) { } static inline void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev) { } #endif +#ifdef CONFIG_PCIE_ECRC +void pcie_set_ecrc_checking(struct pci_dev *dev); +void pcie_ecrc_get_policy(char *str); +#else +static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { } +static inline void pcie_ecrc_get_policy(char *str) { } +#endif + #ifdef CONFIG_PCIE_PTM void pci_ptm_init(struct pci_dev *dev); #else diff --git a/include/linux/pci.h b/include/linux/pci.h index 9b8d0c2a1c9a..65502c564661 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1559,14 +1559,6 @@ bool pci_aer_available(void); static inline bool pci_aer_available(void) { return false; } #endif -#ifdef CONFIG_PCIE_ECRC -void pcie_set_ecrc_checking(struct pci_dev *dev); -void pcie_ecrc_get_policy(char *str); -#else -static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { } -static inline void pcie_ecrc_get_policy(char *str) { } -#endif - bool pci_ats_disabled(void); #ifdef CONFIG_PCIE_PTM -- cgit v1.2.3-71-gd317 From ac6c26da29c12fa511c877c273ed5c939dc9e96c Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:47 -0600 Subject: PCI: Make pci_enable_ptm() private This interface: int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); is only used in drivers/pci/ and does not need to be seen by the rest of the kernel. Move it to drivers/pci/pci.h so it's private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-11-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 3 +++ include/linux/pci.h | 7 ------- 2 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index d3d006c95041..8935fc1ff446 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -551,8 +551,11 @@ static inline void pcie_ecrc_get_policy(char *str) { } #ifdef CONFIG_PCIE_PTM void pci_ptm_init(struct pci_dev *dev); +int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); #else static inline void pci_ptm_init(struct pci_dev *dev) { } +static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) +{ return -EINVAL; } #endif struct pci_dev_reset_methods { diff --git a/include/linux/pci.h b/include/linux/pci.h index 65502c564661..ef73b0c87f01 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1561,13 +1561,6 @@ static inline bool pci_aer_available(void) { return false; } bool pci_ats_disabled(void); -#ifdef CONFIG_PCIE_PTM -int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); -#else -static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) -{ return -EINVAL; } -#endif - void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); -- cgit v1.2.3-71-gd317 From 621f7e354fd8f99db0e3f7a0e8cda238caee9f3a Mon Sep 17 00:00:00 2001 From: Kelsey Skunberg Date: Wed, 24 Jul 2019 17:38:48 -0600 Subject: PCI: Make pci_set_of_node(), etc private These interfaces: void pci_set_of_node(struct pci_dev *dev); void pci_release_of_node(struct pci_dev *dev); void pci_set_bus_of_node(struct pci_bus *bus); void pci_release_bus_of_node(struct pci_bus *bus); are only used in drivers/pci/ and do not need to be seen by the rest of the kernel. Move them to drivers/pci/pci.h so they're private to the PCI subsystem. Link: https://lore.kernel.org/r/20190724233848.73327-12-skunberg.kelsey@gmail.com Signed-off-by: Kelsey Skunberg Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 9 +++++++++ include/linux/pci.h | 8 -------- 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 8935fc1ff446..61bbfd611140 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -592,6 +592,10 @@ struct device_node; int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); int of_pci_get_max_link_speed(struct device_node *node); +void pci_set_of_node(struct pci_dev *dev); +void pci_release_of_node(struct pci_dev *dev); +void pci_set_bus_of_node(struct pci_bus *bus); +void pci_release_bus_of_node(struct pci_bus *bus); #else static inline int @@ -611,6 +615,11 @@ of_pci_get_max_link_speed(struct device_node *node) { return -EINVAL; } + +static inline void pci_set_of_node(struct pci_dev *dev) { } +static inline void pci_release_of_node(struct pci_dev *dev) { } +static inline void pci_set_bus_of_node(struct pci_bus *bus) { } +static inline void pci_release_bus_of_node(struct pci_bus *bus) { } #endif /* CONFIG_OF */ #if defined(CONFIG_OF_ADDRESS) diff --git a/include/linux/pci.h b/include/linux/pci.h index ef73b0c87f01..5a26b7db71b3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2259,10 +2259,6 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, #ifdef CONFIG_OF struct device_node; struct irq_domain; -void pci_set_of_node(struct pci_dev *dev); -void pci_release_of_node(struct pci_dev *dev); -void pci_set_bus_of_node(struct pci_bus *bus); -void pci_release_bus_of_node(struct pci_bus *bus); struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus); int pci_parse_request_of_pci_ranges(struct device *dev, struct list_head *resources, @@ -2272,10 +2268,6 @@ int pci_parse_request_of_pci_ranges(struct device *dev, struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); #else /* CONFIG_OF */ -static inline void pci_set_of_node(struct pci_dev *dev) { } -static inline void pci_release_of_node(struct pci_dev *dev) { } -static inline void pci_set_bus_of_node(struct pci_bus *bus) { } -static inline void pci_release_bus_of_node(struct pci_bus *bus) { } static inline struct irq_domain * pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } static inline int pci_parse_request_of_pci_ranges(struct device *dev, -- cgit v1.2.3-71-gd317 From 259231a045616c4101d023a8f4dcc8379af265a6 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 3 Jul 2019 20:51:26 -0300 Subject: cpuidle: add poll_limit_ns to cpuidle_device structure Add a poll_limit_ns variable to cpuidle_device structure. Calculate and configure it in the new cpuidle_poll_time function, in case its zero. Individual governors are allowed to override this value. Signed-off-by: Marcelo Tosatti Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle.c | 30 ++++++++++++++++++++++++++++++ drivers/cpuidle/poll_state.c | 11 ++--------- drivers/cpuidle/sysfs.c | 7 +++++++ include/linux/cpuidle.h | 6 ++++++ 4 files changed, 45 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 0f4b7c45df3e..0895b988fa92 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -361,6 +361,36 @@ void cpuidle_reflect(struct cpuidle_device *dev, int index) cpuidle_curr_governor->reflect(dev, index); } +/** + * cpuidle_poll_time - return amount of time to poll for, + * governors can override dev->poll_limit_ns if necessary + * + * @drv: the cpuidle driver tied with the cpu + * @dev: the cpuidle device + * + */ +u64 cpuidle_poll_time(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + int i; + u64 limit_ns; + + if (dev->poll_limit_ns) + return dev->poll_limit_ns; + + limit_ns = TICK_NSEC; + for (i = 1; i < drv->state_count; i++) { + if (drv->states[i].disabled || dev->states_usage[i].disable) + continue; + + limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC; + } + + dev->poll_limit_ns = limit_ns; + + return dev->poll_limit_ns; +} + /** * cpuidle_install_idle_handler - installs the cpuidle idle loop handler */ diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 02b9315a9e96..c8fa5f41dfc4 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -20,16 +20,9 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev, local_irq_enable(); if (!current_set_polling_and_test()) { unsigned int loop_count = 0; - u64 limit = TICK_NSEC; - int i; + u64 limit; - for (i = 1; i < drv->state_count; i++) { - if (drv->states[i].disabled || dev->states_usage[i].disable) - continue; - - limit = (u64)drv->states[i].target_residency * NSEC_PER_USEC; - break; - } + limit = cpuidle_poll_time(drv, dev); while (!need_resched()) { cpu_relax(); diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index eb20adb5de23..2bb2683b493c 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -334,6 +334,7 @@ struct cpuidle_state_kobj { struct cpuidle_state_usage *state_usage; struct completion kobj_unregister; struct kobject kobj; + struct cpuidle_device *device; }; #ifdef CONFIG_SUSPEND @@ -391,6 +392,7 @@ static inline void cpuidle_remove_s2idle_attr_group(struct cpuidle_state_kobj *k #define kobj_to_state_obj(k) container_of(k, struct cpuidle_state_kobj, kobj) #define kobj_to_state(k) (kobj_to_state_obj(k)->state) #define kobj_to_state_usage(k) (kobj_to_state_obj(k)->state_usage) +#define kobj_to_device(k) (kobj_to_state_obj(k)->device) #define attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr) static ssize_t cpuidle_state_show(struct kobject *kobj, struct attribute *attr, @@ -414,10 +416,14 @@ static ssize_t cpuidle_state_store(struct kobject *kobj, struct attribute *attr, struct cpuidle_state *state = kobj_to_state(kobj); struct cpuidle_state_usage *state_usage = kobj_to_state_usage(kobj); struct cpuidle_state_attr *cattr = attr_to_stateattr(attr); + struct cpuidle_device *dev = kobj_to_device(kobj); if (cattr->store) ret = cattr->store(state, state_usage, buf, size); + /* reset poll time cache */ + dev->poll_limit_ns = 0; + return ret; } @@ -468,6 +474,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) } kobj->state = &drv->states[i]; kobj->state_usage = &device->states_usage[i]; + kobj->device = device; init_completion(&kobj->kobj_unregister); ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle, diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index bb9a0db89f1a..b484dd69ec21 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -86,6 +86,7 @@ struct cpuidle_device { ktime_t next_hrtimer; int last_residency; + u64 poll_limit_ns; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; @@ -132,6 +133,8 @@ extern int cpuidle_select(struct cpuidle_driver *drv, extern int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index); extern void cpuidle_reflect(struct cpuidle_device *dev, int index); +extern u64 cpuidle_poll_time(struct cpuidle_driver *drv, + struct cpuidle_device *dev); extern int cpuidle_register_driver(struct cpuidle_driver *drv); extern struct cpuidle_driver *cpuidle_get_driver(void); @@ -166,6 +169,9 @@ static inline int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) {return -ENODEV; } static inline void cpuidle_reflect(struct cpuidle_device *dev, int index) { } +extern u64 cpuidle_poll_time(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{return 0; } static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; } -- cgit v1.2.3-71-gd317 From 7d4daeedd575bbc3c40c87fc6708a8b88c50fe7e Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 3 Jul 2019 20:51:27 -0300 Subject: governors: unify last_state_idx Since this field is shared by all governors, move it to cpuidle device structure. Signed-off-by: Marcelo Tosatti Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/governors/ladder.c | 21 ++++++++++----------- drivers/cpuidle/governors/menu.c | 5 ++--- drivers/cpuidle/governors/teo.c | 12 ++++++------ include/linux/cpuidle.h | 1 + 4 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index f0dddc66af26..428eeb832fe7 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -38,7 +38,6 @@ struct ladder_device_state { struct ladder_device { struct ladder_device_state states[CPUIDLE_STATE_MAX]; - int last_state_idx; }; static DEFINE_PER_CPU(struct ladder_device, ladder_devices); @@ -49,12 +48,13 @@ static DEFINE_PER_CPU(struct ladder_device, ladder_devices); * @old_idx: the current state index * @new_idx: the new target state index */ -static inline void ladder_do_selection(struct ladder_device *ldev, +static inline void ladder_do_selection(struct cpuidle_device *dev, + struct ladder_device *ldev, int old_idx, int new_idx) { ldev->states[old_idx].stats.promotion_count = 0; ldev->states[old_idx].stats.demotion_count = 0; - ldev->last_state_idx = new_idx; + dev->last_state_idx = new_idx; } /** @@ -68,13 +68,13 @@ static int ladder_select_state(struct cpuidle_driver *drv, { struct ladder_device *ldev = this_cpu_ptr(&ladder_devices); struct ladder_device_state *last_state; - int last_residency, last_idx = ldev->last_state_idx; + int last_residency, last_idx = dev->last_state_idx; int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0; int latency_req = cpuidle_governor_latency_req(dev->cpu); /* Special case when user has set very strict latency requirement */ if (unlikely(latency_req == 0)) { - ladder_do_selection(ldev, last_idx, 0); + ladder_do_selection(dev, ldev, last_idx, 0); return 0; } @@ -91,7 +91,7 @@ static int ladder_select_state(struct cpuidle_driver *drv, last_state->stats.promotion_count++; last_state->stats.demotion_count = 0; if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) { - ladder_do_selection(ldev, last_idx, last_idx + 1); + ladder_do_selection(dev, ldev, last_idx, last_idx + 1); return last_idx + 1; } } @@ -107,7 +107,7 @@ static int ladder_select_state(struct cpuidle_driver *drv, if (drv->states[i].exit_latency <= latency_req) break; } - ladder_do_selection(ldev, last_idx, i); + ladder_do_selection(dev, ldev, last_idx, i); return i; } @@ -116,7 +116,7 @@ static int ladder_select_state(struct cpuidle_driver *drv, last_state->stats.demotion_count++; last_state->stats.promotion_count = 0; if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) { - ladder_do_selection(ldev, last_idx, last_idx - 1); + ladder_do_selection(dev, ldev, last_idx, last_idx - 1); return last_idx - 1; } } @@ -139,7 +139,7 @@ static int ladder_enable_device(struct cpuidle_driver *drv, struct ladder_device_state *lstate; struct cpuidle_state *state; - ldev->last_state_idx = first_idx; + dev->last_state_idx = first_idx; for (i = first_idx; i < drv->state_count; i++) { state = &drv->states[i]; @@ -167,9 +167,8 @@ static int ladder_enable_device(struct cpuidle_driver *drv, */ static void ladder_reflect(struct cpuidle_device *dev, int index) { - struct ladder_device *ldev = this_cpu_ptr(&ladder_devices); if (index > 0) - ldev->last_state_idx = index; + dev->last_state_idx = index; } static struct cpuidle_governor ladder_governor = { diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index e9a28c7846d6..dace4c7f830c 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -117,7 +117,6 @@ */ struct menu_device { - int last_state_idx; int needs_update; int tick_wakeup; @@ -455,7 +454,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index) { struct menu_device *data = this_cpu_ptr(&menu_devices); - data->last_state_idx = index; + dev->last_state_idx = index; data->needs_update = 1; data->tick_wakeup = tick_nohz_idle_got_tick(); } @@ -468,7 +467,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index) static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) { struct menu_device *data = this_cpu_ptr(&menu_devices); - int last_idx = data->last_state_idx; + int last_idx = dev->last_state_idx; struct cpuidle_state *target = &drv->states[last_idx]; unsigned int measured_us; unsigned int new_factor; diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index 7d05efdbd3c6..a2fd81067a13 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -96,7 +96,6 @@ struct teo_idle_state { * @time_span_ns: Time between idle state selection and post-wakeup update. * @sleep_length_ns: Time till the closest timer event (at the selection time). * @states: Idle states data corresponding to this CPU. - * @last_state: Idle state entered by the CPU last time. * @interval_idx: Index of the most recent saved idle interval. * @intervals: Saved idle duration values. */ @@ -104,7 +103,6 @@ struct teo_cpu { u64 time_span_ns; u64 sleep_length_ns; struct teo_idle_state states[CPUIDLE_STATE_MAX]; - int last_state; int interval_idx; unsigned int intervals[INTERVALS]; }; @@ -130,7 +128,9 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) */ measured_us = sleep_length_us; } else { - unsigned int lat = drv->states[cpu_data->last_state].exit_latency; + unsigned int lat; + + lat = drv->states[dev->last_state_idx].exit_latency; measured_us = ktime_to_us(cpu_data->time_span_ns); /* @@ -245,9 +245,9 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, int max_early_idx, idx, i; ktime_t delta_tick; - if (cpu_data->last_state >= 0) { + if (dev->last_state_idx >= 0) { teo_update(drv, dev); - cpu_data->last_state = -1; + dev->last_state_idx = -1; } cpu_data->time_span_ns = local_clock(); @@ -394,7 +394,7 @@ static void teo_reflect(struct cpuidle_device *dev, int state) { struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); - cpu_data->last_state = state; + dev->last_state_idx = state; /* * If the wakeup was not "natural", but triggered by one of the safety * nets, assume that the CPU might have been idle for the entire sleep diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b484dd69ec21..ba535a1a47d5 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -85,6 +85,7 @@ struct cpuidle_device { unsigned int cpu; ktime_t next_hrtimer; + int last_state_idx; int last_residency; u64 poll_limit_ns; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; -- cgit v1.2.3-71-gd317 From a1c4423b02b2121108e3ea9580741e0f26309a48 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 3 Jul 2019 20:51:29 -0300 Subject: cpuidle-haltpoll: disable host side polling when kvm virtualized When performing guest side polling, it is not necessary to also perform host side polling. So disable host side polling, via the new MSR interface, when loading cpuidle-haltpoll driver. Signed-off-by: Marcelo Tosatti Signed-off-by: Rafael J. Wysocki --- arch/x86/Kconfig | 7 ++++++ arch/x86/include/asm/cpuidle_haltpoll.h | 8 +++++++ arch/x86/kernel/kvm.c | 42 +++++++++++++++++++++++++++++++++ drivers/cpuidle/cpuidle-haltpoll.c | 9 ++++++- include/linux/cpuidle_haltpoll.h | 16 +++++++++++++ 5 files changed, 81 insertions(+), 1 deletion(-) create mode 100644 arch/x86/include/asm/cpuidle_haltpoll.h create mode 100644 include/linux/cpuidle_haltpoll.h (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 222855cc0158..05e78acb187c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -794,6 +794,7 @@ config KVM_GUEST bool "KVM Guest support (including kvmclock)" depends on PARAVIRT select PARAVIRT_CLOCK + select ARCH_CPUIDLE_HALTPOLL default y ---help--- This option enables various optimizations for running under the KVM @@ -802,6 +803,12 @@ config KVM_GUEST underlying device model, the host provides the guest with timing infrastructure such as time of day, and system time +config ARCH_CPUIDLE_HALTPOLL + def_bool n + prompt "Disable host haltpoll when loading haltpoll driver" + help + If virtualized under KVM, disable host haltpoll. + config PVH bool "Support for running PVH guests" ---help--- diff --git a/arch/x86/include/asm/cpuidle_haltpoll.h b/arch/x86/include/asm/cpuidle_haltpoll.h new file mode 100644 index 000000000000..ff8607d81526 --- /dev/null +++ b/arch/x86/include/asm/cpuidle_haltpoll.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_HALTPOLL_H +#define _ARCH_HALTPOLL_H + +void arch_haltpoll_enable(void); +void arch_haltpoll_disable(void); + +#endif diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b7f34fe2171e..f48401be8ce0 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -875,3 +875,45 @@ void __init kvm_spinlock_init(void) } #endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + +static void kvm_disable_host_haltpoll(void *i) +{ + wrmsrl(MSR_KVM_POLL_CONTROL, 0); +} + +static void kvm_enable_host_haltpoll(void *i) +{ + wrmsrl(MSR_KVM_POLL_CONTROL, 1); +} + +void arch_haltpoll_enable(void) +{ + if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) { + printk(KERN_ERR "kvm: host does not support poll control\n"); + printk(KERN_ERR "kvm: host upgrade recommended\n"); + return; + } + + preempt_disable(); + /* Enable guest halt poll disables host halt poll */ + kvm_disable_host_haltpoll(NULL); + smp_call_function(kvm_disable_host_haltpoll, NULL, 1); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(arch_haltpoll_enable); + +void arch_haltpoll_disable(void) +{ + if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) + return; + + preempt_disable(); + /* Enable guest halt poll disables host halt poll */ + kvm_enable_host_haltpoll(NULL); + smp_call_function(kvm_enable_host_haltpoll, NULL, 1); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(arch_haltpoll_disable); +#endif diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c index 35cfb53e9287..9ac093dcbb01 100644 --- a/drivers/cpuidle/cpuidle-haltpoll.c +++ b/drivers/cpuidle/cpuidle-haltpoll.c @@ -15,6 +15,7 @@ #include #include #include +#include static int default_enter_idle(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) @@ -47,6 +48,7 @@ static struct cpuidle_driver haltpoll_driver = { static int __init haltpoll_init(void) { + int ret; struct cpuidle_driver *drv = &haltpoll_driver; cpuidle_poll_state_init(drv); @@ -54,11 +56,16 @@ static int __init haltpoll_init(void) if (!kvm_para_available()) return 0; - return cpuidle_register(&haltpoll_driver, NULL); + ret = cpuidle_register(&haltpoll_driver, NULL); + if (ret == 0) + arch_haltpoll_enable(); + + return ret; } static void __exit haltpoll_exit(void) { + arch_haltpoll_disable(); cpuidle_unregister(&haltpoll_driver); } diff --git a/include/linux/cpuidle_haltpoll.h b/include/linux/cpuidle_haltpoll.h new file mode 100644 index 000000000000..fe5954c2409e --- /dev/null +++ b/include/linux/cpuidle_haltpoll.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _CPUIDLE_HALTPOLL_H +#define _CPUIDLE_HALTPOLL_H + +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL +#include +#else +static inline void arch_haltpoll_enable(void) +{ +} + +static inline void arch_haltpoll_disable(void) +{ +} +#endif +#endif -- cgit v1.2.3-71-gd317 From 64a38e840ce5940253208eaba40265c73decc4ee Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Fri, 26 Jul 2019 18:33:01 -0400 Subject: SUNRPC: Track writers of the 'channel' file to improve cache_listeners_exist The sunrpc cache interface is susceptible to being fooled by a rogue process just reading a 'channel' file. If this happens the kernel may think a valid daemon exists to service the cache when it does not. For example, the following may fool the kernel: cat /proc/net/rpc/auth.unix.gid/channel Change the tracking of readers to writers when considering whether a listener exists as all valid daemon processes either open a channel file O_RDWR or O_WRONLY. While this does not prevent a rogue process from "stealing" a message from the kernel, it does at least improve the kernels perception of whether a valid process servicing the cache exists. Signed-off-by: Dave Wysochanski Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 6 +++--- net/sunrpc/cache.c | 12 ++++++++---- 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index c7f38e897174..f7d086b77a21 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -107,9 +107,9 @@ struct cache_detail { /* fields for communication over channel */ struct list_head queue; - atomic_t readers; /* how many time is /chennel open */ - time_t last_close; /* if no readers, when did last close */ - time_t last_warn; /* when we last warned about no readers */ + atomic_t writers; /* how many time is /channel open */ + time_t last_close; /* if no writers, when did last close */ + time_t last_warn; /* when we last warned about no writers */ union { struct proc_dir_entry *procfs; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 6f1528f271ee..a6a6190ad37a 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -373,7 +373,7 @@ void sunrpc_init_cache_detail(struct cache_detail *cd) spin_lock(&cache_list_lock); cd->nextcheck = 0; cd->entries = 0; - atomic_set(&cd->readers, 0); + atomic_set(&cd->writers, 0); cd->last_close = 0; cd->last_warn = -1; list_add(&cd->others, &cache_list); @@ -1029,11 +1029,13 @@ static int cache_open(struct inode *inode, struct file *filp, } rp->offset = 0; rp->q.reader = 1; - atomic_inc(&cd->readers); + spin_lock(&queue_lock); list_add(&rp->q.list, &cd->queue); spin_unlock(&queue_lock); } + if (filp->f_mode & FMODE_WRITE) + atomic_inc(&cd->writers); filp->private_data = rp; return 0; } @@ -1062,8 +1064,10 @@ static int cache_release(struct inode *inode, struct file *filp, filp->private_data = NULL; kfree(rp); + } + if (filp->f_mode & FMODE_WRITE) { + atomic_dec(&cd->writers); cd->last_close = seconds_since_boot(); - atomic_dec(&cd->readers); } module_put(cd->owner); return 0; @@ -1171,7 +1175,7 @@ static void warn_no_listener(struct cache_detail *detail) static bool cache_listeners_exist(struct cache_detail *detail) { - if (atomic_read(&detail->readers)) + if (atomic_read(&detail->writers)) return true; if (detail->last_close == 0) /* This cache was never opened */ -- cgit v1.2.3-71-gd317 From 7240b60c98d6309363a9f8d5a4ecd5b0626f2aff Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Tue, 30 Jul 2019 07:40:32 -0700 Subject: linux: Add skb_frag_t page_offset accessors Add skb_frag_off(), skb_frag_off_add(), skb_frag_off_set(), and skb_frag_off_copy() accessors for page_offset. Signed-off-by: Jonathan Lemon Signed-off-by: David S. Miller --- include/linux/skbuff.h | 67 ++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 59 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 718742b1c505..2957cdd6c032 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -312,7 +312,7 @@ extern int sysctl_max_skb_frags; typedef struct bio_vec skb_frag_t; /** - * skb_frag_size - Returns the size of a skb fragment + * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) @@ -321,7 +321,7 @@ static inline unsigned int skb_frag_size(const skb_frag_t *frag) } /** - * skb_frag_size_set - Sets the size of a skb fragment + * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ @@ -331,7 +331,7 @@ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) } /** - * skb_frag_size_add - Incrementes the size of a skb fragment by %delta + * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ @@ -341,7 +341,7 @@ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) } /** - * skb_frag_size_sub - Decrements the size of a skb fragment by %delta + * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ @@ -2857,6 +2857,46 @@ static inline void skb_propagate_pfmemalloc(struct page *page, skb->pfmemalloc = true; } +/** + * skb_frag_off() - Returns the offset of a skb fragment + * @frag: the paged fragment + */ +static inline unsigned int skb_frag_off(const skb_frag_t *frag) +{ + return frag->page_offset; +} + +/** + * skb_frag_off_add() - Increments the offset of a skb fragment by @delta + * @frag: skb fragment + * @delta: value to add + */ +static inline void skb_frag_off_add(skb_frag_t *frag, int delta) +{ + frag->page_offset += delta; +} + +/** + * skb_frag_off_set() - Sets the offset of a skb fragment + * @frag: skb fragment + * @offset: offset of fragment + */ +static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) +{ + frag->page_offset = offset; +} + +/** + * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment + * @fragto: skb fragment where offset is set + * @fragfrom: skb fragment offset is copied from + */ +static inline void skb_frag_off_copy(skb_frag_t *fragto, + const skb_frag_t *fragfrom) +{ + fragto->page_offset = fragfrom->page_offset; +} + /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment @@ -2923,7 +2963,7 @@ static inline void skb_frag_unref(struct sk_buff *skb, int f) */ static inline void *skb_frag_address(const skb_frag_t *frag) { - return page_address(skb_frag_page(frag)) + frag->page_offset; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** @@ -2939,7 +2979,18 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) if (unlikely(!ptr)) return NULL; - return ptr + frag->page_offset; + return ptr + skb_frag_off(frag); +} + +/** + * skb_frag_page_copy() - sets the page in a fragment from another fragment + * @fragto: skb fragment where page is set + * @fragfrom: skb fragment page is copied from + */ +static inline void skb_frag_page_copy(skb_frag_t *fragto, + const skb_frag_t *fragfrom) +{ + fragto->bv_page = fragfrom->bv_page; } /** @@ -2987,7 +3038,7 @@ static inline dma_addr_t skb_frag_dma_map(struct device *dev, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), - frag->page_offset + offset, size, dir); + skb_frag_off(frag) + offset, size, dir); } static inline struct sk_buff *pskb_copy(struct sk_buff *skb, @@ -3157,7 +3208,7 @@ static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && - off == frag->page_offset + skb_frag_size(frag); + off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } -- cgit v1.2.3-71-gd317 From 65c84f148e359ed398dcc9ed736131103f40896b Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Tue, 30 Jul 2019 07:40:34 -0700 Subject: linux: Remove bvec page_offset, use bv_offset Now that page_offset is referenced through accessors, remove the union, and use bv_offset. Signed-off-by: Jonathan Lemon Signed-off-by: David S. Miller --- include/linux/bvec.h | 5 +---- include/linux/skbuff.h | 10 +++++----- 2 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 7f2b2ea9399c..a032f01e928c 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -18,10 +18,7 @@ struct bio_vec { struct page *bv_page; unsigned int bv_len; - union { - __u32 page_offset; - unsigned int bv_offset; - }; + unsigned int bv_offset; }; struct bvec_iter { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2957cdd6c032..3aef8d82ea59 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2078,7 +2078,7 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, * on page_is_pfmemalloc doing the right thing(tm). */ frag->bv_page = page; - frag->page_offset = off; + frag->bv_offset = off; skb_frag_size_set(frag, size); page = compound_head(page); @@ -2863,7 +2863,7 @@ static inline void skb_propagate_pfmemalloc(struct page *page, */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { - return frag->page_offset; + return frag->bv_offset; } /** @@ -2873,7 +2873,7 @@ static inline unsigned int skb_frag_off(const skb_frag_t *frag) */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { - frag->page_offset += delta; + frag->bv_offset += delta; } /** @@ -2883,7 +2883,7 @@ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { - frag->page_offset = offset; + frag->bv_offset = offset; } /** @@ -2894,7 +2894,7 @@ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { - fragto->page_offset = fragfrom->page_offset; + fragto->bv_offset = fragfrom->bv_offset; } /** -- cgit v1.2.3-71-gd317 From b74494872555d1f7888dfd9225700a363f4a84fc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Jul 2019 20:30:49 +0200 Subject: hrtimer: Remove task argument from hrtimer_init_sleeper() All callers hand in 'current' and that's the only task pointer which actually makes sense. Remove the task argument and set current in the function. Signed-off-by: Thomas Gleixner Reviewed-by: Steven Rostedt (VMware) Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20190726185752.791885290@linutronix.de --- block/blk-mq.c | 2 +- drivers/staging/android/vsoc.c | 2 +- include/linux/hrtimer.h | 3 +-- include/linux/wait.h | 2 +- kernel/futex.c | 2 +- kernel/time/hrtimer.c | 8 ++++---- net/core/pktgen.c | 2 +- 7 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index b038ec680e84..5f647cb8c695 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3418,7 +3418,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode); hrtimer_set_expires(&hs.timer, kt); - hrtimer_init_sleeper(&hs, current); + hrtimer_init_sleeper(&hs); do { if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE) break; diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c index 00a1ec7b9154..ce480bcf20d2 100644 --- a/drivers/staging/android/vsoc.c +++ b/drivers/staging/android/vsoc.c @@ -442,7 +442,7 @@ static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg) hrtimer_set_expires_range_ns(&to->timer, wake_time, current->timer_slack_ns); - hrtimer_init_sleeper(to, current); + hrtimer_init_sleeper(to); } while (1) { diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 4971100a8cab..3c74f89367c4 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -463,8 +463,7 @@ extern long hrtimer_nanosleep(const struct timespec64 *rqtp, const enum hrtimer_mode mode, const clockid_t clockid); -extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, - struct task_struct *tsk); +extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl); extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); diff --git a/include/linux/wait.h b/include/linux/wait.h index b6f77cf60dd7..d57832774ca6 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -489,7 +489,7 @@ do { \ struct hrtimer_sleeper __t; \ \ hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \ - hrtimer_init_sleeper(&__t, current); \ + hrtimer_init_sleeper(&__t); \ if ((timeout) != KTIME_MAX) \ hrtimer_start_range_ns(&__t.timer, timeout, \ current->timer_slack_ns, \ diff --git a/kernel/futex.c b/kernel/futex.c index 6d50728ef2e7..5e9842ea4012 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -490,7 +490,7 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, hrtimer_init_on_stack(&timeout->timer, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - hrtimer_init_sleeper(timeout, current); + hrtimer_init_sleeper(timeout); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 5ee77f1a8a92..de895d86800c 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1639,10 +1639,10 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) return HRTIMER_NORESTART; } -void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) +void hrtimer_init_sleeper(struct hrtimer_sleeper *sl) { sl->timer.function = hrtimer_wakeup; - sl->task = task; + sl->task = current; } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); @@ -1669,7 +1669,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod { struct restart_block *restart; - hrtimer_init_sleeper(t, current); + hrtimer_init_sleeper(t); do { set_current_state(TASK_INTERRUPTIBLE); @@ -1930,7 +1930,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, hrtimer_init_on_stack(&t.timer, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); - hrtimer_init_sleeper(&t, current); + hrtimer_init_sleeper(&t); hrtimer_start_expires(&t.timer, mode); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index bb9915291644..7f3cf2381f27 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2171,7 +2171,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) } while (ktime_compare(end_time, spin_until) < 0); } else { /* see do_nanosleep */ - hrtimer_init_sleeper(&t, current); + hrtimer_init_sleeper(&t); do { set_current_state(TASK_INTERRUPTIBLE); hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); -- cgit v1.2.3-71-gd317 From 473c7391ce731adb482c03e420964676ed8b494d Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:30 +0200 Subject: vsock/virtio: limit the memory used per-socket Since virtio-vsock was introduced, the buffers filled by the host and pushed to the guest using the vring, are directly queued in a per-socket list. These buffers are preallocated by the guest with a fixed size (4 KB). The maximum amount of memory used by each socket should be controlled by the credit mechanism. The default credit available per-socket is 256 KB, but if we use only 1 byte per packet, the guest can queue up to 262144 of 4 KB buffers, using up to 1 GB of memory per-socket. In addition, the guest will continue to fill the vring with new 4 KB free buffers to avoid starvation of other sockets. This patch mitigates this issue copying the payload of small packets (< 128 bytes) into the buffer of last packet queued, in order to avoid wasting memory. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 2 ++ include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport.c | 1 + net/vmw_vsock/virtio_transport_common.c | 60 ++++++++++++++++++++++++++++----- 4 files changed, 55 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 6a50e1d0529c..6c8390a2af52 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -329,6 +329,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } + pkt->buf_len = pkt->len; + nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter); if (nbytes != pkt->len) { vq_err(vq, "Expected %u byte payload, got %zu bytes\n", diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index e223e2632edd..7d973903f52e 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -52,6 +52,7 @@ struct virtio_vsock_pkt { /* socket refcnt not held, only use for cancellation */ struct vsock_sock *vsk; void *buf; + u32 buf_len; u32 len; u32 off; bool reply; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 0815d1357861..082a30936690 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -307,6 +307,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) break; } + pkt->buf_len = buf_len; pkt->len = buf_len; sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6f1a8aff65c5..095221f94786 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,9 @@ /* How long to wait for graceful shutdown of a connection */ #define VSOCK_CLOSE_TIMEOUT (8 * HZ) +/* Threshold for detecting small packets to copy */ +#define GOOD_COPY_LEN 128 + static const struct virtio_transport *virtio_transport_get_ops(void) { const struct vsock_transport *t = vsock_core_get_transport(); @@ -64,6 +67,9 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, pkt->buf = kmalloc(len, GFP_KERNEL); if (!pkt->buf) goto out_pkt; + + pkt->buf_len = len; + err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; @@ -841,24 +847,60 @@ destroy: return err; } +static void +virtio_transport_recv_enqueue(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + bool free_pkt = false; + + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + + virtio_transport_inc_rx_pkt(vvs, pkt); + + /* Try to copy small packets into the buffer of last packet queued, + * to avoid wasting memory queueing the entire buffer with a small + * payload. + */ + if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) { + struct virtio_vsock_pkt *last_pkt; + + last_pkt = list_last_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + /* If there is space in the last packet queued, we copy the + * new packet in its buffer. + */ + if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + memcpy(last_pkt->buf + last_pkt->len, pkt->buf, + pkt->len); + last_pkt->len += pkt->len; + free_pkt = true; + goto out; + } + } + + list_add_tail(&pkt->list, &vvs->rx_queue); + +out: + spin_unlock_bh(&vvs->rx_lock); + if (free_pkt) + virtio_transport_free_pkt(pkt); +} + static int virtio_transport_recv_connected(struct sock *sk, struct virtio_vsock_pkt *pkt) { struct vsock_sock *vsk = vsock_sk(sk); - struct virtio_vsock_sock *vvs = vsk->trans; int err = 0; switch (le16_to_cpu(pkt->hdr.op)) { case VIRTIO_VSOCK_OP_RW: - pkt->len = le32_to_cpu(pkt->hdr.len); - pkt->off = 0; - - spin_lock_bh(&vvs->rx_lock); - virtio_transport_inc_rx_pkt(vvs, pkt); - list_add_tail(&pkt->list, &vvs->rx_queue); - spin_unlock_bh(&vvs->rx_lock); - + virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: -- cgit v1.2.3-71-gd317 From b89d882dc9fc279c8acbf1df71d51b22394186d5 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:31 +0200 Subject: vsock/virtio: reduce credit update messages In order to reduce the number of credit update messages, we send them only when the space available seen by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport_common.c | 16 +++++++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 7d973903f52e..49fc9d20bc43 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -41,6 +41,7 @@ struct virtio_vsock_sock { /* Protected by rx_lock */ u32 fwd_cnt; + u32 last_fwd_cnt; u32 rx_bytes; struct list_head rx_queue; }; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 095221f94786..a85559d4d974 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -211,6 +211,7 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { spin_lock_bh(&vvs->tx_lock); + vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); spin_unlock_bh(&vvs->tx_lock); @@ -261,6 +262,7 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_sock *vvs = vsk->trans; struct virtio_vsock_pkt *pkt; size_t bytes, total = 0; + u32 free_space; int err = -EFAULT; spin_lock_bh(&vvs->rx_lock); @@ -291,11 +293,19 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, virtio_transport_free_pkt(pkt); } } + + free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt); + spin_unlock_bh(&vvs->rx_lock); - /* Send a credit pkt to peer */ - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + /* We send a credit update only when the space available seen + * by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + */ + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { + virtio_transport_send_credit_update(vsk, + VIRTIO_VSOCK_TYPE_STREAM, + NULL); + } return total; -- cgit v1.2.3-71-gd317 From 9632e9f61bc4191411c47933abe5f2d93c578f5e Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:32 +0200 Subject: vsock/virtio: fix locking in virtio_transport_inc_tx_pkt() fwd_cnt and last_fwd_cnt are protected by rx_lock, so we should use the same spinlock also if we are in the TX path. Move also buf_alloc under the same lock. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 2 +- net/vmw_vsock/virtio_transport_common.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 49fc9d20bc43..4c7781f4b29b 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -35,7 +35,6 @@ struct virtio_vsock_sock { /* Protected by tx_lock */ u32 tx_cnt; - u32 buf_alloc; u32 peer_fwd_cnt; u32 peer_buf_alloc; @@ -43,6 +42,7 @@ struct virtio_vsock_sock { u32 fwd_cnt; u32 last_fwd_cnt; u32 rx_bytes; + u32 buf_alloc; struct list_head rx_queue; }; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a85559d4d974..34a2b42313b7 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -210,11 +210,11 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { - spin_lock_bh(&vvs->tx_lock); + spin_lock_bh(&vvs->rx_lock); vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); - spin_unlock_bh(&vvs->tx_lock); + spin_unlock_bh(&vvs->rx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); -- cgit v1.2.3-71-gd317 From fce04b1ce8e326bf2cafaea4a0c91dbc3e99e403 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 30 Jul 2019 13:43:35 +0300 Subject: gpiolib: of: Reshuffle contents of consumer.h for new library layout Kernel build bot reported a compilation error after the commit f626d6dfb709 ("gpio: of: Break out OF-only code"): drivers/gpio/gpiolib-devres.o: In function `devm_gpiod_get_from_of_node': gpiolib-devres.c:(.text+0x19a): undefined reference to `gpiod_get_from_of_node' This happens due to move the latter under umbrella of CONFIG_OF_GPIO while customer.h contains staled data. Fix it by reshuffling contents of consumer.h to satisfy build dependencies. Reported-by: kbuild test robot Fixes: f626d6dfb709 ("gpio: of: Break out OF-only code"): Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20190730104337.21235-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 78 ++++++++++++++++++++++++++----------------- 1 file changed, 48 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 9ddcf50a3c59..6019d4d128c5 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -170,18 +170,8 @@ struct gpio_desc *gpio_to_desc(unsigned gpio); int desc_to_gpio(const struct gpio_desc *desc); /* Child properties interface */ -struct device_node; struct fwnode_handle; -struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, - const char *propname, int index, - enum gpiod_flags dflags, - const char *label); -struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, - struct device_node *node, - const char *propname, int index, - enum gpiod_flags dflags, - const char *label); struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, const char *propname, int index, enum gpiod_flags dflags, @@ -530,28 +520,8 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) } /* Child properties interface */ -struct device_node; struct fwnode_handle; -static inline -struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, - const char *propname, int index, - enum gpiod_flags dflags, - const char *label) -{ - return ERR_PTR(-ENOSYS); -} - -static inline -struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, - struct device_node *node, - const char *propname, int index, - enum gpiod_flags dflags, - const char *label) -{ - return ERR_PTR(-ENOSYS); -} - static inline struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, const char *propname, int index, @@ -584,6 +554,54 @@ struct gpio_desc *devm_fwnode_get_gpiod_from_child(struct device *dev, flags, label); } +#if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_OF_GPIO) +struct device_node; + +struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, + const char *propname, int index, + enum gpiod_flags dflags, + const char *label); + +#else /* CONFIG_GPIOLIB && CONFIG_OF_GPIO */ + +struct device_node; + +static inline +struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, + const char *propname, int index, + enum gpiod_flags dflags, + const char *label) +{ + return ERR_PTR(-ENOSYS); +} + +#endif /* CONFIG_GPIOLIB && CONFIG_OF_GPIO */ + +#ifdef CONFIG_GPIOLIB +struct device_node; + +struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, + struct device_node *node, + const char *propname, int index, + enum gpiod_flags dflags, + const char *label); + +#else /* CONFIG_GPIOLIB */ + +struct device_node; + +static inline +struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, + struct device_node *node, + const char *propname, int index, + enum gpiod_flags dflags, + const char *label) +{ + return ERR_PTR(-ENOSYS); +} + +#endif /* CONFIG_GPIOLIB */ + #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS) int gpiod_export(struct gpio_desc *desc, bool direction_may_change); -- cgit v1.2.3-71-gd317 From 2838bf941b120ec846a3903db13e319368d51b08 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 30 Jul 2019 13:43:37 +0300 Subject: gpiolib-acpi: Move acpi_dev_add_driver_gpios() et al to consumer.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The API, which belongs to GPIO library, is foreign to ACPI headers. Earlier we moved out I²C out of the latter, and now it's time for acpi_dev_add_driver_gpios() et al. For time being the acpi_gpio_get_irq_resource() and acpi_dev_gpio_irq_get() are left untouched as they need more thought about. Note, it requires uninline acpi_dev_remove_driver_gpios() to keep purity of consumer.h. Cc: Pierre-Louis Bossart Cc: Liam Girdwood Cc: Jie Yang Cc: Mark Brown Cc: alsa-devel@alsa-project.org (moderated list:INTEL ASoC DRIVERS) Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20190730104337.21235-3-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib-acpi.c | 7 ++++ include/linux/acpi.h | 51 ------------------------- include/linux/gpio/consumer.h | 57 ++++++++++++++++++++++++++++ sound/soc/intel/boards/bytcht_cx2072x.c | 1 + sound/soc/intel/boards/cht_bsw_max98090_ti.c | 1 + sound/soc/intel/boards/cht_bsw_rt5672.c | 1 + 6 files changed, 67 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index d54fc6e7c8a9..fdee8afa5339 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -383,6 +383,13 @@ int acpi_dev_add_driver_gpios(struct acpi_device *adev, } EXPORT_SYMBOL_GPL(acpi_dev_add_driver_gpios); +void acpi_dev_remove_driver_gpios(struct acpi_device *adev) +{ + if (adev) + adev->driver_gpios = NULL; +} +EXPORT_SYMBOL_GPL(acpi_dev_remove_driver_gpios); + static void devm_acpi_dev_release_driver_gpios(struct device *dev, void *res) { acpi_dev_remove_driver_gpios(ACPI_COMPANION(dev)); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 9426b9aaed86..e40e1e27ed8e 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -994,62 +994,11 @@ void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const c #endif #endif -struct acpi_gpio_params { - unsigned int crs_entry_index; - unsigned int line_index; - bool active_low; -}; - -struct acpi_gpio_mapping { - const char *name; - const struct acpi_gpio_params *data; - unsigned int size; - -/* Ignore IoRestriction field */ -#define ACPI_GPIO_QUIRK_NO_IO_RESTRICTION BIT(0) -/* - * When ACPI GPIO mapping table is in use the index parameter inside it - * refers to the GPIO resource in _CRS method. That index has no - * distinction of actual type of the resource. When consumer wants to - * get GpioIo type explicitly, this quirk may be used. - */ -#define ACPI_GPIO_QUIRK_ONLY_GPIOIO BIT(1) - - unsigned int quirks; -}; - #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) -int acpi_dev_add_driver_gpios(struct acpi_device *adev, - const struct acpi_gpio_mapping *gpios); - -static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) -{ - if (adev) - adev->driver_gpios = NULL; -} - -int devm_acpi_dev_add_driver_gpios(struct device *dev, - const struct acpi_gpio_mapping *gpios); -void devm_acpi_dev_remove_driver_gpios(struct device *dev); - bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index); #else -static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, - const struct acpi_gpio_mapping *gpios) -{ - return -ENXIO; -} -static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) {} - -static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, - const struct acpi_gpio_mapping *gpios) -{ - return -ENXIO; -} -static inline void devm_acpi_dev_remove_driver_gpios(struct device *dev) {} - static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 6019d4d128c5..aac617371b60 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -602,6 +602,63 @@ struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, #endif /* CONFIG_GPIOLIB */ +struct acpi_gpio_params { + unsigned int crs_entry_index; + unsigned int line_index; + bool active_low; +}; + +struct acpi_gpio_mapping { + const char *name; + const struct acpi_gpio_params *data; + unsigned int size; + +/* Ignore IoRestriction field */ +#define ACPI_GPIO_QUIRK_NO_IO_RESTRICTION BIT(0) +/* + * When ACPI GPIO mapping table is in use the index parameter inside it + * refers to the GPIO resource in _CRS method. That index has no + * distinction of actual type of the resource. When consumer wants to + * get GpioIo type explicitly, this quirk may be used. + */ +#define ACPI_GPIO_QUIRK_ONLY_GPIOIO BIT(1) + + unsigned int quirks; +}; + +#if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_ACPI) + +struct acpi_device; + +int acpi_dev_add_driver_gpios(struct acpi_device *adev, + const struct acpi_gpio_mapping *gpios); +void acpi_dev_remove_driver_gpios(struct acpi_device *adev); + +int devm_acpi_dev_add_driver_gpios(struct device *dev, + const struct acpi_gpio_mapping *gpios); +void devm_acpi_dev_remove_driver_gpios(struct device *dev); + +#else /* CONFIG_GPIOLIB && CONFIG_ACPI */ + +struct acpi_device; + +static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, + const struct acpi_gpio_mapping *gpios) +{ + return -ENXIO; +} +static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) {} + +static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, + const struct acpi_gpio_mapping *gpios) +{ + return -ENXIO; +} +static inline void devm_acpi_dev_remove_driver_gpios(struct device *dev) {} + +#endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ + + #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS) int gpiod_export(struct gpio_desc *desc, bool direction_may_change); diff --git a/sound/soc/intel/boards/bytcht_cx2072x.c b/sound/soc/intel/boards/bytcht_cx2072x.c index 54ac2fd41925..67f06c95eec5 100644 --- a/sound/soc/intel/boards/bytcht_cx2072x.c +++ b/sound/soc/intel/boards/bytcht_cx2072x.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include diff --git a/sound/soc/intel/boards/cht_bsw_max98090_ti.c b/sound/soc/intel/boards/cht_bsw_max98090_ti.c index 33eb72545be6..05db311b579e 100644 --- a/sound/soc/intel/boards/cht_bsw_max98090_ti.c +++ b/sound/soc/intel/boards/cht_bsw_max98090_ti.c @@ -12,6 +12,7 @@ */ #include +#include #include #include #include diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c index 4977b5a65eb8..9d657421730a 100644 --- a/sound/soc/intel/boards/cht_bsw_rt5672.c +++ b/sound/soc/intel/boards/cht_bsw_rt5672.c @@ -8,6 +8,7 @@ * Mengdong Lin */ +#include #include #include #include -- cgit v1.2.3-71-gd317 From 7dcddef6f769d7e60691c732eb6d09cdb1d9df76 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 31 Jul 2019 15:29:52 +1000 Subject: cpuidle: header file stubs must be "static inline" An x86_64 allmodconfig build produces these errors: x86_64-linux-gnu-ld: kernel/sched/core.o: in function `cpuidle_poll_time': core.c:(.text+0x230): multiple definition of `cpuidle_poll_time'; arch/x86/= kernel/process.o:process.c:(.text+0xc0): first defined here (and more) Fixes: 259231a04561 ("cpuidle: add poll_limit_ns to cpuidle_device structure") Signed-off-by: Stephen Rothwell Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index ba535a1a47d5..1a9f54eb3aa1 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -170,7 +170,7 @@ static inline int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) {return -ENODEV; } static inline void cpuidle_reflect(struct cpuidle_device *dev, int index) { } -extern u64 cpuidle_poll_time(struct cpuidle_driver *drv, +static inline u64 cpuidle_poll_time(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return 0; } static inline int cpuidle_register_driver(struct cpuidle_driver *drv) -- cgit v1.2.3-71-gd317 From c1a280b68d4e6b6db4a65aa7865c22d8789ddf09 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Jul 2019 23:19:37 +0200 Subject: sched/preempt: Use CONFIG_PREEMPTION where appropriate CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Switch the preemption code, scheduler and init task over to use CONFIG_PREEMPTION. That's the first step towards RT in that area. The more complex changes are coming separately. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Paolo Bonzini Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Steven Rostedt Link: http://lkml.kernel.org/r/20190726212124.117528401@linutronix.de Signed-off-by: Ingo Molnar --- include/asm-generic/preempt.h | 4 ++-- include/linux/preempt.h | 6 +++--- include/linux/sched.h | 6 +++--- init/init_task.c | 2 +- init/main.c | 2 +- kernel/sched/core.c | 14 +++++++------- kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 4 ++-- 8 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h index c3046c920063..d683f5e6d791 100644 --- a/include/asm-generic/preempt.h +++ b/include/asm-generic/preempt.h @@ -78,11 +78,11 @@ static __always_inline bool should_resched(int preempt_offset) tif_need_resched()); } -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule(void); #define __preempt_schedule() preempt_schedule() extern asmlinkage void preempt_schedule_notrace(void); #define __preempt_schedule_notrace() preempt_schedule_notrace() -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ #endif /* __ASM_PREEMPT_H */ diff --git a/include/linux/preempt.h b/include/linux/preempt.h index dd92b1a93919..bbb68dba37cc 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -182,7 +182,7 @@ do { \ #define preemptible() (preempt_count() == 0 && !irqs_disabled()) -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION #define preempt_enable() \ do { \ barrier(); \ @@ -203,7 +203,7 @@ do { \ __preempt_schedule(); \ } while (0) -#else /* !CONFIG_PREEMPT */ +#else /* !CONFIG_PREEMPTION */ #define preempt_enable() \ do { \ barrier(); \ @@ -217,7 +217,7 @@ do { \ } while (0) #define preempt_check_resched() do { } while (0) -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ #define preempt_disable_notrace() \ do { \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 9f51932bd543..6947516a2d3e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1767,7 +1767,7 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION extern int _cond_resched(void); #else static inline int _cond_resched(void) { return 0; } @@ -1796,12 +1796,12 @@ static inline void cond_resched_rcu(void) /* * Does a critical section need to be broken due to another - * task waiting?: (technically does not depend on CONFIG_PREEMPT, + * task waiting?: (technically does not depend on CONFIG_PREEMPTION, * but a general need for low latency) */ static inline int spin_needbreak(spinlock_t *lock) { -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION return spin_is_contended(lock); #else return 0; diff --git a/init/init_task.c b/init/init_task.c index 7ab773b9b3cd..bfe06c53b14e 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -174,7 +174,7 @@ struct task_struct init_task #ifdef CONFIG_FUNCTION_GRAPH_TRACER .ret_stack = NULL, #endif -#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPT) +#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION) .trace_recursion = 0, #endif #ifdef CONFIG_LIVEPATCH diff --git a/init/main.c b/init/main.c index 96f8d5af52d6..653693da8da6 100644 --- a/init/main.c +++ b/init/main.c @@ -433,7 +433,7 @@ noinline void __ref rest_init(void) /* * Enable might_sleep() and smp_processor_id() checks. - * They cannot be enabled earlier because with CONFIG_PREEMPT=y + * They cannot be enabled earlier because with CONFIG_PREEMPTION=y * kernel_thread() would trigger might_sleep() splats. With * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled * already, but it's stuck on the kthreadd_done completion. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2b037f195473..604a5e137efe 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3581,7 +3581,7 @@ static inline void sched_tick_start(int cpu) { } static inline void sched_tick_stop(int cpu) { } #endif -#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ +#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_TRACE_PREEMPT_TOGGLE)) /* * If the value passed in is equal to the current preempt count @@ -3782,7 +3782,7 @@ again: * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets * called on the nearest possible occasion: * - * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * - If the kernel is preemptible (CONFIG_PREEMPTION=y): * * - in syscall or exception context, at the next outmost * preempt_enable(). (this might be as soon as the wake_up()'s @@ -3791,7 +3791,7 @@ again: * - in IRQ context, return from interrupt-handler to * preemptible context * - * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set) * then at the next: * * - cond_resched() call @@ -4033,7 +4033,7 @@ static void __sched notrace preempt_schedule_common(void) } while (need_resched()); } -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * this is the entry point to schedule() from in-kernel preemption * off of preempt_enable. Kernel preemptions off return from interrupt @@ -4105,7 +4105,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) } EXPORT_SYMBOL_GPL(preempt_schedule_notrace); -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ /* * this is the entry point to schedule() from kernel preemption @@ -5416,7 +5416,7 @@ SYSCALL_DEFINE0(sched_yield) return 0; } -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION int __sched _cond_resched(void) { if (should_resched(0)) { @@ -5433,7 +5433,7 @@ EXPORT_SYMBOL(_cond_resched); * __cond_resched_lock() - if a reschedule is pending, drop the given lock, * call schedule, and on return reacquire the lock. * - * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level * operations here to prevent schedule() from being called twice (once via * spin_unlock(), once by hand). */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bc9cfeaac8bd..aff9d76d8d65 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7430,7 +7430,7 @@ static int detach_tasks(struct lb_env *env) detached++; env->imbalance -= load; -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * NEWIDLE balancing is a source of latency, so preemptible * kernels will stop after the first task is detached to minimize diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 802b1f3405f2..f2ce6ba1c5d5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1943,7 +1943,7 @@ unsigned long arch_scale_freq_capacity(int cpu) #endif #ifdef CONFIG_SMP -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION static inline void double_rq_lock(struct rq *rq1, struct rq *rq2); @@ -1995,7 +1995,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) return ret; } -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ /* * double_lock_balance - lock the busiest runqueue, this_rq is locked already. -- cgit v1.2.3-71-gd317 From 01b1d88b09824bea1a75b0bac04dcf50d9893875 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Jul 2019 23:19:38 +0200 Subject: rcu: Use CONFIG_PREEMPTION CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Switch the conditionals in RCU to use CONFIG_PREEMPTION. That's the first step towards RCU on RT. The further tweaks are work in progress. This neither touches the selftest bits which need a closer look by Paul. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Paolo Bonzini Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Steven Rostedt Link: http://lkml.kernel.org/r/20190726212124.210156346@linutronix.de Signed-off-by: Ingo Molnar --- arch/Kconfig | 2 +- include/linux/rcupdate.h | 2 +- include/linux/rcutree.h | 2 +- include/linux/torture.h | 2 +- kernel/rcu/Kconfig | 8 ++++---- kernel/rcu/tree.c | 6 +++--- kernel/rcu/tree_stall.h | 6 +++--- kernel/trace/Kconfig | 2 +- 8 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index a7b57dd42c26..c7efbc018f4f 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -103,7 +103,7 @@ config STATIC_KEYS_SELFTEST config OPTPROBES def_bool y depends on KPROBES && HAVE_OPTPROBES - select TASKS_RCU if PREEMPT + select TASKS_RCU if PREEMPTION config KPROBES_ON_FTRACE def_bool y diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8f7167478c1d..c4f76a310443 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -578,7 +578,7 @@ do { \ * * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. - * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPT + * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 735601ac27d3..18b1ed9864b0 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -53,7 +53,7 @@ void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; void rcu_end_inkernel_boot(void); bool rcu_is_watching(void); -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION void rcu_all_qs(void); #endif diff --git a/include/linux/torture.h b/include/linux/torture.h index a620118385bb..6241f59e2d6f 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -86,7 +86,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #define torture_stop_kthread(n, tp) \ _torture_stop_kthread("Stopping " #n " task", &(tp)) -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION #define torture_preempt_schedule() preempt_schedule() #else #define torture_preempt_schedule() diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index 480edf328b51..7644eda17d62 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -7,7 +7,7 @@ menu "RCU Subsystem" config TREE_RCU bool - default y if !PREEMPT && SMP + default y if !PREEMPTION && SMP help This option selects the RCU implementation that is designed for very large SMP system with hundreds or @@ -16,7 +16,7 @@ config TREE_RCU config PREEMPT_RCU bool - default y if PREEMPT + default y if PREEMPTION help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -28,7 +28,7 @@ config PREEMPT_RCU config TINY_RCU bool - default y if !PREEMPT && !SMP + default y if !PREEMPTION && !SMP help This option selects the RCU implementation that is designed for UP systems from which real-time response @@ -70,7 +70,7 @@ config TREE_SRCU This option selects the full-fledged version of SRCU. config TASKS_RCU - def_bool PREEMPT + def_bool PREEMPTION select SRCU help This option enables a task-based RCU implementation that uses diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a14e5fbbea46..5962636502bc 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1881,7 +1881,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)) || + if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPTION)) || WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2205,7 +2205,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) mask = 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask == 0) { - if (!IS_ENABLED(CONFIG_PREEMPT) || + if (!IS_ENABLED(CONFIG_PREEMPTION) || rcu_preempt_blocked_readers_cgp(rnp)) { /* * No point in scanning bits because they @@ -2622,7 +2622,7 @@ static int rcu_blocking_is_gp(void) { int ret; - if (IS_ENABLED(CONFIG_PREEMPT)) + if (IS_ENABLED(CONFIG_PREEMPTION)) return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE; might_sleep(); /* Check for RCU read-side critical section. */ preempt_disable(); diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 065183391f75..9b92bf18b737 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -163,7 +163,7 @@ static void rcu_iw_handler(struct irq_work *iwp) // // Printing RCU CPU stall warnings -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * Dump detailed information for all tasks blocking the current RCU @@ -215,7 +215,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return ndetected; } -#else /* #ifdef CONFIG_PREEMPT */ +#else /* #ifdef CONFIG_PREEMPTION */ /* * Because preemptible RCU does not exist, we never have to check for @@ -233,7 +233,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) { return 0; } -#endif /* #else #ifdef CONFIG_PREEMPT */ +#endif /* #else #ifdef CONFIG_PREEMPTION */ /* * Dump stacks of all tasks running on stalled CPUs. First try using diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 98da8998c25c..d2c1fe0b451d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -146,7 +146,7 @@ config FUNCTION_TRACER select GENERIC_TRACER select CONTEXT_SWITCH_TRACER select GLOB - select TASKS_RCU if PREEMPT + select TASKS_RCU if PREEMPTION help Enable the kernel to trace every kernel function. This is done by using a compiler feature to insert a small, 5-byte No-Operation -- cgit v1.2.3-71-gd317 From 27972765bd0410fc2ef5e86a41de17c71440a2dd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 26 Jul 2019 23:19:39 +0200 Subject: locking/spinlocks: Use CONFIG_PREEMPTION CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Adjust the comments in the locking code. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Paolo Bonzini Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Steven Rostedt Link: http://lkml.kernel.org/r/20190726212124.302995288@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/spinlock.h | 2 +- include/linux/spinlock_api_smp.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index ed7c4d6b8235..031ce8617df8 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -214,7 +214,7 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) /* * Define the various spin_lock methods. Note we define these - * regardless of whether CONFIG_SMP or CONFIG_PREEMPT are set. The + * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 42dfab89e740..b762eaba4cdf 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -96,7 +96,7 @@ static inline int __raw_spin_trylock(raw_spinlock_t *lock) /* * If lockdep is enabled then we use the non-preemption spin-ops - * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are + * even on CONFIG_PREEMPTION, because lockdep assumes that interrupts are * not re-enabled during lock-acquire (which the preempt-spin-ops do): */ #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC) -- cgit v1.2.3-71-gd317 From eaf7b46083a7e341a23ab3d6042e0ccc115b0914 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 26 Jul 2019 09:51:12 -0300 Subject: docs: thermal: add it to the driver API The file contents mostly describes driver internals. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Jonathan Corbet --- Documentation/driver-api/index.rst | 1 + .../driver-api/thermal/cpu-cooling-api.rst | 107 +++ .../driver-api/thermal/exynos_thermal.rst | 90 +++ .../thermal/exynos_thermal_emulation.rst | 61 ++ Documentation/driver-api/thermal/index.rst | 18 + .../driver-api/thermal/intel_powerclamp.rst | 320 +++++++++ .../driver-api/thermal/nouveau_thermal.rst | 96 +++ .../driver-api/thermal/power_allocator.rst | 271 +++++++ Documentation/driver-api/thermal/sysfs-api.rst | 798 +++++++++++++++++++++ .../thermal/x86_pkg_temperature_thermal.rst | 55 ++ Documentation/thermal/cpu-cooling-api.rst | 107 --- Documentation/thermal/exynos_thermal.rst | 90 --- Documentation/thermal/exynos_thermal_emulation.rst | 61 -- Documentation/thermal/index.rst | 18 - Documentation/thermal/intel_powerclamp.rst | 320 --------- Documentation/thermal/nouveau_thermal.rst | 96 --- Documentation/thermal/power_allocator.rst | 271 ------- Documentation/thermal/sysfs-api.rst | 798 --------------------- .../thermal/x86_pkg_temperature_thermal.rst | 55 -- MAINTAINERS | 2 +- include/linux/thermal.h | 4 +- 21 files changed, 1820 insertions(+), 1819 deletions(-) create mode 100644 Documentation/driver-api/thermal/cpu-cooling-api.rst create mode 100644 Documentation/driver-api/thermal/exynos_thermal.rst create mode 100644 Documentation/driver-api/thermal/exynos_thermal_emulation.rst create mode 100644 Documentation/driver-api/thermal/index.rst create mode 100644 Documentation/driver-api/thermal/intel_powerclamp.rst create mode 100644 Documentation/driver-api/thermal/nouveau_thermal.rst create mode 100644 Documentation/driver-api/thermal/power_allocator.rst create mode 100644 Documentation/driver-api/thermal/sysfs-api.rst create mode 100644 Documentation/driver-api/thermal/x86_pkg_temperature_thermal.rst delete mode 100644 Documentation/thermal/cpu-cooling-api.rst delete mode 100644 Documentation/thermal/exynos_thermal.rst delete mode 100644 Documentation/thermal/exynos_thermal_emulation.rst delete mode 100644 Documentation/thermal/index.rst delete mode 100644 Documentation/thermal/intel_powerclamp.rst delete mode 100644 Documentation/thermal/nouveau_thermal.rst delete mode 100644 Documentation/thermal/power_allocator.rst delete mode 100644 Documentation/thermal/sysfs-api.rst delete mode 100644 Documentation/thermal/x86_pkg_temperature_thermal.rst (limited to 'include/linux') diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index d12a80f386a6..37ac052ded85 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -65,6 +65,7 @@ available subsections can be seen below. dmaengine/index slimbus soundwire/index + thermal/index fpga/index acpi/index backlight/lp855x-driver.rst diff --git a/Documentation/driver-api/thermal/cpu-cooling-api.rst b/Documentation/driver-api/thermal/cpu-cooling-api.rst new file mode 100644 index 000000000000..645d914c45a6 --- /dev/null +++ b/Documentation/driver-api/thermal/cpu-cooling-api.rst @@ -0,0 +1,107 @@ +======================= +CPU cooling APIs How To +======================= + +Written by Amit Daniel Kachhap + +Updated: 6 Jan 2015 + +Copyright (c) 2012 Samsung Electronics Co., Ltd(http://www.samsung.com) + +0. Introduction +=============== + +The generic cpu cooling(freq clipping) provides registration/unregistration APIs +to the caller. The binding of the cooling devices to the trip point is left for +the user. The registration APIs returns the cooling device pointer. + +1. cpu cooling APIs +=================== + +1.1 cpufreq registration/unregistration APIs +-------------------------------------------- + + :: + + struct thermal_cooling_device + *cpufreq_cooling_register(struct cpumask *clip_cpus) + + This interface function registers the cpufreq cooling device with the name + "thermal-cpufreq-%x". This api can support multiple instances of cpufreq + cooling devices. + + clip_cpus: + cpumask of cpus where the frequency constraints will happen. + + :: + + struct thermal_cooling_device + *of_cpufreq_cooling_register(struct cpufreq_policy *policy) + + This interface function registers the cpufreq cooling device with + the name "thermal-cpufreq-%x" linking it with a device tree node, in + order to bind it via the thermal DT code. This api can support multiple + instances of cpufreq cooling devices. + + policy: + CPUFreq policy. + + + :: + + void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) + + This interface function unregisters the "thermal-cpufreq-%x" cooling device. + + cdev: Cooling device pointer which has to be unregistered. + +2. Power models +=============== + +The power API registration functions provide a simple power model for +CPUs. The current power is calculated as dynamic power (static power isn't +supported currently). This power model requires that the operating-points of +the CPUs are registered using the kernel's opp library and the +`cpufreq_frequency_table` is assigned to the `struct device` of the +cpu. If you are using CONFIG_CPUFREQ_DT then the +`cpufreq_frequency_table` should already be assigned to the cpu +device. + +The dynamic power consumption of a processor depends on many factors. +For a given processor implementation the primary factors are: + +- The time the processor spends running, consuming dynamic power, as + compared to the time in idle states where dynamic consumption is + negligible. Herein we refer to this as 'utilisation'. +- The voltage and frequency levels as a result of DVFS. The DVFS + level is a dominant factor governing power consumption. +- In running time the 'execution' behaviour (instruction types, memory + access patterns and so forth) causes, in most cases, a second order + variation. In pathological cases this variation can be significant, + but typically it is of a much lesser impact than the factors above. + +A high level dynamic power consumption model may then be represented as:: + + Pdyn = f(run) * Voltage^2 * Frequency * Utilisation + +f(run) here represents the described execution behaviour and its +result has a units of Watts/Hz/Volt^2 (this often expressed in +mW/MHz/uVolt^2) + +The detailed behaviour for f(run) could be modelled on-line. However, +in practice, such an on-line model has dependencies on a number of +implementation specific processor support and characterisation +factors. Therefore, in initial implementation that contribution is +represented as a constant coefficient. This is a simplification +consistent with the relative contribution to overall power variation. + +In this simplified representation our model becomes:: + + Pdyn = Capacitance * Voltage^2 * Frequency * Utilisation + +Where `capacitance` is a constant that represents an indicative +running time dynamic power coefficient in fundamental units of +mW/MHz/uVolt^2. Typical values for mobile CPUs might lie in range +from 100 to 500. For reference, the approximate values for the SoC in +ARM's Juno Development Platform are 530 for the Cortex-A57 cluster and +140 for the Cortex-A53 cluster. diff --git a/Documentation/driver-api/thermal/exynos_thermal.rst b/Documentation/driver-api/thermal/exynos_thermal.rst new file mode 100644 index 000000000000..5bd556566c70 --- /dev/null +++ b/Documentation/driver-api/thermal/exynos_thermal.rst @@ -0,0 +1,90 @@ +======================== +Kernel driver exynos_tmu +======================== + +Supported chips: + +* ARM SAMSUNG EXYNOS4, EXYNOS5 series of SoC + + Datasheet: Not publicly available + +Authors: Donggeun Kim +Authors: Amit Daniel + +TMU controller Description: +--------------------------- + +This driver allows to read temperature inside SAMSUNG EXYNOS4/5 series of SoC. + +The chip only exposes the measured 8-bit temperature code value +through a register. +Temperature can be taken from the temperature code. +There are three equations converting from temperature to temperature code. + +The three equations are: + 1. Two point trimming:: + + Tc = (T - 25) * (TI2 - TI1) / (85 - 25) + TI1 + + 2. One point trimming:: + + Tc = T + TI1 - 25 + + 3. No trimming:: + + Tc = T + 50 + + Tc: + Temperature code, T: Temperature, + TI1: + Trimming info for 25 degree Celsius (stored at TRIMINFO register) + Temperature code measured at 25 degree Celsius which is unchanged + TI2: + Trimming info for 85 degree Celsius (stored at TRIMINFO register) + Temperature code measured at 85 degree Celsius which is unchanged + +TMU(Thermal Management Unit) in EXYNOS4/5 generates interrupt +when temperature exceeds pre-defined levels. +The maximum number of configurable threshold is five. +The threshold levels are defined as follows:: + + Level_0: current temperature > trigger_level_0 + threshold + Level_1: current temperature > trigger_level_1 + threshold + Level_2: current temperature > trigger_level_2 + threshold + Level_3: current temperature > trigger_level_3 + threshold + +The threshold and each trigger_level are set +through the corresponding registers. + +When an interrupt occurs, this driver notify kernel thermal framework +with the function exynos_report_trigger. +Although an interrupt condition for level_0 can be set, +it can be used to synchronize the cooling action. + +TMU driver description: +----------------------- + +The exynos thermal driver is structured as:: + + Kernel Core thermal framework + (thermal_core.c, step_wise.c, cpu_cooling.c) + ^ + | + | + TMU configuration data -----> TMU Driver <----> Exynos Core thermal wrapper + (exynos_tmu_data.c) (exynos_tmu.c) (exynos_thermal_common.c) + (exynos_tmu_data.h) (exynos_tmu.h) (exynos_thermal_common.h) + +a) TMU configuration data: + This consist of TMU register offsets/bitfields + described through structure exynos_tmu_registers. Also several + other platform data (struct exynos_tmu_platform_data) members + are used to configure the TMU. +b) TMU driver: + This component initialises the TMU controller and sets different + thresholds. It invokes core thermal implementation with the call + exynos_report_trigger. +c) Exynos Core thermal wrapper: + This provides 3 wrapper function to use the + Kernel core thermal framework. They are exynos_unregister_thermal, + exynos_register_thermal and exynos_report_trigger. diff --git a/Documentation/driver-api/thermal/exynos_thermal_emulation.rst b/Documentation/driver-api/thermal/exynos_thermal_emulation.rst new file mode 100644 index 000000000000..c21d10838bc5 --- /dev/null +++ b/Documentation/driver-api/thermal/exynos_thermal_emulation.rst @@ -0,0 +1,61 @@ +===================== +Exynos Emulation Mode +===================== + +Copyright (C) 2012 Samsung Electronics + +Written by Jonghwa Lee + +Description +----------- + +Exynos 4x12 (4212, 4412) and 5 series provide emulation mode for thermal +management unit. Thermal emulation mode supports software debug for +TMU's operation. User can set temperature manually with software code +and TMU will read current temperature from user value not from sensor's +value. + +Enabling CONFIG_THERMAL_EMULATION option will make this support +available. When it's enabled, sysfs node will be created as +/sys/devices/virtual/thermal/thermal_zone'zone id'/emul_temp. + +The sysfs node, 'emul_node', will contain value 0 for the initial state. +When you input any temperature you want to update to sysfs node, it +automatically enable emulation mode and current temperature will be +changed into it. + +(Exynos also supports user changeable delay time which would be used to +delay of changing temperature. However, this node only uses same delay +of real sensing time, 938us.) + +Exynos emulation mode requires synchronous of value changing and +enabling. It means when you want to update the any value of delay or +next temperature, then you have to enable emulation mode at the same +time. (Or you have to keep the mode enabling.) If you don't, it fails to +change the value to updated one and just use last succeessful value +repeatedly. That's why this node gives users the right to change +termerpature only. Just one interface makes it more simply to use. + +Disabling emulation mode only requires writing value 0 to sysfs node. + +:: + + + TEMP 120 | + | + 100 | + | + 80 | + | +----------- + 60 | | | + | +-------------| | + 40 | | | | + | | | | + 20 | | | +---------- + | | | | | + 0 |______________|_____________|__________|__________|_________ + A A A A TIME + |<----->| |<----->| |<----->| | + | 938us | | | | | | + emulation : 0 50 | 70 | 20 | 0 + current temp: sensor 50 70 20 sensor diff --git a/Documentation/driver-api/thermal/index.rst b/Documentation/driver-api/thermal/index.rst new file mode 100644 index 000000000000..5ba61d19c6ae --- /dev/null +++ b/Documentation/driver-api/thermal/index.rst @@ -0,0 +1,18 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======= +Thermal +======= + +.. toctree:: + :maxdepth: 1 + + cpu-cooling-api + sysfs-api + power_allocator + + exynos_thermal + exynos_thermal_emulation + intel_powerclamp + nouveau_thermal + x86_pkg_temperature_thermal diff --git a/Documentation/driver-api/thermal/intel_powerclamp.rst b/Documentation/driver-api/thermal/intel_powerclamp.rst new file mode 100644 index 000000000000..3f6dfb0b3ea6 --- /dev/null +++ b/Documentation/driver-api/thermal/intel_powerclamp.rst @@ -0,0 +1,320 @@ +======================= +Intel Powerclamp Driver +======================= + +By: + - Arjan van de Ven + - Jacob Pan + +.. Contents: + + (*) Introduction + - Goals and Objectives + + (*) Theory of Operation + - Idle Injection + - Calibration + + (*) Performance Analysis + - Effectiveness and Limitations + - Power vs Performance + - Scalability + - Calibration + - Comparison with Alternative Techniques + + (*) Usage and Interfaces + - Generic Thermal Layer (sysfs) + - Kernel APIs (TBD) + +INTRODUCTION +============ + +Consider the situation where a system’s power consumption must be +reduced at runtime, due to power budget, thermal constraint, or noise +level, and where active cooling is not preferred. Software managed +passive power reduction must be performed to prevent the hardware +actions that are designed for catastrophic scenarios. + +Currently, P-states, T-states (clock modulation), and CPU offlining +are used for CPU throttling. + +On Intel CPUs, C-states provide effective power reduction, but so far +they’re only used opportunistically, based on workload. With the +development of intel_powerclamp driver, the method of synchronizing +idle injection across all online CPU threads was introduced. The goal +is to achieve forced and controllable C-state residency. + +Test/Analysis has been made in the areas of power, performance, +scalability, and user experience. In many cases, clear advantage is +shown over taking the CPU offline or modulating the CPU clock. + + +THEORY OF OPERATION +=================== + +Idle Injection +-------------- + +On modern Intel processors (Nehalem or later), package level C-state +residency is available in MSRs, thus also available to the kernel. + +These MSRs are:: + + #define MSR_PKG_C2_RESIDENCY 0x60D + #define MSR_PKG_C3_RESIDENCY 0x3F8 + #define MSR_PKG_C6_RESIDENCY 0x3F9 + #define MSR_PKG_C7_RESIDENCY 0x3FA + +If the kernel can also inject idle time to the system, then a +closed-loop control system can be established that manages package +level C-state. The intel_powerclamp driver is conceived as such a +control system, where the target set point is a user-selected idle +ratio (based on power reduction), and the error is the difference +between the actual package level C-state residency ratio and the target idle +ratio. + +Injection is controlled by high priority kernel threads, spawned for +each online CPU. + +These kernel threads, with SCHED_FIFO class, are created to perform +clamping actions of controlled duty ratio and duration. Each per-CPU +thread synchronizes its idle time and duration, based on the rounding +of jiffies, so accumulated errors can be prevented to avoid a jittery +effect. Threads are also bound to the CPU such that they cannot be +migrated, unless the CPU is taken offline. In this case, threads +belong to the offlined CPUs will be terminated immediately. + +Running as SCHED_FIFO and relatively high priority, also allows such +scheme to work for both preemptable and non-preemptable kernels. +Alignment of idle time around jiffies ensures scalability for HZ +values. This effect can be better visualized using a Perf timechart. +The following diagram shows the behavior of kernel thread +kidle_inject/cpu. During idle injection, it runs monitor/mwait idle +for a given "duration", then relinquishes the CPU to other tasks, +until the next time interval. + +The NOHZ schedule tick is disabled during idle time, but interrupts +are not masked. Tests show that the extra wakeups from scheduler tick +have a dramatic impact on the effectiveness of the powerclamp driver +on large scale systems (Westmere system with 80 processors). + +:: + + CPU0 + ____________ ____________ + kidle_inject/0 | sleep | mwait | sleep | + _________| |________| |_______ + duration + CPU1 + ____________ ____________ + kidle_inject/1 | sleep | mwait | sleep | + _________| |________| |_______ + ^ + | + | + roundup(jiffies, interval) + +Only one CPU is allowed to collect statistics and update global +control parameters. This CPU is referred to as the controlling CPU in +this document. The controlling CPU is elected at runtime, with a +policy that favors BSP, taking into account the possibility of a CPU +hot-plug. + +In terms of dynamics of the idle control system, package level idle +time is considered largely as a non-causal system where its behavior +cannot be based on the past or current input. Therefore, the +intel_powerclamp driver attempts to enforce the desired idle time +instantly as given input (target idle ratio). After injection, +powerclamp monitors the actual idle for a given time window and adjust +the next injection accordingly to avoid over/under correction. + +When used in a causal control system, such as a temperature control, +it is up to the user of this driver to implement algorithms where +past samples and outputs are included in the feedback. For example, a +PID-based thermal controller can use the powerclamp driver to +maintain a desired target temperature, based on integral and +derivative gains of the past samples. + + + +Calibration +----------- +During scalability testing, it is observed that synchronized actions +among CPUs become challenging as the number of cores grows. This is +also true for the ability of a system to enter package level C-states. + +To make sure the intel_powerclamp driver scales well, online +calibration is implemented. The goals for doing such a calibration +are: + +a) determine the effective range of idle injection ratio +b) determine the amount of compensation needed at each target ratio + +Compensation to each target ratio consists of two parts: + + a) steady state error compensation + This is to offset the error occurring when the system can + enter idle without extra wakeups (such as external interrupts). + + b) dynamic error compensation + When an excessive amount of wakeups occurs during idle, an + additional idle ratio can be added to quiet interrupts, by + slowing down CPU activities. + +A debugfs file is provided for the user to examine compensation +progress and results, such as on a Westmere system:: + + [jacob@nex01 ~]$ cat + /sys/kernel/debug/intel_powerclamp/powerclamp_calib + controlling cpu: 0 + pct confidence steady dynamic (compensation) + 0 0 0 0 + 1 1 0 0 + 2 1 1 0 + 3 3 1 0 + 4 3 1 0 + 5 3 1 0 + 6 3 1 0 + 7 3 1 0 + 8 3 1 0 + ... + 30 3 2 0 + 31 3 2 0 + 32 3 1 0 + 33 3 2 0 + 34 3 1 0 + 35 3 2 0 + 36 3 1 0 + 37 3 2 0 + 38 3 1 0 + 39 3 2 0 + 40 3 3 0 + 41 3 1 0 + 42 3 2 0 + 43 3 1 0 + 44 3 1 0 + 45 3 2 0 + 46 3 3 0 + 47 3 0 0 + 48 3 2 0 + 49 3 3 0 + +Calibration occurs during runtime. No offline method is available. +Steady state compensation is used only when confidence levels of all +adjacent ratios have reached satisfactory level. A confidence level +is accumulated based on clean data collected at runtime. Data +collected during a period without extra interrupts is considered +clean. + +To compensate for excessive amounts of wakeup during idle, additional +idle time is injected when such a condition is detected. Currently, +we have a simple algorithm to double the injection ratio. A possible +enhancement might be to throttle the offending IRQ, such as delaying +EOI for level triggered interrupts. But it is a challenge to be +non-intrusive to the scheduler or the IRQ core code. + + +CPU Online/Offline +------------------ +Per-CPU kernel threads are started/stopped upon receiving +notifications of CPU hotplug activities. The intel_powerclamp driver +keeps track of clamping kernel threads, even after they are migrated +to other CPUs, after a CPU offline event. + + +Performance Analysis +==================== +This section describes the general performance data collected on +multiple systems, including Westmere (80P) and Ivy Bridge (4P, 8P). + +Effectiveness and Limitations +----------------------------- +The maximum range that idle injection is allowed is capped at 50 +percent. As mentioned earlier, since interrupts are allowed during +forced idle time, excessive interrupts could result in less +effectiveness. The extreme case would be doing a ping -f to generated +flooded network interrupts without much CPU acknowledgement. In this +case, little can be done from the idle injection threads. In most +normal cases, such as scp a large file, applications can be throttled +by the powerclamp driver, since slowing down the CPU also slows down +network protocol processing, which in turn reduces interrupts. + +When control parameters change at runtime by the controlling CPU, it +may take an additional period for the rest of the CPUs to catch up +with the changes. During this time, idle injection is out of sync, +thus not able to enter package C- states at the expected ratio. But +this effect is minor, in that in most cases change to the target +ratio is updated much less frequently than the idle injection +frequency. + +Scalability +----------- +Tests also show a minor, but measurable, difference between the 4P/8P +Ivy Bridge system and the 80P Westmere server under 50% idle ratio. +More compensation is needed on Westmere for the same amount of +target idle ratio. The compensation also increases as the idle ratio +gets larger. The above reason constitutes the need for the +calibration code. + +On the IVB 8P system, compared to an offline CPU, powerclamp can +achieve up to 40% better performance per watt. (measured by a spin +counter summed over per CPU counting threads spawned for all running +CPUs). + +Usage and Interfaces +==================== +The powerclamp driver is registered to the generic thermal layer as a +cooling device. Currently, it’s not bound to any thermal zones:: + + jacob@chromoly:/sys/class/thermal/cooling_device14$ grep . * + cur_state:0 + max_state:50 + type:intel_powerclamp + +cur_state allows user to set the desired idle percentage. Writing 0 to +cur_state will stop idle injection. Writing a value between 1 and +max_state will start the idle injection. Reading cur_state returns the +actual and current idle percentage. This may not be the same value +set by the user in that current idle percentage depends on workload +and includes natural idle. When idle injection is disabled, reading +cur_state returns value -1 instead of 0 which is to avoid confusing +100% busy state with the disabled state. + +Example usage: +- To inject 25% idle time:: + + $ sudo sh -c "echo 25 > /sys/class/thermal/cooling_device80/cur_state + +If the system is not busy and has more than 25% idle time already, +then the powerclamp driver will not start idle injection. Using Top +will not show idle injection kernel threads. + +If the system is busy (spin test below) and has less than 25% natural +idle time, powerclamp kernel threads will do idle injection. Forced +idle time is accounted as normal idle in that common code path is +taken as the idle task. + +In this example, 24.1% idle is shown. This helps the system admin or +user determine the cause of slowdown, when a powerclamp driver is in action:: + + + Tasks: 197 total, 1 running, 196 sleeping, 0 stopped, 0 zombie + Cpu(s): 71.2%us, 4.7%sy, 0.0%ni, 24.1%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st + Mem: 3943228k total, 1689632k used, 2253596k free, 74960k buffers + Swap: 4087804k total, 0k used, 4087804k free, 945336k cached + + PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND + 3352 jacob 20 0 262m 644 428 S 286 0.0 0:17.16 spin + 3341 root -51 0 0 0 0 D 25 0.0 0:01.62 kidle_inject/0 + 3344 root -51 0 0 0 0 D 25 0.0 0:01.60 kidle_inject/3 + 3342 root -51 0 0 0 0 D 25 0.0 0:01.61 kidle_inject/1 + 3343 root -51 0 0 0 0 D 25 0.0 0:01.60 kidle_inject/2 + 2935 jacob 20 0 696m 125m 35m S 5 3.3 0:31.11 firefox + 1546 root 20 0 158m 20m 6640 S 3 0.5 0:26.97 Xorg + 2100 jacob 20 0 1223m 88m 30m S 3 2.3 0:23.68 compiz + +Tests have shown that by using the powerclamp driver as a cooling +device, a PID based userspace thermal controller can manage to +control CPU temperature effectively, when no other thermal influence +is added. For example, a UltraBook user can compile the kernel under +certain temperature (below most active trip points). diff --git a/Documentation/driver-api/thermal/nouveau_thermal.rst b/Documentation/driver-api/thermal/nouveau_thermal.rst new file mode 100644 index 000000000000..37255fd6735d --- /dev/null +++ b/Documentation/driver-api/thermal/nouveau_thermal.rst @@ -0,0 +1,96 @@ +===================== +Kernel driver nouveau +===================== + +Supported chips: + +* NV43+ + +Authors: Martin Peres (mupuf) + +Description +----------- + +This driver allows to read the GPU core temperature, drive the GPU fan and +set temperature alarms. + +Currently, due to the absence of in-kernel API to access HWMON drivers, Nouveau +cannot access any of the i2c external monitoring chips it may find. If you +have one of those, temperature and/or fan management through Nouveau's HWMON +interface is likely not to work. This document may then not cover your situation +entirely. + +Temperature management +---------------------- + +Temperature is exposed under as a read-only HWMON attribute temp1_input. + +In order to protect the GPU from overheating, Nouveau supports 4 configurable +temperature thresholds: + + * Fan_boost: + Fan speed is set to 100% when reaching this temperature; + * Downclock: + The GPU will be downclocked to reduce its power dissipation; + * Critical: + The GPU is put on hold to further lower power dissipation; + * Shutdown: + Shut the computer down to protect your GPU. + +WARNING: + Some of these thresholds may not be used by Nouveau depending + on your chipset. + +The default value for these thresholds comes from the GPU's vbios. These +thresholds can be configured thanks to the following HWMON attributes: + + * Fan_boost: temp1_auto_point1_temp and temp1_auto_point1_temp_hyst; + * Downclock: temp1_max and temp1_max_hyst; + * Critical: temp1_crit and temp1_crit_hyst; + * Shutdown: temp1_emergency and temp1_emergency_hyst. + +NOTE: Remember that the values are stored as milli degrees Celsius. Don't forget +to multiply! + +Fan management +-------------- + +Not all cards have a drivable fan. If you do, then the following HWMON +attributes should be available: + + * pwm1_enable: + Current fan management mode (NONE, MANUAL or AUTO); + * pwm1: + Current PWM value (power percentage); + * pwm1_min: + The minimum PWM speed allowed; + * pwm1_max: + The maximum PWM speed allowed (bypassed when hitting Fan_boost); + +You may also have the following attribute: + + * fan1_input: + Speed in RPM of your fan. + +Your fan can be driven in different modes: + + * 0: The fan is left untouched; + * 1: The fan can be driven in manual (use pwm1 to change the speed); + * 2; The fan is driven automatically depending on the temperature. + +NOTE: + Be sure to use the manual mode if you want to drive the fan speed manually + +NOTE2: + When operating in manual mode outside the vbios-defined + [PWM_min, PWM_max] range, the reported fan speed (RPM) may not be accurate + depending on your hardware. + +Bug reports +----------- + +Thermal management on Nouveau is new and may not work on all cards. If you have +inquiries, please ping mupuf on IRC (#nouveau, freenode). + +Bug reports should be filled on Freedesktop's bug tracker. Please follow +http://nouveau.freedesktop.org/wiki/Bugs diff --git a/Documentation/driver-api/thermal/power_allocator.rst b/Documentation/driver-api/thermal/power_allocator.rst new file mode 100644 index 000000000000..67b6a3297238 --- /dev/null +++ b/Documentation/driver-api/thermal/power_allocator.rst @@ -0,0 +1,271 @@ +================================= +Power allocator governor tunables +================================= + +Trip points +----------- + +The governor works optimally with the following two passive trip points: + +1. "switch on" trip point: temperature above which the governor + control loop starts operating. This is the first passive trip + point of the thermal zone. + +2. "desired temperature" trip point: it should be higher than the + "switch on" trip point. This the target temperature the governor + is controlling for. This is the last passive trip point of the + thermal zone. + +PID Controller +-------------- + +The power allocator governor implements a +Proportional-Integral-Derivative controller (PID controller) with +temperature as the control input and power as the controlled output: + + P_max = k_p * e + k_i * err_integral + k_d * diff_err + sustainable_power + +where + - e = desired_temperature - current_temperature + - err_integral is the sum of previous errors + - diff_err = e - previous_error + +It is similar to the one depicted below:: + + k_d + | + current_temp | + | v + | +----------+ +---+ + | +----->| diff_err |-->| X |------+ + | | +----------+ +---+ | + | | | tdp actor + | | k_i | | get_requested_power() + | | | | | | | + | | | | | | | ... + v | v v v v v + +---+ | +-------+ +---+ +---+ +---+ +----------+ + | S |-----+----->| sum e |----->| X |--->| S |-->| S |-->|power | + +---+ | +-------+ +---+ +---+ +---+ |allocation| + ^ | ^ +----------+ + | | | | | + | | +---+ | | | + | +------->| X |-------------------+ v v + | +---+ granted performance + desired_temperature ^ + | + | + k_po/k_pu + +Sustainable power +----------------- + +An estimate of the sustainable dissipatable power (in mW) should be +provided while registering the thermal zone. This estimates the +sustained power that can be dissipated at the desired control +temperature. This is the maximum sustained power for allocation at +the desired maximum temperature. The actual sustained power can vary +for a number of reasons. The closed loop controller will take care of +variations such as environmental conditions, and some factors related +to the speed-grade of the silicon. `sustainable_power` is therefore +simply an estimate, and may be tuned to affect the aggressiveness of +the thermal ramp. For reference, the sustainable power of a 4" phone +is typically 2000mW, while on a 10" tablet is around 4500mW (may vary +depending on screen size). + +If you are using device tree, do add it as a property of the +thermal-zone. For example:: + + thermal-zones { + soc_thermal { + polling-delay = <1000>; + polling-delay-passive = <100>; + sustainable-power = <2500>; + ... + +Instead, if the thermal zone is registered from the platform code, pass a +`thermal_zone_params` that has a `sustainable_power`. If no +`thermal_zone_params` were being passed, then something like below +will suffice:: + + static const struct thermal_zone_params tz_params = { + .sustainable_power = 3500, + }; + +and then pass `tz_params` as the 5th parameter to +`thermal_zone_device_register()` + +k_po and k_pu +------------- + +The implementation of the PID controller in the power allocator +thermal governor allows the configuration of two proportional term +constants: `k_po` and `k_pu`. `k_po` is the proportional term +constant during temperature overshoot periods (current temperature is +above "desired temperature" trip point). Conversely, `k_pu` is the +proportional term constant during temperature undershoot periods +(current temperature below "desired temperature" trip point). + +These controls are intended as the primary mechanism for configuring +the permitted thermal "ramp" of the system. For instance, a lower +`k_pu` value will provide a slower ramp, at the cost of capping +available capacity at a low temperature. On the other hand, a high +value of `k_pu` will result in the governor granting very high power +while temperature is low, and may lead to temperature overshooting. + +The default value for `k_pu` is:: + + 2 * sustainable_power / (desired_temperature - switch_on_temp) + +This means that at `switch_on_temp` the output of the controller's +proportional term will be 2 * `sustainable_power`. The default value +for `k_po` is:: + + sustainable_power / (desired_temperature - switch_on_temp) + +Focusing on the proportional and feed forward values of the PID +controller equation we have:: + + P_max = k_p * e + sustainable_power + +The proportional term is proportional to the difference between the +desired temperature and the current one. When the current temperature +is the desired one, then the proportional component is zero and +`P_max` = `sustainable_power`. That is, the system should operate in +thermal equilibrium under constant load. `sustainable_power` is only +an estimate, which is the reason for closed-loop control such as this. + +Expanding `k_pu` we get:: + + P_max = 2 * sustainable_power * (T_set - T) / (T_set - T_on) + + sustainable_power + +where: + + - T_set is the desired temperature + - T is the current temperature + - T_on is the switch on temperature + +When the current temperature is the switch_on temperature, the above +formula becomes:: + + P_max = 2 * sustainable_power * (T_set - T_on) / (T_set - T_on) + + sustainable_power = 2 * sustainable_power + sustainable_power = + 3 * sustainable_power + +Therefore, the proportional term alone linearly decreases power from +3 * `sustainable_power` to `sustainable_power` as the temperature +rises from the switch on temperature to the desired temperature. + +k_i and integral_cutoff +----------------------- + +`k_i` configures the PID loop's integral term constant. This term +allows the PID controller to compensate for long term drift and for +the quantized nature of the output control: cooling devices can't set +the exact power that the governor requests. When the temperature +error is below `integral_cutoff`, errors are accumulated in the +integral term. This term is then multiplied by `k_i` and the result +added to the output of the controller. Typically `k_i` is set low (1 +or 2) and `integral_cutoff` is 0. + +k_d +--- + +`k_d` configures the PID loop's derivative term constant. It's +recommended to leave it as the default: 0. + +Cooling device power API +======================== + +Cooling devices controlled by this governor must supply the additional +"power" API in their `cooling_device_ops`. It consists on three ops: + +1. :: + + int get_requested_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, u32 *power); + + +@cdev: + The `struct thermal_cooling_device` pointer +@tz: + thermal zone in which we are currently operating +@power: + pointer in which to store the calculated power + +`get_requested_power()` calculates the power requested by the device +in milliwatts and stores it in @power . It should return 0 on +success, -E* on failure. This is currently used by the power +allocator governor to calculate how much power to give to each cooling +device. + +2. :: + + int state2power(struct thermal_cooling_device *cdev, struct + thermal_zone_device *tz, unsigned long state, + u32 *power); + +@cdev: + The `struct thermal_cooling_device` pointer +@tz: + thermal zone in which we are currently operating +@state: + A cooling device state +@power: + pointer in which to store the equivalent power + +Convert cooling device state @state into power consumption in +milliwatts and store it in @power. It should return 0 on success, -E* +on failure. This is currently used by thermal core to calculate the +maximum power that an actor can consume. + +3. :: + + int power2state(struct thermal_cooling_device *cdev, u32 power, + unsigned long *state); + +@cdev: + The `struct thermal_cooling_device` pointer +@power: + power in milliwatts +@state: + pointer in which to store the resulting state + +Calculate a cooling device state that would make the device consume at +most @power mW and store it in @state. It should return 0 on success, +-E* on failure. This is currently used by the thermal core to convert +a given power set by the power allocator governor to a state that the +cooling device can set. It is a function because this conversion may +depend on external factors that may change so this function should the +best conversion given "current circumstances". + +Cooling device weights +---------------------- + +Weights are a mechanism to bias the allocation among cooling +devices. They express the relative power efficiency of different +cooling devices. Higher weight can be used to express higher power +efficiency. Weighting is relative such that if each cooling device +has a weight of one they are considered equal. This is particularly +useful in heterogeneous systems where two cooling devices may perform +the same kind of compute, but with different efficiency. For example, +a system with two different types of processors. + +If the thermal zone is registered using +`thermal_zone_device_register()` (i.e., platform code), then weights +are passed as part of the thermal zone's `thermal_bind_parameters`. +If the platform is registered using device tree, then they are passed +as the `contribution` property of each map in the `cooling-maps` node. + +Limitations of the power allocator governor +=========================================== + +The power allocator governor's PID controller works best if there is a +periodic tick. If you have a driver that calls +`thermal_zone_device_update()` (or anything that ends up calling the +governor's `throttle()` function) repetitively, the governor response +won't be very good. Note that this is not particular to this +governor, step-wise will also misbehave if you call its throttle() +faster than the normal thermal framework tick (due to interrupts for +example) as it will overreact. diff --git a/Documentation/driver-api/thermal/sysfs-api.rst b/Documentation/driver-api/thermal/sysfs-api.rst new file mode 100644 index 000000000000..fab2c9b36d08 --- /dev/null +++ b/Documentation/driver-api/thermal/sysfs-api.rst @@ -0,0 +1,798 @@ +=================================== +Generic Thermal Sysfs driver How To +=================================== + +Written by Sujith Thomas , Zhang Rui + +Updated: 2 January 2008 + +Copyright (c) 2008 Intel Corporation + + +0. Introduction +=============== + +The generic thermal sysfs provides a set of interfaces for thermal zone +devices (sensors) and thermal cooling devices (fan, processor...) to register +with the thermal management solution and to be a part of it. + +This how-to focuses on enabling new thermal zone and cooling devices to +participate in thermal management. +This solution is platform independent and any type of thermal zone devices +and cooling devices should be able to make use of the infrastructure. + +The main task of the thermal sysfs driver is to expose thermal zone attributes +as well as cooling device attributes to the user space. +An intelligent thermal management application can make decisions based on +inputs from thermal zone attributes (the current temperature and trip point +temperature) and throttle appropriate devices. + +- `[0-*]` denotes any positive number starting from 0 +- `[1-*]` denotes any positive number starting from 1 + +1. thermal sysfs driver interface functions +=========================================== + +1.1 thermal zone device interface +--------------------------------- + + :: + + struct thermal_zone_device + *thermal_zone_device_register(char *type, + int trips, int mask, void *devdata, + struct thermal_zone_device_ops *ops, + const struct thermal_zone_params *tzp, + int passive_delay, int polling_delay)) + + This interface function adds a new thermal zone device (sensor) to + /sys/class/thermal folder as `thermal_zone[0-*]`. It tries to bind all the + thermal cooling devices registered at the same time. + + type: + the thermal zone type. + trips: + the total number of trip points this thermal zone supports. + mask: + Bit string: If 'n'th bit is set, then trip point 'n' is writeable. + devdata: + device private data + ops: + thermal zone device call-backs. + + .bind: + bind the thermal zone device with a thermal cooling device. + .unbind: + unbind the thermal zone device with a thermal cooling device. + .get_temp: + get the current temperature of the thermal zone. + .set_trips: + set the trip points window. Whenever the current temperature + is updated, the trip points immediately below and above the + current temperature are found. + .get_mode: + get the current mode (enabled/disabled) of the thermal zone. + + - "enabled" means the kernel thermal management is + enabled. + - "disabled" will prevent kernel thermal driver action + upon trip points so that user applications can take + charge of thermal management. + .set_mode: + set the mode (enabled/disabled) of the thermal zone. + .get_trip_type: + get the type of certain trip point. + .get_trip_temp: + get the temperature above which the certain trip point + will be fired. + .set_emul_temp: + set the emulation temperature which helps in debugging + different threshold temperature points. + tzp: + thermal zone platform parameters. + passive_delay: + number of milliseconds to wait between polls when + performing passive cooling. + polling_delay: + number of milliseconds to wait between polls when checking + whether trip points have been crossed (0 for interrupt driven systems). + + :: + + void thermal_zone_device_unregister(struct thermal_zone_device *tz) + + This interface function removes the thermal zone device. + It deletes the corresponding entry from /sys/class/thermal folder and + unbinds all the thermal cooling devices it uses. + + :: + + struct thermal_zone_device + *thermal_zone_of_sensor_register(struct device *dev, int sensor_id, + void *data, + const struct thermal_zone_of_device_ops *ops) + + This interface adds a new sensor to a DT thermal zone. + This function will search the list of thermal zones described in + device tree and look for the zone that refer to the sensor device + pointed by dev->of_node as temperature providers. For the zone + pointing to the sensor node, the sensor will be added to the DT + thermal zone device. + + The parameters for this interface are: + + dev: + Device node of sensor containing valid node pointer in + dev->of_node. + sensor_id: + a sensor identifier, in case the sensor IP has more + than one sensors + data: + a private pointer (owned by the caller) that will be + passed back, when a temperature reading is needed. + ops: + `struct thermal_zone_of_device_ops *`. + + ============== ======================================= + get_temp a pointer to a function that reads the + sensor temperature. This is mandatory + callback provided by sensor driver. + set_trips a pointer to a function that sets a + temperature window. When this window is + left the driver must inform the thermal + core via thermal_zone_device_update. + get_trend a pointer to a function that reads the + sensor temperature trend. + set_emul_temp a pointer to a function that sets + sensor emulated temperature. + ============== ======================================= + + The thermal zone temperature is provided by the get_temp() function + pointer of thermal_zone_of_device_ops. When called, it will + have the private pointer @data back. + + It returns error pointer if fails otherwise valid thermal zone device + handle. Caller should check the return handle with IS_ERR() for finding + whether success or not. + + :: + + void thermal_zone_of_sensor_unregister(struct device *dev, + struct thermal_zone_device *tzd) + + This interface unregisters a sensor from a DT thermal zone which was + successfully added by interface thermal_zone_of_sensor_register(). + This function removes the sensor callbacks and private data from the + thermal zone device registered with thermal_zone_of_sensor_register() + interface. It will also silent the zone by remove the .get_temp() and + get_trend() thermal zone device callbacks. + + :: + + struct thermal_zone_device + *devm_thermal_zone_of_sensor_register(struct device *dev, + int sensor_id, + void *data, + const struct thermal_zone_of_device_ops *ops) + + This interface is resource managed version of + thermal_zone_of_sensor_register(). + + All details of thermal_zone_of_sensor_register() described in + section 1.1.3 is applicable here. + + The benefit of using this interface to register sensor is that it + is not require to explicitly call thermal_zone_of_sensor_unregister() + in error path or during driver unbinding as this is done by driver + resource manager. + + :: + + void devm_thermal_zone_of_sensor_unregister(struct device *dev, + struct thermal_zone_device *tzd) + + This interface is resource managed version of + thermal_zone_of_sensor_unregister(). + All details of thermal_zone_of_sensor_unregister() described in + section 1.1.4 is applicable here. + Normally this function will not need to be called and the resource + management code will ensure that the resource is freed. + + :: + + int thermal_zone_get_slope(struct thermal_zone_device *tz) + + This interface is used to read the slope attribute value + for the thermal zone device, which might be useful for platform + drivers for temperature calculations. + + :: + + int thermal_zone_get_offset(struct thermal_zone_device *tz) + + This interface is used to read the offset attribute value + for the thermal zone device, which might be useful for platform + drivers for temperature calculations. + +1.2 thermal cooling device interface +------------------------------------ + + + :: + + struct thermal_cooling_device + *thermal_cooling_device_register(char *name, + void *devdata, struct thermal_cooling_device_ops *) + + This interface function adds a new thermal cooling device (fan/processor/...) + to /sys/class/thermal/ folder as `cooling_device[0-*]`. It tries to bind itself + to all the thermal zone devices registered at the same time. + + name: + the cooling device name. + devdata: + device private data. + ops: + thermal cooling devices call-backs. + + .get_max_state: + get the Maximum throttle state of the cooling device. + .get_cur_state: + get the Currently requested throttle state of the + cooling device. + .set_cur_state: + set the Current throttle state of the cooling device. + + :: + + void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev) + + This interface function removes the thermal cooling device. + It deletes the corresponding entry from /sys/class/thermal folder and + unbinds itself from all the thermal zone devices using it. + +1.3 interface for binding a thermal zone device with a thermal cooling device +----------------------------------------------------------------------------- + + :: + + int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, + int trip, struct thermal_cooling_device *cdev, + unsigned long upper, unsigned long lower, unsigned int weight); + + This interface function binds a thermal cooling device to a particular trip + point of a thermal zone device. + + This function is usually called in the thermal zone device .bind callback. + + tz: + the thermal zone device + cdev: + thermal cooling device + trip: + indicates which trip point in this thermal zone the cooling device + is associated with. + upper: + the Maximum cooling state for this trip point. + THERMAL_NO_LIMIT means no upper limit, + and the cooling device can be in max_state. + lower: + the Minimum cooling state can be used for this trip point. + THERMAL_NO_LIMIT means no lower limit, + and the cooling device can be in cooling state 0. + weight: + the influence of this cooling device in this thermal + zone. See 1.4.1 below for more information. + + :: + + int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz, + int trip, struct thermal_cooling_device *cdev); + + This interface function unbinds a thermal cooling device from a particular + trip point of a thermal zone device. This function is usually called in + the thermal zone device .unbind callback. + + tz: + the thermal zone device + cdev: + thermal cooling device + trip: + indicates which trip point in this thermal zone the cooling device + is associated with. + +1.4 Thermal Zone Parameters +--------------------------- + + :: + + struct thermal_bind_params + + This structure defines the following parameters that are used to bind + a zone with a cooling device for a particular trip point. + + .cdev: + The cooling device pointer + .weight: + The 'influence' of a particular cooling device on this + zone. This is relative to the rest of the cooling + devices. For example, if all cooling devices have a + weight of 1, then they all contribute the same. You can + use percentages if you want, but it's not mandatory. A + weight of 0 means that this cooling device doesn't + contribute to the cooling of this zone unless all cooling + devices have a weight of 0. If all weights are 0, then + they all contribute the same. + .trip_mask: + This is a bit mask that gives the binding relation between + this thermal zone and cdev, for a particular trip point. + If nth bit is set, then the cdev and thermal zone are bound + for trip point n. + .binding_limits: + This is an array of cooling state limits. Must have + exactly 2 * thermal_zone.number_of_trip_points. It is an + array consisting of tuples of + state limits. Each trip will be associated with one state + limit tuple when binding. A NULL pointer means + on all trips. + These limits are used when binding a cdev to a trip point. + .match: + This call back returns success(0) if the 'tz and cdev' need to + be bound, as per platform data. + + :: + + struct thermal_zone_params + + This structure defines the platform level parameters for a thermal zone. + This data, for each thermal zone should come from the platform layer. + This is an optional feature where some platforms can choose not to + provide this data. + + .governor_name: + Name of the thermal governor used for this zone + .no_hwmon: + a boolean to indicate if the thermal to hwmon sysfs interface + is required. when no_hwmon == false, a hwmon sysfs interface + will be created. when no_hwmon == true, nothing will be done. + In case the thermal_zone_params is NULL, the hwmon interface + will be created (for backward compatibility). + .num_tbps: + Number of thermal_bind_params entries for this zone + .tbp: + thermal_bind_params entries + +2. sysfs attributes structure +============================= + +== ================ +RO read only value +WO write only value +RW read/write value +== ================ + +Thermal sysfs attributes will be represented under /sys/class/thermal. +Hwmon sysfs I/F extension is also available under /sys/class/hwmon +if hwmon is compiled in or built as a module. + +Thermal zone device sys I/F, created once it's registered:: + + /sys/class/thermal/thermal_zone[0-*]: + |---type: Type of the thermal zone + |---temp: Current temperature + |---mode: Working mode of the thermal zone + |---policy: Thermal governor used for this zone + |---available_policies: Available thermal governors for this zone + |---trip_point_[0-*]_temp: Trip point temperature + |---trip_point_[0-*]_type: Trip point type + |---trip_point_[0-*]_hyst: Hysteresis value for this trip point + |---emul_temp: Emulated temperature set node + |---sustainable_power: Sustainable dissipatable power + |---k_po: Proportional term during temperature overshoot + |---k_pu: Proportional term during temperature undershoot + |---k_i: PID's integral term in the power allocator gov + |---k_d: PID's derivative term in the power allocator + |---integral_cutoff: Offset above which errors are accumulated + |---slope: Slope constant applied as linear extrapolation + |---offset: Offset constant applied as linear extrapolation + +Thermal cooling device sys I/F, created once it's registered:: + + /sys/class/thermal/cooling_device[0-*]: + |---type: Type of the cooling device(processor/fan/...) + |---max_state: Maximum cooling state of the cooling device + |---cur_state: Current cooling state of the cooling device + |---stats: Directory containing cooling device's statistics + |---stats/reset: Writing any value resets the statistics + |---stats/time_in_state_ms: Time (msec) spent in various cooling states + |---stats/total_trans: Total number of times cooling state is changed + |---stats/trans_table: Cooing state transition table + + +Then next two dynamic attributes are created/removed in pairs. They represent +the relationship between a thermal zone and its associated cooling device. +They are created/removed for each successful execution of +thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device. + +:: + + /sys/class/thermal/thermal_zone[0-*]: + |---cdev[0-*]: [0-*]th cooling device in current thermal zone + |---cdev[0-*]_trip_point: Trip point that cdev[0-*] is associated with + |---cdev[0-*]_weight: Influence of the cooling device in + this thermal zone + +Besides the thermal zone device sysfs I/F and cooling device sysfs I/F, +the generic thermal driver also creates a hwmon sysfs I/F for each _type_ +of thermal zone device. E.g. the generic thermal driver registers one hwmon +class device and build the associated hwmon sysfs I/F for all the registered +ACPI thermal zones. + +:: + + /sys/class/hwmon/hwmon[0-*]: + |---name: The type of the thermal zone devices + |---temp[1-*]_input: The current temperature of thermal zone [1-*] + |---temp[1-*]_critical: The critical trip point of thermal zone [1-*] + +Please read Documentation/hwmon/sysfs-interface.rst for additional information. + +Thermal zone attributes +----------------------- + +type + Strings which represent the thermal zone type. + This is given by thermal zone driver as part of registration. + E.g: "acpitz" indicates it's an ACPI thermal device. + In order to keep it consistent with hwmon sys attribute; this should + be a short, lowercase string, not containing spaces nor dashes. + RO, Required + +temp + Current temperature as reported by thermal zone (sensor). + Unit: millidegree Celsius + RO, Required + +mode + One of the predefined values in [enabled, disabled]. + This file gives information about the algorithm that is currently + managing the thermal zone. It can be either default kernel based + algorithm or user space application. + + enabled + enable Kernel Thermal management. + disabled + Preventing kernel thermal zone driver actions upon + trip points so that user application can take full + charge of the thermal management. + + RW, Optional + +policy + One of the various thermal governors used for a particular zone. + + RW, Required + +available_policies + Available thermal governors which can be used for a particular zone. + + RO, Required + +`trip_point_[0-*]_temp` + The temperature above which trip point will be fired. + + Unit: millidegree Celsius + + RO, Optional + +`trip_point_[0-*]_type` + Strings which indicate the type of the trip point. + + E.g. it can be one of critical, hot, passive, `active[0-*]` for ACPI + thermal zone. + + RO, Optional + +`trip_point_[0-*]_hyst` + The hysteresis value for a trip point, represented as an integer + Unit: Celsius + RW, Optional + +`cdev[0-*]` + Sysfs link to the thermal cooling device node where the sys I/F + for cooling device throttling control represents. + + RO, Optional + +`cdev[0-*]_trip_point` + The trip point in this thermal zone which `cdev[0-*]` is associated + with; -1 means the cooling device is not associated with any trip + point. + + RO, Optional + +`cdev[0-*]_weight` + The influence of `cdev[0-*]` in this thermal zone. This value + is relative to the rest of cooling devices in the thermal + zone. For example, if a cooling device has a weight double + than that of other, it's twice as effective in cooling the + thermal zone. + + RW, Optional + +passive + Attribute is only present for zones in which the passive cooling + policy is not supported by native thermal driver. Default is zero + and can be set to a temperature (in millidegrees) to enable a + passive trip point for the zone. Activation is done by polling with + an interval of 1 second. + + Unit: millidegrees Celsius + + Valid values: 0 (disabled) or greater than 1000 + + RW, Optional + +emul_temp + Interface to set the emulated temperature method in thermal zone + (sensor). After setting this temperature, the thermal zone may pass + this temperature to platform emulation function if registered or + cache it locally. This is useful in debugging different temperature + threshold and its associated cooling action. This is write only node + and writing 0 on this node should disable emulation. + Unit: millidegree Celsius + + WO, Optional + + WARNING: + Be careful while enabling this option on production systems, + because userland can easily disable the thermal policy by simply + flooding this sysfs node with low temperature values. + +sustainable_power + An estimate of the sustained power that can be dissipated by + the thermal zone. Used by the power allocator governor. For + more information see Documentation/driver-api/thermal/power_allocator.rst + + Unit: milliwatts + + RW, Optional + +k_po + The proportional term of the power allocator governor's PID + controller during temperature overshoot. Temperature overshoot + is when the current temperature is above the "desired + temperature" trip point. For more information see + Documentation/driver-api/thermal/power_allocator.rst + + RW, Optional + +k_pu + The proportional term of the power allocator governor's PID + controller during temperature undershoot. Temperature undershoot + is when the current temperature is below the "desired + temperature" trip point. For more information see + Documentation/driver-api/thermal/power_allocator.rst + + RW, Optional + +k_i + The integral term of the power allocator governor's PID + controller. This term allows the PID controller to compensate + for long term drift. For more information see + Documentation/driver-api/thermal/power_allocator.rst + + RW, Optional + +k_d + The derivative term of the power allocator governor's PID + controller. For more information see + Documentation/driver-api/thermal/power_allocator.rst + + RW, Optional + +integral_cutoff + Temperature offset from the desired temperature trip point + above which the integral term of the power allocator + governor's PID controller starts accumulating errors. For + example, if integral_cutoff is 0, then the integral term only + accumulates error when temperature is above the desired + temperature trip point. For more information see + Documentation/driver-api/thermal/power_allocator.rst + + Unit: millidegree Celsius + + RW, Optional + +slope + The slope constant used in a linear extrapolation model + to determine a hotspot temperature based off the sensor's + raw readings. It is up to the device driver to determine + the usage of these values. + + RW, Optional + +offset + The offset constant used in a linear extrapolation model + to determine a hotspot temperature based off the sensor's + raw readings. It is up to the device driver to determine + the usage of these values. + + RW, Optional + +Cooling device attributes +------------------------- + +type + String which represents the type of device, e.g: + + - for generic ACPI: should be "Fan", "Processor" or "LCD" + - for memory controller device on intel_menlow platform: + should be "Memory controller". + + RO, Required + +max_state + The maximum permissible cooling state of this cooling device. + + RO, Required + +cur_state + The current cooling state of this cooling device. + The value can any integer numbers between 0 and max_state: + + - cur_state == 0 means no cooling + - cur_state == max_state means the maximum cooling. + + RW, Required + +stats/reset + Writing any value resets the cooling device's statistics. + WO, Required + +stats/time_in_state_ms: + The amount of time spent by the cooling device in various cooling + states. The output will have "