From d895494d079f1139b16e38a1f8e96910f72eaa2e Mon Sep 17 00:00:00 2001 From: Stephan Raue Date: Tue, 8 Mar 2011 15:56:22 +0100 Subject: [PATCH] linux: drop unneeded patches Signed-off-by: Stephan Raue --- ...110-drm_nouveau_upstream-20110222.patch.bk | 4449 --------- ...nux-2.6.38-rc8-700_701-730_BFS_patches.txt | 20 - ....6.38-rc8-701_sched-bfs-363.patch.disabled | 8243 ----------------- ..._2637-bfs363-nonhotplug_fix.patch.disabled | 60 - .../linux-2.6.38-rc8-702_ck2-version.patch | 19 - ...ux-2.6.38-rc8-703_cpufreq-bfs_tweaks.patch | 37 - ...linux-2.6.38-rc8-704_hz-default_1000.patch | 17 - ...nux-2.6.38-rc8-705_hz-no_default_250.patch | 47 - .../linux-2.6.38-rc8-706_hz-raise_max.patch | 174 - ...onfig-expose_vmsplit_option.patch.disabled | 40 - ...08_mm-kswapd_inherit_prio-1.patch.disabled | 69 - ...-709_mm-decrease_default_dirty_ratio.patch | 34 - ...-710_mm-drop_swap_cache_aggressively.patch | 87 - ...enable_swaptoken_only_when_swap_full.patch | 20 - ...-rc8-712_mm-background_scan.patch.disabled | 137 - ...-rc8-713_mm-idleprio_prio-1.patch.disabled | 33 - ...4_mm-lru_cache_add_lru_tail.patch.disabled | 250 - ...-2.6.38-rc8-717_preempt-desktop-tune.patch | 36 - ...ve-background-load-function.patch.disabled | 61 - projects/ATV/linux/linux.i386.conf | 17 +- projects/Generic/linux/linux.i386.conf | 17 +- projects/ION/linux/linux.i386.conf | 17 +- projects/ION/linux/linux.x86_64.conf | 17 +- projects/Intel/linux/linux.i386.conf | 17 +- projects/Intel/linux/linux.x86_64.conf | 17 +- 25 files changed, 30 insertions(+), 13905 deletions(-) delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-110-drm_nouveau_upstream-20110222.patch.bk delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-700_701-730_BFS_patches.txt delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-701_sched-bfs-363.patch.disabled delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-702_2637-bfs363-nonhotplug_fix.patch.disabled delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-702_ck2-version.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-703_cpufreq-bfs_tweaks.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-704_hz-default_1000.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-705_hz-no_default_250.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-706_hz-raise_max.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-707_kconfig-expose_vmsplit_option.patch.disabled delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-708_mm-kswapd_inherit_prio-1.patch.disabled delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-709_mm-decrease_default_dirty_ratio.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-710_mm-drop_swap_cache_aggressively.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-711_mm-enable_swaptoken_only_when_swap_full.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-712_mm-background_scan.patch.disabled delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-713_mm-idleprio_prio-1.patch.disabled delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-714_mm-lru_cache_add_lru_tail.patch.disabled delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-717_preempt-desktop-tune.patch delete mode 100644 packages/linux/patches/linux-2.6.38-rc8-718_sched-add-above-background-load-function.patch.disabled diff --git a/packages/linux/patches/linux-2.6.38-rc8-110-drm_nouveau_upstream-20110222.patch.bk b/packages/linux/patches/linux-2.6.38-rc8-110-drm_nouveau_upstream-20110222.patch.bk deleted file mode 100644 index 32cbe2de6d..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-110-drm_nouveau_upstream-20110222.patch.bk +++ /dev/null @@ -1,4449 +0,0 @@ -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_bios.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_bios.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_bios.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_bios.c 2011-02-22 14:25:08.609606768 +0100 -@@ -282,7 +282,7 @@ - { - #if 0 - sync(); -- msleep(2); -+ mdelay(2); - #endif - } - -@@ -1904,7 +1904,7 @@ - BIOSLOG(bios, "0x%04X: " - "Condition not met, sleeping for 20ms\n", - offset); -- msleep(20); -+ mdelay(20); - } - } - -@@ -1938,7 +1938,7 @@ - BIOSLOG(bios, "0x%04X: Sleeping for 0x%04X milliseconds\n", - offset, time); - -- msleep(time); -+ mdelay(time); - - return 3; - } -@@ -2962,7 +2962,7 @@ - if (time < 1000) - udelay(time); - else -- msleep((time + 900) / 1000); -+ mdelay((time + 900) / 1000); - - return 3; - } -@@ -3856,7 +3856,7 @@ - - if (script == LVDS_PANEL_OFF) { - /* off-on delay in ms */ -- msleep(ROM16(bios->data[bios->fp.xlated_entry + 7])); -+ mdelay(ROM16(bios->data[bios->fp.xlated_entry + 7])); - } - #ifdef __powerpc__ - /* Powerbook specific quirks */ -@@ -5950,6 +5950,11 @@ - } - } - -+static const u8 hpd_gpio[16] = { -+ 0xff, 0x07, 0x08, 0xff, 0xff, 0x51, 0x52, 0xff, -+ 0xff, 0xff, 0xff, 0xff, 0xff, 0x5e, 0x5f, 0x60, -+}; -+ - static void - parse_dcb_connector_table(struct nvbios *bios) - { -@@ -5986,23 +5991,9 @@ - - cte->type = (cte->entry & 0x000000ff) >> 0; - cte->index2 = (cte->entry & 0x00000f00) >> 8; -- switch (cte->entry & 0x00033000) { -- case 0x00001000: -- cte->gpio_tag = 0x07; -- break; -- case 0x00002000: -- cte->gpio_tag = 0x08; -- break; -- case 0x00010000: -- cte->gpio_tag = 0x51; -- break; -- case 0x00020000: -- cte->gpio_tag = 0x52; -- break; -- default: -- cte->gpio_tag = 0xff; -- break; -- } -+ -+ cte->gpio_tag = ffs((cte->entry & 0x07033000) >> 12); -+ cte->gpio_tag = hpd_gpio[cte->gpio_tag]; - - if (cte->type == 0xff) - continue; -@@ -6702,11 +6693,11 @@ - struct nvbios *bios = &dev_priv->vbios; - struct init_exec iexec = { true, false }; - -- mutex_lock(&bios->lock); -+ spin_lock_bh(&bios->lock); - bios->display.output = dcbent; - parse_init_table(bios, table, &iexec); - bios->display.output = NULL; -- mutex_unlock(&bios->lock); -+ spin_unlock_bh(&bios->lock); - } - - static bool NVInitVBIOS(struct drm_device *dev) -@@ -6715,7 +6706,7 @@ - struct nvbios *bios = &dev_priv->vbios; - - memset(bios, 0, sizeof(struct nvbios)); -- mutex_init(&bios->lock); -+ spin_lock_init(&bios->lock); - bios->dev = dev; - - if (!NVShadowVBIOS(dev, bios->data)) -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_bios.h linux-2.6/drivers/gpu/drm/nouveau/nouveau_bios.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_bios.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_bios.h 2011-02-22 14:16:21.580230479 +0100 -@@ -251,7 +251,7 @@ - uint8_t digital_min_front_porch; - bool fp_no_ddc; - -- struct mutex lock; -+ spinlock_t lock; - - uint8_t data[NV_PROM_SIZE]; - unsigned int length; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_bo.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_bo.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_bo.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_bo.c 2011-02-22 14:32:02.564311615 +0100 -@@ -54,8 +54,8 @@ - } - - static void --nouveau_bo_fixup_align(struct nouveau_bo *nvbo, int *align, int *size, -- int *page_shift) -+nouveau_bo_fixup_align(struct nouveau_bo *nvbo, u32 flags, -+ int *align, int *size, int *page_shift) - { - struct drm_nouveau_private *dev_priv = nouveau_bdev(nvbo->bo.bdev); - -@@ -80,7 +80,7 @@ - } - } else { - if (likely(dev_priv->chan_vm)) { -- if (*size > 256 * 1024) -+ if (!(flags & TTM_PL_FLAG_TT) && *size > 256 * 1024) - *page_shift = dev_priv->chan_vm->lpg_shift; - else - *page_shift = dev_priv->chan_vm->spg_shift; -@@ -98,8 +98,7 @@ - int - nouveau_bo_new(struct drm_device *dev, struct nouveau_channel *chan, - int size, int align, uint32_t flags, uint32_t tile_mode, -- uint32_t tile_flags, bool no_vm, bool mappable, -- struct nouveau_bo **pnvbo) -+ uint32_t tile_flags, struct nouveau_bo **pnvbo) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_bo *nvbo; -@@ -110,16 +109,14 @@ - return -ENOMEM; - INIT_LIST_HEAD(&nvbo->head); - INIT_LIST_HEAD(&nvbo->entry); -- nvbo->mappable = mappable; -- nvbo->no_vm = no_vm; - nvbo->tile_mode = tile_mode; - nvbo->tile_flags = tile_flags; - nvbo->bo.bdev = &dev_priv->ttm.bdev; - -- nouveau_bo_fixup_align(nvbo, &align, &size, &page_shift); -+ nouveau_bo_fixup_align(nvbo, flags, &align, &size, &page_shift); - align >>= PAGE_SHIFT; - -- if (!nvbo->no_vm && dev_priv->chan_vm) { -+ if (dev_priv->chan_vm) { - ret = nouveau_vm_get(dev_priv->chan_vm, size, page_shift, - NV_MEM_ACCESS_RW, &nvbo->vma); - if (ret) { -@@ -140,11 +137,8 @@ - } - nvbo->channel = NULL; - -- if (nvbo->vma.node) { -- if (nvbo->bo.mem.mem_type == TTM_PL_VRAM) -- nvbo->bo.offset = nvbo->vma.offset; -- } -- -+ if (nvbo->vma.node) -+ nvbo->bo.offset = nvbo->vma.offset; - *pnvbo = nvbo; - return 0; - } -@@ -314,11 +308,8 @@ - if (ret) - return ret; - -- if (nvbo->vma.node) { -- if (nvbo->bo.mem.mem_type == TTM_PL_VRAM) -- nvbo->bo.offset = nvbo->vma.offset; -- } -- -+ if (nvbo->vma.node) -+ nvbo->bo.offset = nvbo->vma.offset; - return 0; - } - -@@ -381,7 +372,8 @@ - case NOUVEAU_GART_AGP: - return ttm_agp_backend_init(bdev, dev->agp->bridge); - #endif -- case NOUVEAU_GART_SGDMA: -+ case NOUVEAU_GART_PDMA: -+ case NOUVEAU_GART_HW: - return nouveau_sgdma_init_ttm(dev); - default: - NV_ERROR(dev, "Unknown GART type %d\n", -@@ -427,7 +419,10 @@ - man->default_caching = TTM_PL_FLAG_WC; - break; - case TTM_PL_TT: -- man->func = &ttm_bo_manager_func; -+ if (dev_priv->card_type >= NV_50) -+ man->func = &nouveau_gart_manager; -+ else -+ man->func = &ttm_bo_manager_func; - switch (dev_priv->gart_info.type) { - case NOUVEAU_GART_AGP: - man->flags = TTM_MEMTYPE_FLAG_MAPPABLE; -@@ -435,7 +430,8 @@ - TTM_PL_FLAG_WC; - man->default_caching = TTM_PL_FLAG_WC; - break; -- case NOUVEAU_GART_SGDMA: -+ case NOUVEAU_GART_PDMA: -+ case NOUVEAU_GART_HW: - man->flags = TTM_MEMTYPE_FLAG_MAPPABLE | - TTM_MEMTYPE_FLAG_CMA; - man->available_caching = TTM_PL_MASK_CACHING; -@@ -497,45 +493,22 @@ - return ret; - } - --static inline uint32_t --nouveau_bo_mem_ctxdma(struct ttm_buffer_object *bo, -- struct nouveau_channel *chan, struct ttm_mem_reg *mem) --{ -- struct nouveau_bo *nvbo = nouveau_bo(bo); -- -- if (nvbo->no_vm) { -- if (mem->mem_type == TTM_PL_TT) -- return NvDmaGART; -- return NvDmaVRAM; -- } -- -- if (mem->mem_type == TTM_PL_TT) -- return chan->gart_handle; -- return chan->vram_handle; --} -- - static int - nvc0_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo, - struct ttm_mem_reg *old_mem, struct ttm_mem_reg *new_mem) - { -- struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); -+ struct nouveau_mem *old_node = old_mem->mm_node; -+ struct nouveau_mem *new_node = new_mem->mm_node; - struct nouveau_bo *nvbo = nouveau_bo(bo); -- u64 src_offset = old_mem->start << PAGE_SHIFT; -- u64 dst_offset = new_mem->start << PAGE_SHIFT; - u32 page_count = new_mem->num_pages; -+ u64 src_offset, dst_offset; - int ret; - -- if (!nvbo->no_vm) { -- if (old_mem->mem_type == TTM_PL_VRAM) -- src_offset = nvbo->vma.offset; -- else -- src_offset += dev_priv->gart_info.aper_base; -- -- if (new_mem->mem_type == TTM_PL_VRAM) -- dst_offset = nvbo->vma.offset; -- else -- dst_offset += dev_priv->gart_info.aper_base; -- } -+ src_offset = old_node->tmp_vma.offset; -+ if (new_node->tmp_vma.node) -+ dst_offset = new_node->tmp_vma.offset; -+ else -+ dst_offset = nvbo->vma.offset; - - page_count = new_mem->num_pages; - while (page_count) { -@@ -570,33 +543,18 @@ - nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo, - struct ttm_mem_reg *old_mem, struct ttm_mem_reg *new_mem) - { -- struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); -+ struct nouveau_mem *old_node = old_mem->mm_node; -+ struct nouveau_mem *new_node = new_mem->mm_node; - struct nouveau_bo *nvbo = nouveau_bo(bo); - u64 length = (new_mem->num_pages << PAGE_SHIFT); - u64 src_offset, dst_offset; - int ret; - -- src_offset = old_mem->start << PAGE_SHIFT; -- dst_offset = new_mem->start << PAGE_SHIFT; -- if (!nvbo->no_vm) { -- if (old_mem->mem_type == TTM_PL_VRAM) -- src_offset = nvbo->vma.offset; -- else -- src_offset += dev_priv->gart_info.aper_base; -- -- if (new_mem->mem_type == TTM_PL_VRAM) -- dst_offset = nvbo->vma.offset; -- else -- dst_offset += dev_priv->gart_info.aper_base; -- } -- -- ret = RING_SPACE(chan, 3); -- if (ret) -- return ret; -- -- BEGIN_RING(chan, NvSubM2MF, 0x0184, 2); -- OUT_RING (chan, nouveau_bo_mem_ctxdma(bo, chan, old_mem)); -- OUT_RING (chan, nouveau_bo_mem_ctxdma(bo, chan, new_mem)); -+ src_offset = old_node->tmp_vma.offset; -+ if (new_node->tmp_vma.node) -+ dst_offset = new_node->tmp_vma.offset; -+ else -+ dst_offset = nvbo->vma.offset; - - while (length) { - u32 amount, stride, height; -@@ -677,6 +635,15 @@ - return 0; - } - -+static inline uint32_t -+nouveau_bo_mem_ctxdma(struct ttm_buffer_object *bo, -+ struct nouveau_channel *chan, struct ttm_mem_reg *mem) -+{ -+ if (mem->mem_type == TTM_PL_TT) -+ return chan->gart_handle; -+ return chan->vram_handle; -+} -+ - static int - nv04_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo, - struct ttm_mem_reg *old_mem, struct ttm_mem_reg *new_mem) -@@ -730,15 +697,43 @@ - { - struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); - struct nouveau_bo *nvbo = nouveau_bo(bo); -+ struct ttm_mem_reg *old_mem = &bo->mem; - struct nouveau_channel *chan; - int ret; - - chan = nvbo->channel; -- if (!chan || nvbo->no_vm) { -+ if (!chan) { - chan = dev_priv->channel; - mutex_lock_nested(&chan->mutex, NOUVEAU_KCHANNEL_MUTEX); - } - -+ /* create temporary vma for old memory, this will get cleaned -+ * up after ttm destroys the ttm_mem_reg -+ */ -+ if (dev_priv->card_type >= NV_50) { -+ struct nouveau_mem *node = old_mem->mm_node; -+ if (!node->tmp_vma.node) { -+ u32 page_shift = nvbo->vma.node->type; -+ if (old_mem->mem_type == TTM_PL_TT) -+ page_shift = nvbo->vma.vm->spg_shift; -+ -+ ret = nouveau_vm_get(chan->vm, -+ old_mem->num_pages << PAGE_SHIFT, -+ page_shift, NV_MEM_ACCESS_RO, -+ &node->tmp_vma); -+ if (ret) -+ goto out; -+ } -+ -+ if (old_mem->mem_type == TTM_PL_VRAM) -+ nouveau_vm_map(&node->tmp_vma, node); -+ else { -+ nouveau_vm_map_sg(&node->tmp_vma, 0, -+ old_mem->num_pages << PAGE_SHIFT, -+ node, node->pages); -+ } -+ } -+ - if (dev_priv->card_type < NV_50) - ret = nv04_bo_move_m2mf(chan, bo, &bo->mem, new_mem); - else -@@ -752,6 +747,7 @@ - no_wait_gpu, new_mem); - } - -+out: - if (chan == dev_priv->channel) - mutex_unlock(&chan->mutex); - return ret; -@@ -762,6 +758,7 @@ - bool no_wait_reserve, bool no_wait_gpu, - struct ttm_mem_reg *new_mem) - { -+ struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); - u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING; - struct ttm_placement placement; - struct ttm_mem_reg tmp_mem; -@@ -781,7 +778,23 @@ - if (ret) - goto out; - -+ if (dev_priv->card_type >= NV_50) { -+ struct nouveau_bo *nvbo = nouveau_bo(bo); -+ struct nouveau_mem *node = tmp_mem.mm_node; -+ struct nouveau_vma *vma = &nvbo->vma; -+ if (vma->node->type != vma->vm->spg_shift) -+ vma = &node->tmp_vma; -+ nouveau_vm_map_sg(vma, 0, tmp_mem.num_pages << PAGE_SHIFT, -+ node, node->pages); -+ } -+ - ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_reserve, no_wait_gpu, &tmp_mem); -+ -+ if (dev_priv->card_type >= NV_50) { -+ struct nouveau_bo *nvbo = nouveau_bo(bo); -+ nouveau_vm_unmap(&nvbo->vma); -+ } -+ - if (ret) - goto out; - -@@ -824,6 +837,36 @@ - return ret; - } - -+static void -+nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem) -+{ -+ struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); -+ struct nouveau_mem *node = new_mem->mm_node; -+ struct nouveau_bo *nvbo = nouveau_bo(bo); -+ struct nouveau_vma *vma = &nvbo->vma; -+ struct nouveau_vm *vm = vma->vm; -+ -+ if (dev_priv->card_type < NV_50) -+ return; -+ -+ switch (new_mem->mem_type) { -+ case TTM_PL_VRAM: -+ nouveau_vm_map(vma, node); -+ break; -+ case TTM_PL_TT: -+ if (vma->node->type != vm->spg_shift) { -+ nouveau_vm_unmap(vma); -+ vma = &node->tmp_vma; -+ } -+ nouveau_vm_map_sg(vma, 0, new_mem->num_pages << PAGE_SHIFT, -+ node, node->pages); -+ break; -+ default: -+ nouveau_vm_unmap(&nvbo->vma); -+ break; -+ } -+} -+ - static int - nouveau_bo_vm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem, - struct nouveau_tile_reg **new_tile) -@@ -831,19 +874,13 @@ - struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); - struct drm_device *dev = dev_priv->dev; - struct nouveau_bo *nvbo = nouveau_bo(bo); -- uint64_t offset; -+ u64 offset = new_mem->start << PAGE_SHIFT; - -- if (nvbo->no_vm || new_mem->mem_type != TTM_PL_VRAM) { -- /* Nothing to do. */ -- *new_tile = NULL; -+ *new_tile = NULL; -+ if (new_mem->mem_type != TTM_PL_VRAM) - return 0; -- } - -- offset = new_mem->start << PAGE_SHIFT; -- -- if (dev_priv->chan_vm) { -- nouveau_vm_map(&nvbo->vma, new_mem->mm_node); -- } else if (dev_priv->card_type >= NV_10) { -+ if (dev_priv->card_type >= NV_10) { - *new_tile = nv10_mem_set_tiling(dev, offset, new_mem->size, - nvbo->tile_mode, - nvbo->tile_flags); -@@ -860,11 +897,8 @@ - struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); - struct drm_device *dev = dev_priv->dev; - -- if (dev_priv->card_type >= NV_10 && -- dev_priv->card_type < NV_50) { -- nv10_mem_put_tile_region(dev, *old_tile, bo->sync_obj); -- *old_tile = new_tile; -- } -+ nv10_mem_put_tile_region(dev, *old_tile, bo->sync_obj); -+ *old_tile = new_tile; - } - - static int -@@ -878,9 +912,11 @@ - struct nouveau_tile_reg *new_tile = NULL; - int ret = 0; - -- ret = nouveau_bo_vm_bind(bo, new_mem, &new_tile); -- if (ret) -- return ret; -+ if (dev_priv->card_type < NV_50) { -+ ret = nouveau_bo_vm_bind(bo, new_mem, &new_tile); -+ if (ret) -+ return ret; -+ } - - /* Fake bo copy. */ - if (old_mem->mem_type == TTM_PL_SYSTEM && !bo->ttm) { -@@ -911,10 +947,12 @@ - ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem); - - out: -- if (ret) -- nouveau_bo_vm_cleanup(bo, NULL, &new_tile); -- else -- nouveau_bo_vm_cleanup(bo, new_tile, &nvbo->tile); -+ if (dev_priv->card_type < NV_50) { -+ if (ret) -+ nouveau_bo_vm_cleanup(bo, NULL, &new_tile); -+ else -+ nouveau_bo_vm_cleanup(bo, new_tile, &nvbo->tile); -+ } - - return ret; - } -@@ -955,7 +993,7 @@ - break; - case TTM_PL_VRAM: - { -- struct nouveau_vram *vram = mem->mm_node; -+ struct nouveau_mem *node = mem->mm_node; - u8 page_shift; - - if (!dev_priv->bar1_vm) { -@@ -966,23 +1004,23 @@ - } - - if (dev_priv->card_type == NV_C0) -- page_shift = vram->page_shift; -+ page_shift = node->page_shift; - else - page_shift = 12; - - ret = nouveau_vm_get(dev_priv->bar1_vm, mem->bus.size, - page_shift, NV_MEM_ACCESS_RW, -- &vram->bar_vma); -+ &node->bar_vma); - if (ret) - return ret; - -- nouveau_vm_map(&vram->bar_vma, vram); -+ nouveau_vm_map(&node->bar_vma, node); - if (ret) { -- nouveau_vm_put(&vram->bar_vma); -+ nouveau_vm_put(&node->bar_vma); - return ret; - } - -- mem->bus.offset = vram->bar_vma.offset; -+ mem->bus.offset = node->bar_vma.offset; - if (dev_priv->card_type == NV_50) /*XXX*/ - mem->bus.offset -= 0x0020000000ULL; - mem->bus.base = pci_resource_start(dev->pdev, 1); -@@ -999,16 +1037,16 @@ - nouveau_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) - { - struct drm_nouveau_private *dev_priv = nouveau_bdev(bdev); -- struct nouveau_vram *vram = mem->mm_node; -+ struct nouveau_mem *node = mem->mm_node; - - if (!dev_priv->bar1_vm || mem->mem_type != TTM_PL_VRAM) - return; - -- if (!vram->bar_vma.node) -+ if (!node->bar_vma.node) - return; - -- nouveau_vm_unmap(&vram->bar_vma); -- nouveau_vm_put(&vram->bar_vma); -+ nouveau_vm_unmap(&node->bar_vma); -+ nouveau_vm_put(&node->bar_vma); - } - - static int -@@ -1058,6 +1096,7 @@ - .invalidate_caches = nouveau_bo_invalidate_caches, - .init_mem_type = nouveau_bo_init_mem_type, - .evict_flags = nouveau_bo_evict_flags, -+ .move_notify = nouveau_bo_move_ntfy, - .move = nouveau_bo_move, - .verify_access = nouveau_bo_verify_access, - .sync_obj_signaled = __nouveau_fence_signalled, -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_channel.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_channel.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_channel.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_channel.c 2011-02-22 14:16:21.581230459 +0100 -@@ -35,7 +35,7 @@ - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_bo *pb = chan->pushbuf_bo; - struct nouveau_gpuobj *pushbuf = NULL; -- int ret; -+ int ret = 0; - - if (dev_priv->card_type >= NV_50) { - if (dev_priv->card_type < NV_C0) { -@@ -90,8 +90,7 @@ - else - location = TTM_PL_FLAG_TT; - -- ret = nouveau_bo_new(dev, NULL, 65536, 0, location, 0, 0x0000, false, -- true, &pushbuf); -+ ret = nouveau_bo_new(dev, NULL, 65536, 0, location, 0, 0x0000, &pushbuf); - if (ret) { - NV_ERROR(dev, "error allocating DMA push buffer: %d\n", ret); - return NULL; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_display.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_display.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_display.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_display.c 2011-02-22 14:16:21.582230439 +0100 -@@ -32,6 +32,7 @@ - #include "nouveau_hw.h" - #include "nouveau_crtc.h" - #include "nouveau_dma.h" -+#include "nv50_display.h" - - static void - nouveau_user_framebuffer_destroy(struct drm_framebuffer *drm_fb) -@@ -61,18 +62,59 @@ - }; - - int --nouveau_framebuffer_init(struct drm_device *dev, struct nouveau_framebuffer *nouveau_fb, -- struct drm_mode_fb_cmd *mode_cmd, struct nouveau_bo *nvbo) -+nouveau_framebuffer_init(struct drm_device *dev, -+ struct nouveau_framebuffer *nv_fb, -+ struct drm_mode_fb_cmd *mode_cmd, -+ struct nouveau_bo *nvbo) - { -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct drm_framebuffer *fb = &nv_fb->base; - int ret; - -- ret = drm_framebuffer_init(dev, &nouveau_fb->base, &nouveau_framebuffer_funcs); -+ ret = drm_framebuffer_init(dev, fb, &nouveau_framebuffer_funcs); - if (ret) { - return ret; - } - -- drm_helper_mode_fill_fb_struct(&nouveau_fb->base, mode_cmd); -- nouveau_fb->nvbo = nvbo; -+ drm_helper_mode_fill_fb_struct(fb, mode_cmd); -+ nv_fb->nvbo = nvbo; -+ -+ if (dev_priv->card_type >= NV_50) { -+ u32 tile_flags = nouveau_bo_tile_layout(nvbo); -+ if (tile_flags == 0x7a00 || -+ tile_flags == 0xfe00) -+ nv_fb->r_dma = NvEvoFB32; -+ else -+ if (tile_flags == 0x7000) -+ nv_fb->r_dma = NvEvoFB16; -+ else -+ nv_fb->r_dma = NvEvoVRAM_LP; -+ -+ switch (fb->depth) { -+ case 8: nv_fb->r_format = NV50_EVO_CRTC_FB_DEPTH_8; break; -+ case 15: nv_fb->r_format = NV50_EVO_CRTC_FB_DEPTH_15; break; -+ case 16: nv_fb->r_format = NV50_EVO_CRTC_FB_DEPTH_16; break; -+ case 24: -+ case 32: nv_fb->r_format = NV50_EVO_CRTC_FB_DEPTH_24; break; -+ case 30: nv_fb->r_format = NV50_EVO_CRTC_FB_DEPTH_30; break; -+ default: -+ NV_ERROR(dev, "unknown depth %d\n", fb->depth); -+ return -EINVAL; -+ } -+ -+ if (dev_priv->chipset == 0x50) -+ nv_fb->r_format |= (tile_flags << 8); -+ -+ if (!tile_flags) -+ nv_fb->r_pitch = 0x00100000 | fb->pitch; -+ else { -+ u32 mode = nvbo->tile_mode; -+ if (dev_priv->card_type >= NV_C0) -+ mode >>= 4; -+ nv_fb->r_pitch = ((fb->pitch / 4) << 4) | mode; -+ } -+ } -+ - return 0; - } - -@@ -182,6 +224,7 @@ - struct nouveau_page_flip_state *s, - struct nouveau_fence **pfence) - { -+ struct drm_nouveau_private *dev_priv = chan->dev->dev_private; - struct drm_device *dev = chan->dev; - unsigned long flags; - int ret; -@@ -201,9 +244,12 @@ - if (ret) - goto fail; - -- BEGIN_RING(chan, NvSubSw, NV_SW_PAGE_FLIP, 1); -- OUT_RING(chan, 0); -- FIRE_RING(chan); -+ if (dev_priv->card_type < NV_C0) -+ BEGIN_RING(chan, NvSubSw, NV_SW_PAGE_FLIP, 1); -+ else -+ BEGIN_NVC0(chan, 2, NvSubM2MF, 0x0500, 1); -+ OUT_RING (chan, 0); -+ FIRE_RING (chan); - - ret = nouveau_fence_new(chan, pfence, true); - if (ret) -@@ -244,7 +290,7 @@ - - /* Initialize a page flip struct */ - *s = (struct nouveau_page_flip_state) -- { { }, s->event, nouveau_crtc(crtc)->index, -+ { { }, event, nouveau_crtc(crtc)->index, - fb->bits_per_pixel, fb->pitch, crtc->x, crtc->y, - new_bo->bo.offset }; - -@@ -255,6 +301,14 @@ - mutex_lock(&chan->mutex); - - /* Emit a page flip */ -+ if (dev_priv->card_type >= NV_50) { -+ ret = nv50_display_flip_next(crtc, fb, chan); -+ if (ret) { -+ nouveau_channel_put(&chan); -+ goto fail_unreserve; -+ } -+ } -+ - ret = nouveau_page_flip_emit(chan, old_bo, new_bo, s, &fence); - nouveau_channel_put(&chan); - if (ret) -@@ -305,7 +359,8 @@ - } - - list_del(&s->head); -- *ps = *s; -+ if (ps) -+ *ps = *s; - kfree(s); - - spin_unlock_irqrestore(&dev->event_lock, flags); -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_dma.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_dma.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_dma.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_dma.c 2011-02-22 14:16:21.582230439 +0100 -@@ -96,13 +96,15 @@ - OUT_RING(chan, 0); - - /* Initialise NV_MEMORY_TO_MEMORY_FORMAT */ -- ret = RING_SPACE(chan, 4); -+ ret = RING_SPACE(chan, 6); - if (ret) - return ret; - BEGIN_RING(chan, NvSubM2MF, NV_MEMORY_TO_MEMORY_FORMAT_NAME, 1); -- OUT_RING(chan, NvM2MF); -- BEGIN_RING(chan, NvSubM2MF, NV_MEMORY_TO_MEMORY_FORMAT_DMA_NOTIFY, 1); -- OUT_RING(chan, NvNotify0); -+ OUT_RING (chan, NvM2MF); -+ BEGIN_RING(chan, NvSubM2MF, NV_MEMORY_TO_MEMORY_FORMAT_DMA_NOTIFY, 3); -+ OUT_RING (chan, NvNotify0); -+ OUT_RING (chan, chan->vram_handle); -+ OUT_RING (chan, chan->gart_handle); - - /* Sit back and pray the channel works.. */ - FIRE_RING(chan); -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_dma.h linux-2.6/drivers/gpu/drm/nouveau/nouveau_dma.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_dma.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_dma.h 2011-02-22 14:16:21.582230439 +0100 -@@ -61,8 +61,6 @@ - NvM2MF = 0x80000001, - NvDmaFB = 0x80000002, - NvDmaTT = 0x80000003, -- NvDmaVRAM = 0x80000004, -- NvDmaGART = 0x80000005, - NvNotify0 = 0x80000006, - Nv2D = 0x80000007, - NvCtxSurf2D = 0x80000008, -@@ -73,12 +71,15 @@ - NvImageBlit = 0x8000000d, - NvSw = 0x8000000e, - NvSema = 0x8000000f, -+ NvEvoSema0 = 0x80000010, -+ NvEvoSema1 = 0x80000011, - - /* G80+ display objects */ - NvEvoVRAM = 0x01000000, - NvEvoFB16 = 0x01000001, - NvEvoFB32 = 0x01000002, -- NvEvoVRAM_LP = 0x01000003 -+ NvEvoVRAM_LP = 0x01000003, -+ NvEvoSync = 0xcafe0000 - }; - - #define NV_MEMORY_TO_MEMORY_FORMAT 0x00000039 -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_dp.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_dp.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_dp.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_dp.c 2011-02-22 14:16:21.582230439 +0100 -@@ -175,7 +175,6 @@ - { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - struct drm_device *dev = encoder->dev; -- struct bit_displayport_encoder_table_entry *dpse; - struct bit_displayport_encoder_table *dpe; - int ret, i, dpe_headerlen, vs = 0, pre = 0; - uint8_t request[2]; -@@ -183,7 +182,6 @@ - dpe = nouveau_bios_dp_table(dev, nv_encoder->dcb, &dpe_headerlen); - if (!dpe) - return false; -- dpse = (void *)((char *)dpe + dpe_headerlen); - - ret = auxch_rd(encoder, DP_ADJUST_REQUEST_LANE0_1, request, 2); - if (ret) -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_drv.h linux-2.6/drivers/gpu/drm/nouveau/nouveau_drv.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_drv.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_drv.h 2011-02-22 14:16:21.583230419 +0100 -@@ -57,7 +57,7 @@ - #include "nouveau_util.h" - - struct nouveau_grctx; --struct nouveau_vram; -+struct nouveau_mem; - #include "nouveau_vm.h" - - #define MAX_NUM_DCB_ENTRIES 16 -@@ -65,13 +65,16 @@ - #define NOUVEAU_MAX_CHANNEL_NR 128 - #define NOUVEAU_MAX_TILE_NR 15 - --struct nouveau_vram { -+struct nouveau_mem { - struct drm_device *dev; - - struct nouveau_vma bar_vma; -+ struct nouveau_vma tmp_vma; - u8 page_shift; - -+ struct drm_mm_node *tag; - struct list_head regions; -+ dma_addr_t *pages; - u32 memtype; - u64 offset; - u64 size; -@@ -90,6 +93,7 @@ - struct nouveau_bo { - struct ttm_buffer_object bo; - struct ttm_placement placement; -+ u32 valid_domains; - u32 placements[3]; - u32 busy_placements[3]; - struct ttm_bo_kmap_obj kmap; -@@ -104,8 +108,6 @@ - struct nouveau_channel *channel; - - struct nouveau_vma vma; -- bool mappable; -- bool no_vm; - - uint32_t tile_mode; - uint32_t tile_flags; -@@ -387,6 +389,7 @@ - }; - - struct nouveau_display_engine { -+ void *priv; - int (*early_init)(struct drm_device *); - void (*late_takedown)(struct drm_device *); - int (*create)(struct drm_device *); -@@ -509,8 +512,8 @@ - struct nouveau_vram_engine { - int (*init)(struct drm_device *); - int (*get)(struct drm_device *, u64, u32 align, u32 size_nc, -- u32 type, struct nouveau_vram **); -- void (*put)(struct drm_device *, struct nouveau_vram **); -+ u32 type, struct nouveau_mem **); -+ void (*put)(struct drm_device *, struct nouveau_mem **); - - bool (*flags_valid)(struct drm_device *, u32 tile_flags); - }; -@@ -652,8 +655,6 @@ - /* interrupt handling */ - void (*irq_handler[32])(struct drm_device *); - bool msi_enabled; -- struct workqueue_struct *wq; -- struct work_struct irq_work; - - struct list_head vbl_waiting; - -@@ -691,15 +692,22 @@ - struct { - enum { - NOUVEAU_GART_NONE = 0, -- NOUVEAU_GART_AGP, -- NOUVEAU_GART_SGDMA -+ NOUVEAU_GART_AGP, /* AGP */ -+ NOUVEAU_GART_PDMA, /* paged dma object */ -+ NOUVEAU_GART_HW /* on-chip gart/vm */ - } type; - uint64_t aper_base; - uint64_t aper_size; - uint64_t aper_free; - -+ struct ttm_backend_func *func; -+ -+ struct { -+ struct page *page; -+ dma_addr_t addr; -+ } dummy; -+ - struct nouveau_gpuobj *sg_ctxdma; -- struct nouveau_vma vma; - } gart_info; - - /* nv10-nv40 tiling regions */ -@@ -740,14 +748,6 @@ - - struct backlight_device *backlight; - -- struct nouveau_channel *evo; -- u32 evo_alloc; -- struct { -- struct dcb_entry *dcb; -- u16 script; -- u32 pclk; -- } evo_irq; -- - struct { - struct dentry *channel_root; - } debugfs; -@@ -847,6 +847,7 @@ - struct nouveau_tile_reg *tile, - struct nouveau_fence *fence); - extern const struct ttm_mem_type_manager_func nouveau_vram_manager; -+extern const struct ttm_mem_type_manager_func nouveau_gart_manager; - - /* nouveau_notifier.c */ - extern int nouveau_notifier_init_channel(struct nouveau_channel *); -@@ -1294,7 +1295,7 @@ - extern int nouveau_bo_new(struct drm_device *, struct nouveau_channel *, - int size, int align, uint32_t flags, - uint32_t tile_mode, uint32_t tile_flags, -- bool no_vm, bool mappable, struct nouveau_bo **); -+ struct nouveau_bo **); - extern int nouveau_bo_pin(struct nouveau_bo *, uint32_t flags); - extern int nouveau_bo_unpin(struct nouveau_bo *); - extern int nouveau_bo_map(struct nouveau_bo *); -@@ -1355,9 +1356,9 @@ - - /* nouveau_gem.c */ - extern int nouveau_gem_new(struct drm_device *, struct nouveau_channel *, -- int size, int align, uint32_t flags, -+ int size, int align, uint32_t domain, - uint32_t tile_mode, uint32_t tile_flags, -- bool no_vm, bool mappable, struct nouveau_bo **); -+ struct nouveau_bo **); - extern int nouveau_gem_object_new(struct drm_gem_object *); - extern void nouveau_gem_object_del(struct drm_gem_object *); - extern int nouveau_gem_ioctl_new(struct drm_device *, void *, -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_fbcon.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_fbcon.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_fbcon.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_fbcon.c 2011-02-22 14:16:21.584230398 +0100 -@@ -296,8 +296,8 @@ - size = mode_cmd.pitch * mode_cmd.height; - size = roundup(size, PAGE_SIZE); - -- ret = nouveau_gem_new(dev, dev_priv->channel, size, 0, TTM_PL_FLAG_VRAM, -- 0, 0x0000, false, true, &nvbo); -+ ret = nouveau_gem_new(dev, dev_priv->channel, size, 0, -+ NOUVEAU_GEM_DOMAIN_VRAM, 0, 0x0000, &nvbo); - if (ret) { - NV_ERROR(dev, "failed to allocate framebuffer\n"); - goto out; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_fb.h linux-2.6/drivers/gpu/drm/nouveau/nouveau_fb.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_fb.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_fb.h 2011-02-22 14:16:21.584230398 +0100 -@@ -30,6 +30,9 @@ - struct nouveau_framebuffer { - struct drm_framebuffer base; - struct nouveau_bo *nvbo; -+ u32 r_dma; -+ u32 r_format; -+ u32 r_pitch; - }; - - static inline struct nouveau_framebuffer * -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_fence.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_fence.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_fence.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_fence.c 2011-02-22 14:16:21.584230398 +0100 -@@ -32,8 +32,7 @@ - #include "nouveau_dma.h" - - #define USE_REFCNT(dev) (nouveau_private(dev)->chipset >= 0x10) --#define USE_SEMA(dev) (nouveau_private(dev)->chipset >= 0x17 && \ -- nouveau_private(dev)->card_type < NV_C0) -+#define USE_SEMA(dev) (nouveau_private(dev)->chipset >= 0x17) - - struct nouveau_fence { - struct nouveau_channel *channel; -@@ -259,11 +258,12 @@ - } - - static struct nouveau_semaphore * --alloc_semaphore(struct drm_device *dev) -+semaphore_alloc(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_semaphore *sema; -- int ret; -+ int size = (dev_priv->chipset < 0x84) ? 4 : 16; -+ int ret, i; - - if (!USE_SEMA(dev)) - return NULL; -@@ -277,9 +277,9 @@ - goto fail; - - spin_lock(&dev_priv->fence.lock); -- sema->mem = drm_mm_search_free(&dev_priv->fence.heap, 4, 0, 0); -+ sema->mem = drm_mm_search_free(&dev_priv->fence.heap, size, 0, 0); - if (sema->mem) -- sema->mem = drm_mm_get_block_atomic(sema->mem, 4, 0); -+ sema->mem = drm_mm_get_block_atomic(sema->mem, size, 0); - spin_unlock(&dev_priv->fence.lock); - - if (!sema->mem) -@@ -287,7 +287,8 @@ - - kref_init(&sema->ref); - sema->dev = dev; -- nouveau_bo_wr32(dev_priv->fence.bo, sema->mem->start / 4, 0); -+ for (i = sema->mem->start; i < sema->mem->start + size; i += 4) -+ nouveau_bo_wr32(dev_priv->fence.bo, i / 4, 0); - - return sema; - fail: -@@ -296,7 +297,7 @@ - } - - static void --free_semaphore(struct kref *ref) -+semaphore_free(struct kref *ref) - { - struct nouveau_semaphore *sema = - container_of(ref, struct nouveau_semaphore, ref); -@@ -318,61 +319,107 @@ - if (unlikely(!signalled)) - nouveau_bo_wr32(dev_priv->fence.bo, sema->mem->start / 4, 1); - -- kref_put(&sema->ref, free_semaphore); -+ kref_put(&sema->ref, semaphore_free); - } - - static int --emit_semaphore(struct nouveau_channel *chan, int method, -- struct nouveau_semaphore *sema) -+semaphore_acquire(struct nouveau_channel *chan, struct nouveau_semaphore *sema) - { -- struct drm_nouveau_private *dev_priv = sema->dev->dev_private; -- struct nouveau_fence *fence; -- bool smart = (dev_priv->card_type >= NV_50); -+ struct drm_nouveau_private *dev_priv = chan->dev->dev_private; -+ struct nouveau_fence *fence = NULL; - int ret; - -- ret = RING_SPACE(chan, smart ? 8 : 4); -+ if (dev_priv->chipset < 0x84) { -+ ret = RING_SPACE(chan, 3); -+ if (ret) -+ return ret; -+ -+ BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_OFFSET, 2); -+ OUT_RING (chan, sema->mem->start); -+ OUT_RING (chan, 1); -+ } else -+ if (dev_priv->chipset < 0xc0) { -+ struct nouveau_vma *vma = &dev_priv->fence.bo->vma; -+ u64 offset = vma->offset + sema->mem->start; -+ -+ ret = RING_SPACE(chan, 5); -+ if (ret) -+ return ret; -+ -+ BEGIN_RING(chan, NvSubSw, 0x0010, 4); -+ OUT_RING (chan, upper_32_bits(offset)); -+ OUT_RING (chan, lower_32_bits(offset)); -+ OUT_RING (chan, 1); -+ OUT_RING (chan, 1); /* ACQUIRE_EQ */ -+ } else { -+ struct nouveau_vma *vma = &dev_priv->fence.bo->vma; -+ u64 offset = vma->offset + sema->mem->start; -+ -+ ret = RING_SPACE(chan, 5); -+ if (ret) -+ return ret; -+ -+ BEGIN_NVC0(chan, 2, NvSubM2MF, 0x0010, 4); -+ OUT_RING (chan, upper_32_bits(offset)); -+ OUT_RING (chan, lower_32_bits(offset)); -+ OUT_RING (chan, 1); -+ OUT_RING (chan, 0x1001); /* ACQUIRE_EQ */ -+ } -+ -+ /* Delay semaphore destruction until its work is done */ -+ ret = nouveau_fence_new(chan, &fence, true); - if (ret) - return ret; - -- if (smart) { -- BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1); -- OUT_RING(chan, NvSema); -- } -- BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_OFFSET, 1); -- OUT_RING(chan, sema->mem->start); -+ kref_get(&sema->ref); -+ nouveau_fence_work(fence, semaphore_work, sema); -+ nouveau_fence_unref(&fence); -+ return 0; -+} - -- if (smart && method == NV_SW_SEMAPHORE_ACQUIRE) { -- /* -- * NV50 tries to be too smart and context-switch -- * between semaphores instead of doing a "first come, -- * first served" strategy like previous cards -- * do. -- * -- * That's bad because the ACQUIRE latency can get as -- * large as the PFIFO context time slice in the -- * typical DRI2 case where you have several -- * outstanding semaphores at the same moment. -- * -- * If we're going to ACQUIRE, force the card to -- * context switch before, just in case the matching -- * RELEASE is already scheduled to be executed in -- * another channel. -- */ -- BEGIN_RING(chan, NvSubSw, NV_SW_YIELD, 1); -- OUT_RING(chan, 0); -- } -- -- BEGIN_RING(chan, NvSubSw, method, 1); -- OUT_RING(chan, 1); -- -- if (smart && method == NV_SW_SEMAPHORE_RELEASE) { -- /* -- * Force the card to context switch, there may be -- * another channel waiting for the semaphore we just -- * released. -- */ -- BEGIN_RING(chan, NvSubSw, NV_SW_YIELD, 1); -- OUT_RING(chan, 0); -+static int -+semaphore_release(struct nouveau_channel *chan, struct nouveau_semaphore *sema) -+{ -+ struct drm_nouveau_private *dev_priv = chan->dev->dev_private; -+ struct nouveau_fence *fence = NULL; -+ int ret; -+ -+ if (dev_priv->chipset < 0x84) { -+ ret = RING_SPACE(chan, 4); -+ if (ret) -+ return ret; -+ -+ BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_OFFSET, 1); -+ OUT_RING (chan, sema->mem->start); -+ BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_RELEASE, 1); -+ OUT_RING (chan, 1); -+ } else -+ if (dev_priv->chipset < 0xc0) { -+ struct nouveau_vma *vma = &dev_priv->fence.bo->vma; -+ u64 offset = vma->offset + sema->mem->start; -+ -+ ret = RING_SPACE(chan, 5); -+ if (ret) -+ return ret; -+ -+ BEGIN_RING(chan, NvSubSw, 0x0010, 4); -+ OUT_RING (chan, upper_32_bits(offset)); -+ OUT_RING (chan, lower_32_bits(offset)); -+ OUT_RING (chan, 1); -+ OUT_RING (chan, 2); /* RELEASE */ -+ } else { -+ struct nouveau_vma *vma = &dev_priv->fence.bo->vma; -+ u64 offset = vma->offset + sema->mem->start; -+ -+ ret = RING_SPACE(chan, 5); -+ if (ret) -+ return ret; -+ -+ BEGIN_NVC0(chan, 2, NvSubM2MF, 0x0010, 4); -+ OUT_RING (chan, upper_32_bits(offset)); -+ OUT_RING (chan, lower_32_bits(offset)); -+ OUT_RING (chan, 1); -+ OUT_RING (chan, 0x1002); /* RELEASE */ - } - - /* Delay semaphore destruction until its work is done */ -@@ -383,7 +430,6 @@ - kref_get(&sema->ref); - nouveau_fence_work(fence, semaphore_work, sema); - nouveau_fence_unref(&fence); -- - return 0; - } - -@@ -400,7 +446,7 @@ - nouveau_fence_signalled(fence))) - goto out; - -- sema = alloc_semaphore(dev); -+ sema = semaphore_alloc(dev); - if (!sema) { - /* Early card or broken userspace, fall back to - * software sync. */ -@@ -418,17 +464,17 @@ - } - - /* Make wchan wait until it gets signalled */ -- ret = emit_semaphore(wchan, NV_SW_SEMAPHORE_ACQUIRE, sema); -+ ret = semaphore_acquire(wchan, sema); - if (ret) - goto out_unlock; - - /* Signal the semaphore from chan */ -- ret = emit_semaphore(chan, NV_SW_SEMAPHORE_RELEASE, sema); -+ ret = semaphore_release(chan, sema); - - out_unlock: - mutex_unlock(&chan->mutex); - out_unref: -- kref_put(&sema->ref, free_semaphore); -+ kref_put(&sema->ref, semaphore_free); - out: - if (chan) - nouveau_channel_put_unlocked(&chan); -@@ -449,22 +495,23 @@ - struct nouveau_gpuobj *obj = NULL; - int ret; - -+ if (dev_priv->card_type >= NV_C0) -+ goto out_initialised; -+ - /* Create an NV_SW object for various sync purposes */ - ret = nouveau_gpuobj_gr_new(chan, NvSw, NV_SW); - if (ret) - return ret; - - /* we leave subchannel empty for nvc0 */ -- if (dev_priv->card_type < NV_C0) { -- ret = RING_SPACE(chan, 2); -- if (ret) -- return ret; -- BEGIN_RING(chan, NvSubSw, 0, 1); -- OUT_RING(chan, NvSw); -- } -+ ret = RING_SPACE(chan, 2); -+ if (ret) -+ return ret; -+ BEGIN_RING(chan, NvSubSw, 0, 1); -+ OUT_RING(chan, NvSw); - - /* Create a DMA object for the shared cross-channel sync area. */ -- if (USE_SEMA(dev)) { -+ if (USE_SEMA(dev) && dev_priv->chipset < 0x84) { - struct ttm_mem_reg *mem = &dev_priv->fence.bo->bo.mem; - - ret = nouveau_gpuobj_dma_new(chan, NV_CLASS_DMA_IN_MEMORY, -@@ -484,14 +531,20 @@ - return ret; - BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1); - OUT_RING(chan, NvSema); -+ } else { -+ ret = RING_SPACE(chan, 2); -+ if (ret) -+ return ret; -+ BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1); -+ OUT_RING (chan, chan->vram_handle); /* whole VM */ - } - - FIRE_RING(chan); - -+out_initialised: - INIT_LIST_HEAD(&chan->fence.pending); - spin_lock_init(&chan->fence.lock); - atomic_set(&chan->fence.last_sequence_irq, 0); -- - return 0; - } - -@@ -519,12 +572,13 @@ - nouveau_fence_init(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -+ int size = (dev_priv->chipset < 0x84) ? 4096 : 16384; - int ret; - - /* Create a shared VRAM heap for cross-channel sync. */ - if (USE_SEMA(dev)) { -- ret = nouveau_bo_new(dev, NULL, 4096, 0, TTM_PL_FLAG_VRAM, -- 0, 0, false, true, &dev_priv->fence.bo); -+ ret = nouveau_bo_new(dev, NULL, size, 0, TTM_PL_FLAG_VRAM, -+ 0, 0, &dev_priv->fence.bo); - if (ret) - return ret; - -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_gem.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_gem.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_gem.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_gem.c 2011-02-22 14:16:21.585230377 +0100 -@@ -61,19 +61,36 @@ - - int - nouveau_gem_new(struct drm_device *dev, struct nouveau_channel *chan, -- int size, int align, uint32_t flags, uint32_t tile_mode, -- uint32_t tile_flags, bool no_vm, bool mappable, -- struct nouveau_bo **pnvbo) -+ int size, int align, uint32_t domain, uint32_t tile_mode, -+ uint32_t tile_flags, struct nouveau_bo **pnvbo) - { -+ struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_bo *nvbo; -+ u32 flags = 0; - int ret; - -+ if (domain & NOUVEAU_GEM_DOMAIN_VRAM) -+ flags |= TTM_PL_FLAG_VRAM; -+ if (domain & NOUVEAU_GEM_DOMAIN_GART) -+ flags |= TTM_PL_FLAG_TT; -+ if (!flags || domain & NOUVEAU_GEM_DOMAIN_CPU) -+ flags |= TTM_PL_FLAG_SYSTEM; -+ - ret = nouveau_bo_new(dev, chan, size, align, flags, tile_mode, -- tile_flags, no_vm, mappable, pnvbo); -+ tile_flags, pnvbo); - if (ret) - return ret; - nvbo = *pnvbo; - -+ /* we restrict allowed domains on nv50+ to only the types -+ * that were requested at creation time. not possibly on -+ * earlier chips without busting the ABI. -+ */ -+ nvbo->valid_domains = NOUVEAU_GEM_DOMAIN_VRAM | -+ NOUVEAU_GEM_DOMAIN_GART; -+ if (dev_priv->card_type >= NV_50) -+ nvbo->valid_domains &= domain; -+ - nvbo->gem = drm_gem_object_alloc(dev, nvbo->bo.mem.size); - if (!nvbo->gem) { - nouveau_bo_ref(NULL, pnvbo); -@@ -97,7 +114,7 @@ - - rep->size = nvbo->bo.mem.num_pages << PAGE_SHIFT; - rep->offset = nvbo->bo.offset; -- rep->map_handle = nvbo->mappable ? nvbo->bo.addr_space_offset : 0; -+ rep->map_handle = nvbo->bo.addr_space_offset; - rep->tile_mode = nvbo->tile_mode; - rep->tile_flags = nvbo->tile_flags; - return 0; -@@ -111,19 +128,11 @@ - struct drm_nouveau_gem_new *req = data; - struct nouveau_bo *nvbo = NULL; - struct nouveau_channel *chan = NULL; -- uint32_t flags = 0; - int ret = 0; - - if (unlikely(dev_priv->ttm.bdev.dev_mapping == NULL)) - dev_priv->ttm.bdev.dev_mapping = dev_priv->dev->dev_mapping; - -- if (req->info.domain & NOUVEAU_GEM_DOMAIN_VRAM) -- flags |= TTM_PL_FLAG_VRAM; -- if (req->info.domain & NOUVEAU_GEM_DOMAIN_GART) -- flags |= TTM_PL_FLAG_TT; -- if (!flags || req->info.domain & NOUVEAU_GEM_DOMAIN_CPU) -- flags |= TTM_PL_FLAG_SYSTEM; -- - if (!dev_priv->engine.vram.flags_valid(dev, req->info.tile_flags)) { - NV_ERROR(dev, "bad page flags: 0x%08x\n", req->info.tile_flags); - return -EINVAL; -@@ -135,10 +144,9 @@ - return PTR_ERR(chan); - } - -- ret = nouveau_gem_new(dev, chan, req->info.size, req->align, flags, -- req->info.tile_mode, req->info.tile_flags, false, -- (req->info.domain & NOUVEAU_GEM_DOMAIN_MAPPABLE), -- &nvbo); -+ ret = nouveau_gem_new(dev, chan, req->info.size, req->align, -+ req->info.domain, req->info.tile_mode, -+ req->info.tile_flags, &nvbo); - if (chan) - nouveau_channel_put(&chan); - if (ret) -@@ -161,7 +169,7 @@ - { - struct nouveau_bo *nvbo = gem->driver_private; - struct ttm_buffer_object *bo = &nvbo->bo; -- uint32_t domains = valid_domains & -+ uint32_t domains = valid_domains & nvbo->valid_domains & - (write_domains ? write_domains : read_domains); - uint32_t pref_flags = 0, valid_flags = 0; - -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_mem.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_mem.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_mem.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_mem.c 2011-02-22 14:16:21.587230337 +0100 -@@ -152,7 +152,6 @@ - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - -- nouveau_bo_unpin(dev_priv->vga_ram); - nouveau_bo_ref(NULL, &dev_priv->vga_ram); - - ttm_bo_device_release(&dev_priv->ttm.bdev); -@@ -393,11 +392,17 @@ - struct ttm_bo_device *bdev = &dev_priv->ttm.bdev; - int ret, dma_bits; - -- if (dev_priv->card_type >= NV_50 && -- pci_dma_supported(dev->pdev, DMA_BIT_MASK(40))) -- dma_bits = 40; -- else -- dma_bits = 32; -+ dma_bits = 32; -+ if (dev_priv->card_type >= NV_50) { -+ if (pci_dma_supported(dev->pdev, DMA_BIT_MASK(40))) -+ dma_bits = 40; -+ } else -+ if (drm_device_is_pcie(dev) && -+ dev_priv->chipset != 0x40 && -+ dev_priv->chipset != 0x45) { -+ if (pci_dma_supported(dev->pdev, DMA_BIT_MASK(39))) -+ dma_bits = 39; -+ } - - ret = pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(dma_bits)); - if (ret) -@@ -455,13 +460,17 @@ - return ret; - } - -- ret = nouveau_bo_new(dev, NULL, 256*1024, 0, TTM_PL_FLAG_VRAM, -- 0, 0, true, true, &dev_priv->vga_ram); -- if (ret == 0) -- ret = nouveau_bo_pin(dev_priv->vga_ram, TTM_PL_FLAG_VRAM); -- if (ret) { -- NV_WARN(dev, "failed to reserve VGA memory\n"); -- nouveau_bo_ref(NULL, &dev_priv->vga_ram); -+ if (dev_priv->card_type < NV_50) { -+ ret = nouveau_bo_new(dev, NULL, 256*1024, 0, TTM_PL_FLAG_VRAM, -+ 0, 0, &dev_priv->vga_ram); -+ if (ret == 0) -+ ret = nouveau_bo_pin(dev_priv->vga_ram, -+ TTM_PL_FLAG_VRAM); -+ -+ if (ret) { -+ NV_WARN(dev, "failed to reserve VGA memory\n"); -+ nouveau_bo_ref(NULL, &dev_priv->vga_ram); -+ } - } - - dev_priv->fb_mtrr = drm_mtrr_add(pci_resource_start(dev->pdev, 1), -@@ -666,13 +675,14 @@ - { - struct drm_nouveau_private *dev_priv = nouveau_bdev(man->bdev); - struct nouveau_mm *mm; -- u32 b_size; -+ u64 size, block, rsvd; - int ret; - -- p_size = (p_size << PAGE_SHIFT) >> 12; -- b_size = dev_priv->vram_rblock_size >> 12; -+ rsvd = (256 * 1024); /* vga memory */ -+ size = (p_size << PAGE_SHIFT) - rsvd; -+ block = dev_priv->vram_rblock_size; - -- ret = nouveau_mm_init(&mm, 0, p_size, b_size); -+ ret = nouveau_mm_init(&mm, rsvd >> 12, size >> 12, block >> 12); - if (ret) - return ret; - -@@ -700,9 +710,15 @@ - { - struct drm_nouveau_private *dev_priv = nouveau_bdev(man->bdev); - struct nouveau_vram_engine *vram = &dev_priv->engine.vram; -+ struct nouveau_mem *node = mem->mm_node; - struct drm_device *dev = dev_priv->dev; - -- vram->put(dev, (struct nouveau_vram **)&mem->mm_node); -+ if (node->tmp_vma.node) { -+ nouveau_vm_unmap(&node->tmp_vma); -+ nouveau_vm_put(&node->tmp_vma); -+ } -+ -+ vram->put(dev, (struct nouveau_mem **)&mem->mm_node); - } - - static int -@@ -715,7 +731,7 @@ - struct nouveau_vram_engine *vram = &dev_priv->engine.vram; - struct drm_device *dev = dev_priv->dev; - struct nouveau_bo *nvbo = nouveau_bo(bo); -- struct nouveau_vram *node; -+ struct nouveau_mem *node; - u32 size_nc = 0; - int ret; - -@@ -724,7 +740,7 @@ - - ret = vram->get(dev, mem->num_pages << PAGE_SHIFT, - mem->page_alignment << PAGE_SHIFT, size_nc, -- (nvbo->tile_flags >> 8) & 0xff, &node); -+ (nvbo->tile_flags >> 8) & 0x3ff, &node); - if (ret) - return ret; - -@@ -769,3 +785,84 @@ - nouveau_vram_manager_del, - nouveau_vram_manager_debug - }; -+ -+static int -+nouveau_gart_manager_init(struct ttm_mem_type_manager *man, unsigned long psize) -+{ -+ return 0; -+} -+ -+static int -+nouveau_gart_manager_fini(struct ttm_mem_type_manager *man) -+{ -+ return 0; -+} -+ -+static void -+nouveau_gart_manager_del(struct ttm_mem_type_manager *man, -+ struct ttm_mem_reg *mem) -+{ -+ struct nouveau_mem *node = mem->mm_node; -+ -+ if (node->tmp_vma.node) { -+ nouveau_vm_unmap(&node->tmp_vma); -+ nouveau_vm_put(&node->tmp_vma); -+ } -+ mem->mm_node = NULL; -+} -+ -+static int -+nouveau_gart_manager_new(struct ttm_mem_type_manager *man, -+ struct ttm_buffer_object *bo, -+ struct ttm_placement *placement, -+ struct ttm_mem_reg *mem) -+{ -+ struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev); -+ struct nouveau_bo *nvbo = nouveau_bo(bo); -+ struct nouveau_vma *vma = &nvbo->vma; -+ struct nouveau_vm *vm = vma->vm; -+ struct nouveau_mem *node; -+ int ret; -+ -+ if (unlikely((mem->num_pages << PAGE_SHIFT) >= -+ dev_priv->gart_info.aper_size)) -+ return -ENOMEM; -+ -+ node = kzalloc(sizeof(*node), GFP_KERNEL); -+ if (!node) -+ return -ENOMEM; -+ -+ /* This node must be for evicting large-paged VRAM -+ * to system memory. Due to a nv50 limitation of -+ * not being able to mix large/small pages within -+ * the same PDE, we need to create a temporary -+ * small-paged VMA for the eviction. -+ */ -+ if (vma->node->type != vm->spg_shift) { -+ ret = nouveau_vm_get(vm, (u64)vma->node->length << 12, -+ vm->spg_shift, NV_MEM_ACCESS_RW, -+ &node->tmp_vma); -+ if (ret) { -+ kfree(node); -+ return ret; -+ } -+ } -+ -+ node->page_shift = nvbo->vma.node->type; -+ mem->mm_node = node; -+ mem->start = 0; -+ return 0; -+} -+ -+void -+nouveau_gart_manager_debug(struct ttm_mem_type_manager *man, const char *prefix) -+{ -+} -+ -+const struct ttm_mem_type_manager_func nouveau_gart_manager = { -+ nouveau_gart_manager_init, -+ nouveau_gart_manager_fini, -+ nouveau_gart_manager_new, -+ nouveau_gart_manager_del, -+ nouveau_gart_manager_debug -+}; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_mm.h linux-2.6/drivers/gpu/drm/nouveau/nouveau_mm.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_mm.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_mm.h 2011-02-22 14:16:21.587230337 +0100 -@@ -53,13 +53,13 @@ - - int nv50_vram_init(struct drm_device *); - int nv50_vram_new(struct drm_device *, u64 size, u32 align, u32 size_nc, -- u32 memtype, struct nouveau_vram **); --void nv50_vram_del(struct drm_device *, struct nouveau_vram **); -+ u32 memtype, struct nouveau_mem **); -+void nv50_vram_del(struct drm_device *, struct nouveau_mem **); - bool nv50_vram_flags_valid(struct drm_device *, u32 tile_flags); - - int nvc0_vram_init(struct drm_device *); - int nvc0_vram_new(struct drm_device *, u64 size, u32 align, u32 ncmin, -- u32 memtype, struct nouveau_vram **); -+ u32 memtype, struct nouveau_mem **); - bool nvc0_vram_flags_valid(struct drm_device *, u32 tile_flags); - - #endif -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_notifier.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_notifier.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_notifier.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_notifier.c 2011-02-22 14:16:21.587230337 +0100 -@@ -39,12 +39,11 @@ - int ret; - - if (nouveau_vram_notify) -- flags = TTM_PL_FLAG_VRAM; -+ flags = NOUVEAU_GEM_DOMAIN_VRAM; - else -- flags = TTM_PL_FLAG_TT; -+ flags = NOUVEAU_GEM_DOMAIN_GART; - -- ret = nouveau_gem_new(dev, NULL, PAGE_SIZE, 0, flags, -- 0, 0x0000, false, true, &ntfy); -+ ret = nouveau_gem_new(dev, NULL, PAGE_SIZE, 0, flags, 0, 0, &ntfy); - if (ret) - return ret; - -@@ -99,6 +98,7 @@ - int size, uint32_t *b_offset) - { - struct drm_device *dev = chan->dev; -+ struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_gpuobj *nobj = NULL; - struct drm_mm_node *mem; - uint32_t offset; -@@ -112,11 +112,16 @@ - return -ENOMEM; - } - -- if (chan->notifier_bo->bo.mem.mem_type == TTM_PL_VRAM) -- target = NV_MEM_TARGET_VRAM; -- else -- target = NV_MEM_TARGET_GART; -- offset = chan->notifier_bo->bo.mem.start << PAGE_SHIFT; -+ if (dev_priv->card_type < NV_50) { -+ if (chan->notifier_bo->bo.mem.mem_type == TTM_PL_VRAM) -+ target = NV_MEM_TARGET_VRAM; -+ else -+ target = NV_MEM_TARGET_GART; -+ offset = chan->notifier_bo->bo.mem.start << PAGE_SHIFT; -+ } else { -+ target = NV_MEM_TARGET_VM; -+ offset = chan->notifier_bo->vma.offset; -+ } - offset += mem->start; - - ret = nouveau_gpuobj_dma_new(chan, NV_CLASS_DMA_IN_MEMORY, offset, -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_object.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_object.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_object.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_object.c 2011-02-22 14:16:21.588230317 +0100 -@@ -36,6 +36,7 @@ - #include "nouveau_drm.h" - #include "nouveau_ramht.h" - #include "nouveau_vm.h" -+#include "nv50_display.h" - - struct nouveau_gpuobj_method { - struct list_head head; -@@ -490,16 +491,22 @@ - } - - if (target == NV_MEM_TARGET_GART) { -- if (dev_priv->gart_info.type == NOUVEAU_GART_AGP) { -- target = NV_MEM_TARGET_PCI_NOSNOOP; -- base += dev_priv->gart_info.aper_base; -- } else -- if (base != 0) { -- base = nouveau_sgdma_get_physical(dev, base); -+ struct nouveau_gpuobj *gart = dev_priv->gart_info.sg_ctxdma; -+ -+ if (dev_priv->gart_info.type == NOUVEAU_GART_PDMA) { -+ if (base == 0) { -+ nouveau_gpuobj_ref(gart, pobj); -+ return 0; -+ } -+ -+ base = nouveau_sgdma_get_physical(dev, base); - target = NV_MEM_TARGET_PCI; - } else { -- nouveau_gpuobj_ref(dev_priv->gart_info.sg_ctxdma, pobj); -- return 0; -+ base += dev_priv->gart_info.aper_base; -+ if (dev_priv->gart_info.type == NOUVEAU_GART_AGP) -+ target = NV_MEM_TARGET_PCI_NOSNOOP; -+ else -+ target = NV_MEM_TARGET_PCI; - } - } - -@@ -776,7 +783,7 @@ - struct drm_device *dev = chan->dev; - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_gpuobj *vram = NULL, *tt = NULL; -- int ret; -+ int ret, i; - - NV_DEBUG(dev, "ch%d vram=0x%08x tt=0x%08x\n", chan->id, vram_h, tt_h); - -@@ -841,6 +848,25 @@ - nouveau_gpuobj_ref(NULL, &ramht); - if (ret) - return ret; -+ -+ /* dma objects for display sync channel semaphore blocks */ -+ for (i = 0; i < 2; i++) { -+ struct nouveau_gpuobj *sem = NULL; -+ struct nv50_display_crtc *dispc = -+ &nv50_display(dev)->crtc[i]; -+ u64 offset = dispc->sem.bo->bo.mem.start << PAGE_SHIFT; -+ -+ ret = nouveau_gpuobj_dma_new(chan, 0x3d, offset, 0xfff, -+ NV_MEM_ACCESS_RW, -+ NV_MEM_TARGET_VRAM, &sem); -+ if (ret) -+ return ret; -+ -+ ret = nouveau_ramht_insert(chan, NvEvoSema0 + i, sem); -+ nouveau_gpuobj_ref(NULL, &sem); -+ if (ret) -+ return ret; -+ } - } - - /* VRAM ctxdma */ -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_ramht.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_ramht.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_ramht.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_ramht.c 2011-02-22 14:16:21.589230297 +0100 -@@ -114,7 +114,9 @@ - (gpuobj->engine << NV40_RAMHT_CONTEXT_ENGINE_SHIFT); - } else { - if (gpuobj->engine == NVOBJ_ENGINE_DISPLAY) { -- ctx = (gpuobj->cinst << 10) | chan->id; -+ ctx = (gpuobj->cinst << 10) | -+ (chan->id << 28) | -+ chan->id; /* HASH_TAG */ - } else { - ctx = (gpuobj->cinst >> 4) | - ((gpuobj->engine << -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_sgdma.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_sgdma.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_sgdma.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_sgdma.c 2011-02-22 14:16:21.589230297 +0100 -@@ -74,8 +74,24 @@ - } - } - -+static void -+nouveau_sgdma_destroy(struct ttm_backend *be) -+{ -+ struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; -+ -+ if (be) { -+ NV_DEBUG(nvbe->dev, "\n"); -+ -+ if (nvbe) { -+ if (nvbe->pages) -+ be->func->clear(be); -+ kfree(nvbe); -+ } -+ } -+} -+ - static int --nouveau_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) -+nv04_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) - { - struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; - struct drm_device *dev = nvbe->dev; -@@ -102,7 +118,7 @@ - } - - static int --nouveau_sgdma_unbind(struct ttm_backend *be) -+nv04_sgdma_unbind(struct ttm_backend *be) - { - struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; - struct drm_device *dev = nvbe->dev; -@@ -125,59 +141,245 @@ - return 0; - } - -+static struct ttm_backend_func nv04_sgdma_backend = { -+ .populate = nouveau_sgdma_populate, -+ .clear = nouveau_sgdma_clear, -+ .bind = nv04_sgdma_bind, -+ .unbind = nv04_sgdma_unbind, -+ .destroy = nouveau_sgdma_destroy -+}; -+ - static void --nouveau_sgdma_destroy(struct ttm_backend *be) -+nv41_sgdma_flush(struct nouveau_sgdma_be *nvbe) -+{ -+ struct drm_device *dev = nvbe->dev; -+ -+ nv_wr32(dev, 0x100810, 0x00000022); -+ if (!nv_wait(dev, 0x100810, 0x00000100, 0x00000100)) -+ NV_ERROR(dev, "vm flush timeout: 0x%08x\n", -+ nv_rd32(dev, 0x100810)); -+ nv_wr32(dev, 0x100810, 0x00000000); -+} -+ -+static int -+nv41_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) - { - struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; -+ struct drm_nouveau_private *dev_priv = nvbe->dev->dev_private; -+ struct nouveau_gpuobj *pgt = dev_priv->gart_info.sg_ctxdma; -+ dma_addr_t *list = nvbe->pages; -+ u32 pte = mem->start << 2; -+ u32 cnt = nvbe->nr_pages; - -- if (be) { -- NV_DEBUG(nvbe->dev, "\n"); -+ nvbe->offset = mem->start << PAGE_SHIFT; - -- if (nvbe) { -- if (nvbe->pages) -- be->func->clear(be); -- kfree(nvbe); -+ while (cnt--) { -+ nv_wo32(pgt, pte, (*list++ >> 7) | 1); -+ pte += 4; -+ } -+ -+ nv41_sgdma_flush(nvbe); -+ nvbe->bound = true; -+ return 0; -+} -+ -+static int -+nv41_sgdma_unbind(struct ttm_backend *be) -+{ -+ struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; -+ struct drm_nouveau_private *dev_priv = nvbe->dev->dev_private; -+ struct nouveau_gpuobj *pgt = dev_priv->gart_info.sg_ctxdma; -+ u32 pte = (nvbe->offset >> 12) << 2; -+ u32 cnt = nvbe->nr_pages; -+ -+ while (cnt--) { -+ nv_wo32(pgt, pte, 0x00000000); -+ pte += 4; -+ } -+ -+ nv41_sgdma_flush(nvbe); -+ nvbe->bound = false; -+ return 0; -+} -+ -+static struct ttm_backend_func nv41_sgdma_backend = { -+ .populate = nouveau_sgdma_populate, -+ .clear = nouveau_sgdma_clear, -+ .bind = nv41_sgdma_bind, -+ .unbind = nv41_sgdma_unbind, -+ .destroy = nouveau_sgdma_destroy -+}; -+ -+static void -+nv44_sgdma_flush(struct nouveau_sgdma_be *nvbe) -+{ -+ struct drm_device *dev = nvbe->dev; -+ -+ nv_wr32(dev, 0x100814, (nvbe->nr_pages - 1) << 12); -+ nv_wr32(dev, 0x100808, nvbe->offset | 0x20); -+ if (!nv_wait(dev, 0x100808, 0x00000001, 0x00000001)) -+ NV_ERROR(dev, "gart flush timeout: 0x%08x\n", -+ nv_rd32(dev, 0x100808)); -+ nv_wr32(dev, 0x100808, 0x00000000); -+} -+ -+static void -+nv44_sgdma_fill(struct nouveau_gpuobj *pgt, dma_addr_t *list, u32 base, u32 cnt) -+{ -+ struct drm_nouveau_private *dev_priv = pgt->dev->dev_private; -+ dma_addr_t dummy = dev_priv->gart_info.dummy.addr; -+ u32 pte, tmp[4]; -+ -+ pte = base >> 2; -+ base &= ~0x0000000f; -+ -+ tmp[0] = nv_ro32(pgt, base + 0x0); -+ tmp[1] = nv_ro32(pgt, base + 0x4); -+ tmp[2] = nv_ro32(pgt, base + 0x8); -+ tmp[3] = nv_ro32(pgt, base + 0xc); -+ while (cnt--) { -+ u32 addr = list ? (*list++ >> 12) : (dummy >> 12); -+ switch (pte++ & 0x3) { -+ case 0: -+ tmp[0] &= ~0x07ffffff; -+ tmp[0] |= addr; -+ break; -+ case 1: -+ tmp[0] &= ~0xf8000000; -+ tmp[0] |= addr << 27; -+ tmp[1] &= ~0x003fffff; -+ tmp[1] |= addr >> 5; -+ break; -+ case 2: -+ tmp[1] &= ~0xffc00000; -+ tmp[1] |= addr << 22; -+ tmp[2] &= ~0x0001ffff; -+ tmp[2] |= addr >> 10; -+ break; -+ case 3: -+ tmp[2] &= ~0xfffe0000; -+ tmp[2] |= addr << 17; -+ tmp[3] &= ~0x00000fff; -+ tmp[3] |= addr >> 15; -+ break; - } - } -+ -+ tmp[3] |= 0x40000000; -+ -+ nv_wo32(pgt, base + 0x0, tmp[0]); -+ nv_wo32(pgt, base + 0x4, tmp[1]); -+ nv_wo32(pgt, base + 0x8, tmp[2]); -+ nv_wo32(pgt, base + 0xc, tmp[3]); - } - - static int --nv50_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) -+nv44_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) - { - struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; - struct drm_nouveau_private *dev_priv = nvbe->dev->dev_private; -+ struct nouveau_gpuobj *pgt = dev_priv->gart_info.sg_ctxdma; -+ dma_addr_t *list = nvbe->pages; -+ u32 pte = mem->start << 2, tmp[4]; -+ u32 cnt = nvbe->nr_pages; -+ int i; - - nvbe->offset = mem->start << PAGE_SHIFT; - -- nouveau_vm_map_sg(&dev_priv->gart_info.vma, nvbe->offset, -- nvbe->nr_pages << PAGE_SHIFT, nvbe->pages); -+ if (pte & 0x0000000c) { -+ u32 max = 4 - ((pte >> 2) & 0x3); -+ u32 part = (cnt > max) ? max : cnt; -+ nv44_sgdma_fill(pgt, list, pte, part); -+ pte += (part << 2); -+ list += part; -+ cnt -= part; -+ } -+ -+ while (cnt >= 4) { -+ for (i = 0; i < 4; i++) -+ tmp[i] = *list++ >> 12; -+ nv_wo32(pgt, pte + 0x0, tmp[0] >> 0 | tmp[1] << 27); -+ nv_wo32(pgt, pte + 0x4, tmp[1] >> 5 | tmp[2] << 22); -+ nv_wo32(pgt, pte + 0x8, tmp[2] >> 10 | tmp[3] << 17); -+ nv_wo32(pgt, pte + 0xc, tmp[3] >> 15 | 0x40000000); -+ pte += 0x10; -+ cnt -= 4; -+ } -+ -+ if (cnt) -+ nv44_sgdma_fill(pgt, list, pte, cnt); -+ -+ nv44_sgdma_flush(nvbe); - nvbe->bound = true; - return 0; - } - - static int --nv50_sgdma_unbind(struct ttm_backend *be) -+nv44_sgdma_unbind(struct ttm_backend *be) - { - struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; - struct drm_nouveau_private *dev_priv = nvbe->dev->dev_private; -+ struct nouveau_gpuobj *pgt = dev_priv->gart_info.sg_ctxdma; -+ u32 pte = (nvbe->offset >> 12) << 2; -+ u32 cnt = nvbe->nr_pages; -+ -+ if (pte & 0x0000000c) { -+ u32 max = 4 - ((pte >> 2) & 0x3); -+ u32 part = (cnt > max) ? max : cnt; -+ nv44_sgdma_fill(pgt, NULL, pte, part); -+ pte += (part << 2); -+ cnt -= part; -+ } - -- if (!nvbe->bound) -- return 0; -+ while (cnt >= 4) { -+ nv_wo32(pgt, pte + 0x0, 0x00000000); -+ nv_wo32(pgt, pte + 0x4, 0x00000000); -+ nv_wo32(pgt, pte + 0x8, 0x00000000); -+ nv_wo32(pgt, pte + 0xc, 0x00000000); -+ pte += 0x10; -+ cnt -= 4; -+ } - -- nouveau_vm_unmap_at(&dev_priv->gart_info.vma, nvbe->offset, -- nvbe->nr_pages << PAGE_SHIFT); -+ if (cnt) -+ nv44_sgdma_fill(pgt, NULL, pte, cnt); -+ -+ nv44_sgdma_flush(nvbe); - nvbe->bound = false; - return 0; - } - --static struct ttm_backend_func nouveau_sgdma_backend = { -+static struct ttm_backend_func nv44_sgdma_backend = { - .populate = nouveau_sgdma_populate, - .clear = nouveau_sgdma_clear, -- .bind = nouveau_sgdma_bind, -- .unbind = nouveau_sgdma_unbind, -+ .bind = nv44_sgdma_bind, -+ .unbind = nv44_sgdma_unbind, - .destroy = nouveau_sgdma_destroy - }; - -+static int -+nv50_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) -+{ -+ struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; -+ struct nouveau_mem *node = mem->mm_node; -+ /* noop: bound in move_notify() */ -+ node->pages = nvbe->pages; -+ nvbe->pages = (dma_addr_t *)node; -+ nvbe->bound = true; -+ return 0; -+} -+ -+static int -+nv50_sgdma_unbind(struct ttm_backend *be) -+{ -+ struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)be; -+ struct nouveau_mem *node = (struct nouveau_mem *)nvbe->pages; -+ /* noop: unbound in move_notify() */ -+ nvbe->pages = node->pages; -+ node->pages = NULL; -+ nvbe->bound = false; -+ return 0; -+} -+ - static struct ttm_backend_func nv50_sgdma_backend = { - .populate = nouveau_sgdma_populate, - .clear = nouveau_sgdma_clear, -@@ -198,10 +400,7 @@ - - nvbe->dev = dev; - -- if (dev_priv->card_type < NV_50) -- nvbe->backend.func = &nouveau_sgdma_backend; -- else -- nvbe->backend.func = &nv50_sgdma_backend; -+ nvbe->backend.func = dev_priv->gart_info.func; - return &nvbe->backend; - } - -@@ -210,21 +409,65 @@ - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_gpuobj *gpuobj = NULL; -- uint32_t aper_size, obj_size; -- int i, ret; -+ u32 aper_size, align; -+ int ret; - -- if (dev_priv->card_type < NV_50) { -- if(dev_priv->ramin_rsvd_vram < 2 * 1024 * 1024) -- aper_size = 64 * 1024 * 1024; -- else -- aper_size = 512 * 1024 * 1024; -- -- obj_size = (aper_size >> NV_CTXDMA_PAGE_SHIFT) * 4; -- obj_size += 8; /* ctxdma header */ -- -- ret = nouveau_gpuobj_new(dev, NULL, obj_size, 16, -- NVOBJ_FLAG_ZERO_ALLOC | -- NVOBJ_FLAG_ZERO_FREE, &gpuobj); -+ if (dev_priv->card_type >= NV_50 || -+ dev_priv->ramin_rsvd_vram >= 2 * 1024 * 1024) -+ aper_size = 512 * 1024 * 1024; -+ else -+ aper_size = 64 * 1024 * 1024; -+ -+ /* Dear NVIDIA, NV44+ would like proper present bits in PTEs for -+ * christmas. The cards before it have them, the cards after -+ * it have them, why is NV44 so unloved? -+ */ -+ dev_priv->gart_info.dummy.page = alloc_page(GFP_DMA32 | GFP_KERNEL); -+ if (!dev_priv->gart_info.dummy.page) -+ return -ENOMEM; -+ -+ dev_priv->gart_info.dummy.addr = -+ pci_map_page(dev->pdev, dev_priv->gart_info.dummy.page, -+ 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); -+ if (pci_dma_mapping_error(dev->pdev, dev_priv->gart_info.dummy.addr)) { -+ NV_ERROR(dev, "error mapping dummy page\n"); -+ __free_page(dev_priv->gart_info.dummy.page); -+ dev_priv->gart_info.dummy.page = NULL; -+ return -ENOMEM; -+ } -+ -+ if (dev_priv->card_type >= NV_50) { -+ dev_priv->gart_info.aper_base = 0; -+ dev_priv->gart_info.aper_size = aper_size; -+ dev_priv->gart_info.type = NOUVEAU_GART_HW; -+ dev_priv->gart_info.func = &nv50_sgdma_backend; -+ } else -+ if (drm_device_is_pcie(dev) && -+ dev_priv->chipset != 0x40 && dev_priv->chipset != 0x45) { -+ if (nv44_graph_class(dev)) { -+ dev_priv->gart_info.func = &nv44_sgdma_backend; -+ align = 512 * 1024; -+ } else { -+ dev_priv->gart_info.func = &nv41_sgdma_backend; -+ align = 16; -+ } -+ -+ ret = nouveau_gpuobj_new(dev, NULL, aper_size / 1024, align, -+ NVOBJ_FLAG_ZERO_ALLOC | -+ NVOBJ_FLAG_ZERO_FREE, &gpuobj); -+ if (ret) { -+ NV_ERROR(dev, "Error creating sgdma object: %d\n", ret); -+ return ret; -+ } -+ -+ dev_priv->gart_info.sg_ctxdma = gpuobj; -+ dev_priv->gart_info.aper_base = 0; -+ dev_priv->gart_info.aper_size = aper_size; -+ dev_priv->gart_info.type = NOUVEAU_GART_HW; -+ } else { -+ ret = nouveau_gpuobj_new(dev, NULL, (aper_size / 1024) + 8, 16, -+ NVOBJ_FLAG_ZERO_ALLOC | -+ NVOBJ_FLAG_ZERO_FREE, &gpuobj); - if (ret) { - NV_ERROR(dev, "Error creating sgdma object: %d\n", ret); - return ret; -@@ -236,25 +479,14 @@ - (0 << 14) /* RW */ | - (2 << 16) /* PCI */); - nv_wo32(gpuobj, 4, aper_size - 1); -- for (i = 2; i < 2 + (aper_size >> 12); i++) -- nv_wo32(gpuobj, i * 4, 0x00000000); - - dev_priv->gart_info.sg_ctxdma = gpuobj; - dev_priv->gart_info.aper_base = 0; - dev_priv->gart_info.aper_size = aper_size; -- } else -- if (dev_priv->chan_vm) { -- ret = nouveau_vm_get(dev_priv->chan_vm, 512 * 1024 * 1024, -- 12, NV_MEM_ACCESS_RW, -- &dev_priv->gart_info.vma); -- if (ret) -- return ret; -- -- dev_priv->gart_info.aper_base = dev_priv->gart_info.vma.offset; -- dev_priv->gart_info.aper_size = 512 * 1024 * 1024; -+ dev_priv->gart_info.type = NOUVEAU_GART_PDMA; -+ dev_priv->gart_info.func = &nv04_sgdma_backend; - } - -- dev_priv->gart_info.type = NOUVEAU_GART_SGDMA; - return 0; - } - -@@ -264,7 +496,13 @@ - struct drm_nouveau_private *dev_priv = dev->dev_private; - - nouveau_gpuobj_ref(NULL, &dev_priv->gart_info.sg_ctxdma); -- nouveau_vm_put(&dev_priv->gart_info.vma); -+ -+ if (dev_priv->gart_info.dummy.page) { -+ pci_unmap_page(dev->pdev, dev_priv->gart_info.dummy.addr, -+ PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); -+ __free_page(dev_priv->gart_info.dummy.page); -+ dev_priv->gart_info.dummy.page = NULL; -+ } - } - - uint32_t -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_state.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_state.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_state.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_state.c 2011-02-22 14:16:21.590230277 +0100 -@@ -544,7 +544,6 @@ - nouveau_card_init_channel(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_gpuobj *gpuobj = NULL; - int ret; - - ret = nouveau_channel_alloc(dev, &dev_priv->channel, -@@ -552,41 +551,8 @@ - if (ret) - return ret; - -- /* no dma objects on fermi... */ -- if (dev_priv->card_type >= NV_C0) -- goto out_done; -- -- ret = nouveau_gpuobj_dma_new(dev_priv->channel, NV_CLASS_DMA_IN_MEMORY, -- 0, dev_priv->vram_size, -- NV_MEM_ACCESS_RW, NV_MEM_TARGET_VRAM, -- &gpuobj); -- if (ret) -- goto out_err; -- -- ret = nouveau_ramht_insert(dev_priv->channel, NvDmaVRAM, gpuobj); -- nouveau_gpuobj_ref(NULL, &gpuobj); -- if (ret) -- goto out_err; -- -- ret = nouveau_gpuobj_dma_new(dev_priv->channel, NV_CLASS_DMA_IN_MEMORY, -- 0, dev_priv->gart_info.aper_size, -- NV_MEM_ACCESS_RW, NV_MEM_TARGET_GART, -- &gpuobj); -- if (ret) -- goto out_err; -- -- ret = nouveau_ramht_insert(dev_priv->channel, NvDmaGART, gpuobj); -- nouveau_gpuobj_ref(NULL, &gpuobj); -- if (ret) -- goto out_err; -- --out_done: - mutex_unlock(&dev_priv->channel->mutex); - return 0; -- --out_err: -- nouveau_channel_put(&dev_priv->channel); -- return ret; - } - - static void nouveau_switcheroo_set_state(struct pci_dev *pdev, -@@ -929,12 +895,6 @@ - NV_DEBUG(dev, "vendor: 0x%X device: 0x%X class: 0x%X\n", - dev->pci_vendor, dev->pci_device, dev->pdev->class); - -- dev_priv->wq = create_workqueue("nouveau"); -- if (!dev_priv->wq) { -- ret = -EINVAL; -- goto err_priv; -- } -- - /* resource 0 is mmio regs */ - /* resource 1 is linear FB */ - /* resource 2 is RAMIN (mmio regs + 0x1000000) */ -@@ -947,7 +907,7 @@ - NV_ERROR(dev, "Unable to initialize the mmio mapping. " - "Please report your setup to " DRIVER_EMAIL "\n"); - ret = -EINVAL; -- goto err_wq; -+ goto err_priv; - } - NV_DEBUG(dev, "regs mapped ok at 0x%llx\n", - (unsigned long long)mmio_start_offs); -@@ -1054,8 +1014,6 @@ - iounmap(dev_priv->ramin); - err_mmio: - iounmap(dev_priv->mmio); --err_wq: -- destroy_workqueue(dev_priv->wq); - err_priv: - kfree(dev_priv); - dev->dev_private = NULL; -@@ -1126,7 +1084,7 @@ - getparam->value = 1; - break; - case NOUVEAU_GETPARAM_HAS_PAGEFLIP: -- getparam->value = (dev_priv->card_type < NV_50); -+ getparam->value = 1; - break; - case NOUVEAU_GETPARAM_GRAPH_UNITS: - /* NV40 and NV50 versions are quite different, but register -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_temp.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_temp.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_temp.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_temp.c 2011-02-22 14:16:21.590230277 +0100 -@@ -239,11 +239,9 @@ - probe_monitoring_device(struct nouveau_i2c_chan *i2c, - struct i2c_board_info *info) - { -- char modalias[16] = "i2c:"; - struct i2c_client *client; - -- strlcat(modalias, info->type, sizeof(modalias)); -- request_module(modalias); -+ request_module("%s%s", I2C_MODULE_PREFIX, info->type); - - client = i2c_new_device(&i2c->adapter, info); - if (!client) -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_vm.c linux-2.6/drivers/gpu/drm/nouveau/nouveau_vm.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_vm.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_vm.c 2011-02-22 14:16:21.591230257 +0100 -@@ -28,7 +28,7 @@ - #include "nouveau_vm.h" - - void --nouveau_vm_map_at(struct nouveau_vma *vma, u64 delta, struct nouveau_vram *vram) -+nouveau_vm_map_at(struct nouveau_vma *vma, u64 delta, struct nouveau_mem *node) - { - struct nouveau_vm *vm = vma->vm; - struct nouveau_mm_node *r; -@@ -40,7 +40,8 @@ - u32 max = 1 << (vm->pgt_bits - bits); - u32 end, len; - -- list_for_each_entry(r, &vram->regions, rl_entry) { -+ delta = 0; -+ list_for_each_entry(r, &node->regions, rl_entry) { - u64 phys = (u64)r->offset << 12; - u32 num = r->length >> bits; - -@@ -52,7 +53,7 @@ - end = max; - len = end - pte; - -- vm->map(vma, pgt, vram, pte, len, phys); -+ vm->map(vma, pgt, node, pte, len, phys, delta); - - num -= len; - pte += len; -@@ -60,6 +61,8 @@ - pde++; - pte = 0; - } -+ -+ delta += (u64)len << vma->node->type; - } - } - -@@ -67,14 +70,14 @@ - } - - void --nouveau_vm_map(struct nouveau_vma *vma, struct nouveau_vram *vram) -+nouveau_vm_map(struct nouveau_vma *vma, struct nouveau_mem *node) - { -- nouveau_vm_map_at(vma, 0, vram); -+ nouveau_vm_map_at(vma, 0, node); - } - - void - nouveau_vm_map_sg(struct nouveau_vma *vma, u64 delta, u64 length, -- dma_addr_t *list) -+ struct nouveau_mem *mem, dma_addr_t *list) - { - struct nouveau_vm *vm = vma->vm; - int big = vma->node->type != vm->spg_shift; -@@ -94,7 +97,7 @@ - end = max; - len = end - pte; - -- vm->map_sg(vma, pgt, pte, list, len); -+ vm->map_sg(vma, pgt, mem, pte, len, list); - - num -= len; - pte += len; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_vm.h linux-2.6/drivers/gpu/drm/nouveau/nouveau_vm.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nouveau_vm.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nouveau_vm.h 2011-02-22 14:16:21.591230257 +0100 -@@ -67,9 +67,10 @@ - void (*map_pgt)(struct nouveau_gpuobj *pgd, u32 pde, - struct nouveau_gpuobj *pgt[2]); - void (*map)(struct nouveau_vma *, struct nouveau_gpuobj *, -- struct nouveau_vram *, u32 pte, u32 cnt, u64 phys); -+ struct nouveau_mem *, u32 pte, u32 cnt, -+ u64 phys, u64 delta); - void (*map_sg)(struct nouveau_vma *, struct nouveau_gpuobj *, -- u32 pte, dma_addr_t *, u32 cnt); -+ struct nouveau_mem *, u32 pte, u32 cnt, dma_addr_t *); - void (*unmap)(struct nouveau_gpuobj *pgt, u32 pte, u32 cnt); - void (*flush)(struct nouveau_vm *); - }; -@@ -82,20 +83,20 @@ - int nouveau_vm_get(struct nouveau_vm *, u64 size, u32 page_shift, - u32 access, struct nouveau_vma *); - void nouveau_vm_put(struct nouveau_vma *); --void nouveau_vm_map(struct nouveau_vma *, struct nouveau_vram *); --void nouveau_vm_map_at(struct nouveau_vma *, u64 offset, struct nouveau_vram *); -+void nouveau_vm_map(struct nouveau_vma *, struct nouveau_mem *); -+void nouveau_vm_map_at(struct nouveau_vma *, u64 offset, struct nouveau_mem *); - void nouveau_vm_unmap(struct nouveau_vma *); - void nouveau_vm_unmap_at(struct nouveau_vma *, u64 offset, u64 length); - void nouveau_vm_map_sg(struct nouveau_vma *, u64 offset, u64 length, -- dma_addr_t *); -+ struct nouveau_mem *, dma_addr_t *); - - /* nv50_vm.c */ - void nv50_vm_map_pgt(struct nouveau_gpuobj *pgd, u32 pde, - struct nouveau_gpuobj *pgt[2]); - void nv50_vm_map(struct nouveau_vma *, struct nouveau_gpuobj *, -- struct nouveau_vram *, u32 pte, u32 cnt, u64 phys); -+ struct nouveau_mem *, u32 pte, u32 cnt, u64 phys, u64 delta); - void nv50_vm_map_sg(struct nouveau_vma *, struct nouveau_gpuobj *, -- u32 pte, dma_addr_t *, u32 cnt); -+ struct nouveau_mem *, u32 pte, u32 cnt, dma_addr_t *); - void nv50_vm_unmap(struct nouveau_gpuobj *, u32 pte, u32 cnt); - void nv50_vm_flush(struct nouveau_vm *); - void nv50_vm_flush_engine(struct drm_device *, int engine); -@@ -104,9 +105,9 @@ - void nvc0_vm_map_pgt(struct nouveau_gpuobj *pgd, u32 pde, - struct nouveau_gpuobj *pgt[2]); - void nvc0_vm_map(struct nouveau_vma *, struct nouveau_gpuobj *, -- struct nouveau_vram *, u32 pte, u32 cnt, u64 phys); -+ struct nouveau_mem *, u32 pte, u32 cnt, u64 phys, u64 delta); - void nvc0_vm_map_sg(struct nouveau_vma *, struct nouveau_gpuobj *, -- u32 pte, dma_addr_t *, u32 cnt); -+ struct nouveau_mem *, u32 pte, u32 cnt, dma_addr_t *); - void nvc0_vm_unmap(struct nouveau_gpuobj *, u32 pte, u32 cnt); - void nvc0_vm_flush(struct nouveau_vm *); - -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv04_crtc.c linux-2.6/drivers/gpu/drm/nouveau/nv04_crtc.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv04_crtc.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv04_crtc.c 2011-02-22 14:16:21.592230236 +0100 -@@ -1031,7 +1031,7 @@ - drm_mode_crtc_set_gamma_size(&nv_crtc->base, 256); - - ret = nouveau_bo_new(dev, NULL, 64*64*4, 0x100, TTM_PL_FLAG_VRAM, -- 0, 0x0000, false, true, &nv_crtc->cursor.nvbo); -+ 0, 0x0000, &nv_crtc->cursor.nvbo); - if (!ret) { - ret = nouveau_bo_pin(nv_crtc->cursor.nvbo, TTM_PL_FLAG_VRAM); - if (!ret) -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv04_fifo.c linux-2.6/drivers/gpu/drm/nouveau/nv04_fifo.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv04_fifo.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv04_fifo.c 2011-02-22 14:16:21.593230215 +0100 -@@ -379,6 +379,15 @@ - return handled; - } - -+static const char *nv_dma_state_err(u32 state) -+{ -+ static const char * const desc[] = { -+ "NONE", "CALL_SUBR_ACTIVE", "INVALID_MTHD", "RET_SUBR_INACTIVE", -+ "INVALID_CMD", "IB_EMPTY"/* NV50+ */, "MEM_FAULT", "UNK" -+ }; -+ return desc[(state >> 29) & 0x7]; -+} -+ - void - nv04_fifo_isr(struct drm_device *dev) - { -@@ -460,9 +469,10 @@ - if (nouveau_ratelimit()) - NV_INFO(dev, "PFIFO_DMA_PUSHER - Ch %d Get 0x%02x%08x " - "Put 0x%02x%08x IbGet 0x%08x IbPut 0x%08x " -- "State 0x%08x Push 0x%08x\n", -+ "State 0x%08x (err: %s) Push 0x%08x\n", - chid, ho_get, dma_get, ho_put, - dma_put, ib_get, ib_put, state, -+ nv_dma_state_err(state), - push); - - /* METHOD_COUNT, in DMA_STATE on earlier chipsets */ -@@ -476,8 +486,9 @@ - } - } else { - NV_INFO(dev, "PFIFO_DMA_PUSHER - Ch %d Get 0x%08x " -- "Put 0x%08x State 0x%08x Push 0x%08x\n", -- chid, dma_get, dma_put, state, push); -+ "Put 0x%08x State 0x%08x (err: %s) Push 0x%08x\n", -+ chid, dma_get, dma_put, state, -+ nv_dma_state_err(state), push); - - if (dma_get != dma_put) - nv_wr32(dev, 0x003244, dma_put); -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv40_fb.c linux-2.6/drivers/gpu/drm/nouveau/nv40_fb.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv40_fb.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv40_fb.c 2011-02-22 14:16:21.596230155 +0100 -@@ -24,6 +24,53 @@ - } - } - -+static void -+nv40_fb_init_gart(struct drm_device *dev) -+{ -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nouveau_gpuobj *gart = dev_priv->gart_info.sg_ctxdma; -+ -+ if (dev_priv->gart_info.type != NOUVEAU_GART_HW) { -+ nv_wr32(dev, 0x100800, 0x00000001); -+ return; -+ } -+ -+ nv_wr32(dev, 0x100800, gart->pinst | 0x00000002); -+ nv_mask(dev, 0x10008c, 0x00000100, 0x00000100); -+ nv_wr32(dev, 0x100820, 0x00000000); -+} -+ -+static void -+nv44_fb_init_gart(struct drm_device *dev) -+{ -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nouveau_gpuobj *gart = dev_priv->gart_info.sg_ctxdma; -+ u32 vinst; -+ -+ if (dev_priv->gart_info.type != NOUVEAU_GART_HW) { -+ nv_wr32(dev, 0x100850, 0x80000000); -+ nv_wr32(dev, 0x100800, 0x00000001); -+ return; -+ } -+ -+ /* calculate vram address of this PRAMIN block, object -+ * must be allocated on 512KiB alignment, and not exceed -+ * a total size of 512KiB for this to work correctly -+ */ -+ vinst = nv_rd32(dev, 0x10020c); -+ vinst -= ((gart->pinst >> 19) + 1) << 19; -+ -+ nv_wr32(dev, 0x100850, 0x80000000); -+ nv_wr32(dev, 0x100818, dev_priv->gart_info.dummy.addr); -+ -+ nv_wr32(dev, 0x100804, dev_priv->gart_info.aper_size); -+ nv_wr32(dev, 0x100850, 0x00008000); -+ nv_mask(dev, 0x10008c, 0x00000200, 0x00000200); -+ nv_wr32(dev, 0x100820, 0x00000000); -+ nv_wr32(dev, 0x10082c, 0x00000001); -+ nv_wr32(dev, 0x100800, vinst | 0x00000010); -+} -+ - int - nv40_fb_init(struct drm_device *dev) - { -@@ -32,12 +79,12 @@ - uint32_t tmp; - int i; - -- /* This is strictly a NV4x register (don't know about NV5x). */ -- /* The blob sets these to all kinds of values, and they mess up our setup. */ -- /* I got value 0x52802 instead. For some cards the blob even sets it back to 0x1. */ -- /* Note: the blob doesn't read this value, so i'm pretty sure this is safe for all cards. */ -- /* Any idea what this is? */ -- nv_wr32(dev, NV40_PFB_UNK_800, 0x1); -+ if (dev_priv->chipset != 0x40 && dev_priv->chipset != 0x45) { -+ if (nv44_graph_class(dev)) -+ nv44_fb_init_gart(dev); -+ else -+ nv40_fb_init_gart(dev); -+ } - - switch (dev_priv->chipset) { - case 0x40: -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_crtc.c linux-2.6/drivers/gpu/drm/nouveau/nv50_crtc.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_crtc.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_crtc.c 2011-02-22 14:16:21.598230115 +0100 -@@ -65,7 +65,7 @@ - { - struct drm_device *dev = nv_crtc->base.dev; - struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - int index = nv_crtc->index, ret; - - NV_DEBUG_KMS(dev, "index %d\n", nv_crtc->index); -@@ -135,8 +135,7 @@ - nv50_crtc_set_dither(struct nouveau_crtc *nv_crtc, bool on, bool update) - { - struct drm_device *dev = nv_crtc->base.dev; -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - int ret; - - NV_DEBUG_KMS(dev, "\n"); -@@ -186,8 +185,7 @@ - struct nouveau_connector *nv_connector = - nouveau_crtc_connector_get(nv_crtc); - struct drm_device *dev = nv_crtc->base.dev; -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - struct drm_display_mode *native_mode = NULL; - struct drm_display_mode *mode = &nv_crtc->base.mode; - uint32_t outX, outY, horiz, vert; -@@ -445,6 +443,42 @@ - { - } - -+static int -+nv50_crtc_wait_complete(struct drm_crtc *crtc) -+{ -+ struct drm_device *dev = crtc->dev; -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nouveau_timer_engine *ptimer = &dev_priv->engine.timer; -+ struct nv50_display *disp = nv50_display(dev); -+ struct nouveau_channel *evo = disp->master; -+ u64 start; -+ int ret; -+ -+ ret = RING_SPACE(evo, 6); -+ if (ret) -+ return ret; -+ BEGIN_RING(evo, 0, 0x0084, 1); -+ OUT_RING (evo, 0x80000000); -+ BEGIN_RING(evo, 0, 0x0080, 1); -+ OUT_RING (evo, 0); -+ BEGIN_RING(evo, 0, 0x0084, 1); -+ OUT_RING (evo, 0x00000000); -+ -+ nv_wo32(disp->ntfy, 0x000, 0x00000000); -+ FIRE_RING (evo); -+ -+ start = ptimer->read(dev); -+ do { -+ nv_wr32(dev, 0x61002c, 0x370); -+ nv_wr32(dev, 0x000140, 1); -+ -+ if (nv_ro32(disp->ntfy, 0x000)) -+ return 0; -+ } while (ptimer->read(dev) - start < 2000000000ULL); -+ -+ return -EBUSY; -+} -+ - static void - nv50_crtc_prepare(struct drm_crtc *crtc) - { -@@ -453,6 +487,7 @@ - - NV_DEBUG_KMS(dev, "index %d\n", nv_crtc->index); - -+ nv50_display_flip_stop(crtc); - drm_vblank_pre_modeset(dev, nv_crtc->index); - nv50_crtc_blank(nv_crtc, true); - } -@@ -461,24 +496,14 @@ - nv50_crtc_commit(struct drm_crtc *crtc) - { - struct drm_device *dev = crtc->dev; -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; - struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); -- int ret; - - NV_DEBUG_KMS(dev, "index %d\n", nv_crtc->index); - - nv50_crtc_blank(nv_crtc, false); - drm_vblank_post_modeset(dev, nv_crtc->index); -- -- ret = RING_SPACE(evo, 2); -- if (ret) { -- NV_ERROR(dev, "no space while committing crtc\n"); -- return; -- } -- BEGIN_RING(evo, 0, NV50_EVO_UPDATE, 1); -- OUT_RING (evo, 0); -- FIRE_RING (evo); -+ nv50_crtc_wait_complete(crtc); -+ nv50_display_flip_next(crtc, crtc->fb, NULL); - } - - static bool -@@ -491,15 +516,15 @@ - static int - nv50_crtc_do_mode_set_base(struct drm_crtc *crtc, - struct drm_framebuffer *passed_fb, -- int x, int y, bool update, bool atomic) -+ int x, int y, bool atomic) - { - struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); - struct drm_device *dev = nv_crtc->base.dev; - struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - struct drm_framebuffer *drm_fb = nv_crtc->base.fb; - struct nouveau_framebuffer *fb = nouveau_framebuffer(drm_fb); -- int ret, format; -+ int ret; - - NV_DEBUG_KMS(dev, "index %d\n", nv_crtc->index); - -@@ -525,28 +550,6 @@ - } - } - -- switch (drm_fb->depth) { -- case 8: -- format = NV50_EVO_CRTC_FB_DEPTH_8; -- break; -- case 15: -- format = NV50_EVO_CRTC_FB_DEPTH_15; -- break; -- case 16: -- format = NV50_EVO_CRTC_FB_DEPTH_16; -- break; -- case 24: -- case 32: -- format = NV50_EVO_CRTC_FB_DEPTH_24; -- break; -- case 30: -- format = NV50_EVO_CRTC_FB_DEPTH_30; -- break; -- default: -- NV_ERROR(dev, "unknown depth %d\n", drm_fb->depth); -- return -EINVAL; -- } -- - nv_crtc->fb.offset = fb->nvbo->bo.mem.start << PAGE_SHIFT; - nv_crtc->fb.tile_flags = nouveau_bo_tile_layout(fb->nvbo); - nv_crtc->fb.cpp = drm_fb->bits_per_pixel / 8; -@@ -556,14 +559,7 @@ - return ret; - - BEGIN_RING(evo, 0, NV50_EVO_CRTC(nv_crtc->index, FB_DMA), 1); -- if (nv_crtc->fb.tile_flags == 0x7a00 || -- nv_crtc->fb.tile_flags == 0xfe00) -- OUT_RING(evo, NvEvoFB32); -- else -- if (nv_crtc->fb.tile_flags == 0x7000) -- OUT_RING(evo, NvEvoFB16); -- else -- OUT_RING(evo, NvEvoVRAM_LP); -+ OUT_RING (evo, fb->r_dma); - } - - ret = RING_SPACE(evo, 12); -@@ -571,45 +567,26 @@ - return ret; - - BEGIN_RING(evo, 0, NV50_EVO_CRTC(nv_crtc->index, FB_OFFSET), 5); -- OUT_RING(evo, nv_crtc->fb.offset >> 8); -- OUT_RING(evo, 0); -- OUT_RING(evo, (drm_fb->height << 16) | drm_fb->width); -- if (!nv_crtc->fb.tile_flags) { -- OUT_RING(evo, drm_fb->pitch | (1 << 20)); -- } else { -- u32 tile_mode = fb->nvbo->tile_mode; -- if (dev_priv->card_type >= NV_C0) -- tile_mode >>= 4; -- OUT_RING(evo, ((drm_fb->pitch / 4) << 4) | tile_mode); -- } -- if (dev_priv->chipset == 0x50) -- OUT_RING(evo, (nv_crtc->fb.tile_flags << 8) | format); -- else -- OUT_RING(evo, format); -+ OUT_RING (evo, nv_crtc->fb.offset >> 8); -+ OUT_RING (evo, 0); -+ OUT_RING (evo, (drm_fb->height << 16) | drm_fb->width); -+ OUT_RING (evo, fb->r_pitch); -+ OUT_RING (evo, fb->r_format); - - BEGIN_RING(evo, 0, NV50_EVO_CRTC(nv_crtc->index, CLUT_MODE), 1); -- OUT_RING(evo, fb->base.depth == 8 ? -- NV50_EVO_CRTC_CLUT_MODE_OFF : NV50_EVO_CRTC_CLUT_MODE_ON); -+ OUT_RING (evo, fb->base.depth == 8 ? -+ NV50_EVO_CRTC_CLUT_MODE_OFF : NV50_EVO_CRTC_CLUT_MODE_ON); - - BEGIN_RING(evo, 0, NV50_EVO_CRTC(nv_crtc->index, COLOR_CTRL), 1); -- OUT_RING(evo, NV50_EVO_CRTC_COLOR_CTRL_COLOR); -+ OUT_RING (evo, NV50_EVO_CRTC_COLOR_CTRL_COLOR); - BEGIN_RING(evo, 0, NV50_EVO_CRTC(nv_crtc->index, FB_POS), 1); -- OUT_RING(evo, (y << 16) | x); -+ OUT_RING (evo, (y << 16) | x); - - if (nv_crtc->lut.depth != fb->base.depth) { - nv_crtc->lut.depth = fb->base.depth; - nv50_crtc_lut_load(crtc); - } - -- if (update) { -- ret = RING_SPACE(evo, 2); -- if (ret) -- return ret; -- BEGIN_RING(evo, 0, NV50_EVO_UPDATE, 1); -- OUT_RING(evo, 0); -- FIRE_RING(evo); -- } -- - return 0; - } - -@@ -619,8 +596,7 @@ - struct drm_framebuffer *old_fb) - { - struct drm_device *dev = crtc->dev; -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); - struct nouveau_connector *nv_connector = NULL; - uint32_t hsync_dur, vsync_dur, hsync_start_to_end, vsync_start_to_end; -@@ -700,14 +676,25 @@ - nv_crtc->set_dither(nv_crtc, nv_connector->use_dithering, false); - nv_crtc->set_scale(nv_crtc, nv_connector->scaling_mode, false); - -- return nv50_crtc_do_mode_set_base(crtc, old_fb, x, y, false, false); -+ return nv50_crtc_do_mode_set_base(crtc, old_fb, x, y, false); - } - - static int - nv50_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, - struct drm_framebuffer *old_fb) - { -- return nv50_crtc_do_mode_set_base(crtc, old_fb, x, y, true, false); -+ int ret; -+ -+ nv50_display_flip_stop(crtc); -+ ret = nv50_crtc_do_mode_set_base(crtc, old_fb, x, y, false); -+ if (ret) -+ return ret; -+ -+ ret = nv50_crtc_wait_complete(crtc); -+ if (ret) -+ return ret; -+ -+ return nv50_display_flip_next(crtc, crtc->fb, NULL); - } - - static int -@@ -715,7 +702,14 @@ - struct drm_framebuffer *fb, - int x, int y, enum mode_set_atomic state) - { -- return nv50_crtc_do_mode_set_base(crtc, fb, x, y, true, true); -+ int ret; -+ -+ nv50_display_flip_stop(crtc); -+ ret = nv50_crtc_do_mode_set_base(crtc, fb, x, y, true); -+ if (ret) -+ return ret; -+ -+ return nv50_crtc_wait_complete(crtc); - } - - static const struct drm_crtc_helper_funcs nv50_crtc_helper_funcs = { -@@ -758,7 +752,7 @@ - nv_crtc->lut.depth = 0; - - ret = nouveau_bo_new(dev, NULL, 4096, 0x100, TTM_PL_FLAG_VRAM, -- 0, 0x0000, false, true, &nv_crtc->lut.nvbo); -+ 0, 0x0000, &nv_crtc->lut.nvbo); - if (!ret) { - ret = nouveau_bo_pin(nv_crtc->lut.nvbo, TTM_PL_FLAG_VRAM); - if (!ret) -@@ -784,7 +778,7 @@ - drm_mode_crtc_set_gamma_size(&nv_crtc->base, 256); - - ret = nouveau_bo_new(dev, NULL, 64*64*4, 0x100, TTM_PL_FLAG_VRAM, -- 0, 0x0000, false, true, &nv_crtc->cursor.nvbo); -+ 0, 0x0000, &nv_crtc->cursor.nvbo); - if (!ret) { - ret = nouveau_bo_pin(nv_crtc->cursor.nvbo, TTM_PL_FLAG_VRAM); - if (!ret) -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_cursor.c linux-2.6/drivers/gpu/drm/nouveau/nv50_cursor.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_cursor.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_cursor.c 2011-02-22 14:16:21.598230115 +0100 -@@ -36,9 +36,9 @@ - static void - nv50_cursor_show(struct nouveau_crtc *nv_crtc, bool update) - { -- struct drm_nouveau_private *dev_priv = nv_crtc->base.dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; - struct drm_device *dev = nv_crtc->base.dev; -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - int ret; - - NV_DEBUG_KMS(dev, "\n"); -@@ -71,9 +71,9 @@ - static void - nv50_cursor_hide(struct nouveau_crtc *nv_crtc, bool update) - { -- struct drm_nouveau_private *dev_priv = nv_crtc->base.dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; - struct drm_device *dev = nv_crtc->base.dev; -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - int ret; - - NV_DEBUG_KMS(dev, "\n"); -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_dac.c linux-2.6/drivers/gpu/drm/nouveau/nv50_dac.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_dac.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_dac.c 2011-02-22 14:16:21.599230095 +0100 -@@ -41,8 +41,7 @@ - { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - struct drm_device *dev = encoder->dev; -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - int ret; - - if (!nv_encoder->crtc) -@@ -216,8 +215,7 @@ - { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - struct drm_device *dev = encoder->dev; -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - struct nouveau_crtc *crtc = nouveau_crtc(encoder->crtc); - uint32_t mode_ctl = 0, mode_ctl2 = 0; - int ret; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_display.c linux-2.6/drivers/gpu/drm/nouveau/nv50_display.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_display.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_display.c 2011-02-22 14:16:21.599230095 +0100 -@@ -24,6 +24,7 @@ - * - */ - -+#define NOUVEAU_DMA_DEBUG (nouveau_reg_debug & NOUVEAU_REG_DEBUG_EVO) - #include "nv50_display.h" - #include "nouveau_crtc.h" - #include "nouveau_encoder.h" -@@ -34,6 +35,7 @@ - #include "drm_crtc_helper.h" - - static void nv50_display_isr(struct drm_device *); -+static void nv50_display_bh(unsigned long); - - static inline int - nv50_sor_nr(struct drm_device *dev) -@@ -172,16 +174,16 @@ - ret = nv50_evo_init(dev); - if (ret) - return ret; -- evo = dev_priv->evo; -+ evo = nv50_display(dev)->master; - - nv_wr32(dev, NV50_PDISPLAY_OBJECTS, (evo->ramin->vinst >> 8) | 9); - -- ret = RING_SPACE(evo, 11); -+ ret = RING_SPACE(evo, 15); - if (ret) - return ret; - BEGIN_RING(evo, 0, NV50_EVO_UNK84, 2); - OUT_RING(evo, NV50_EVO_UNK84_NOTIFY_DISABLED); -- OUT_RING(evo, NV50_EVO_DMA_NOTIFY_HANDLE_NONE); -+ OUT_RING(evo, NvEvoSync); - BEGIN_RING(evo, 0, NV50_EVO_CRTC(0, FB_DMA), 1); - OUT_RING(evo, NV50_EVO_CRTC_FB_DMA_HANDLE_NONE); - BEGIN_RING(evo, 0, NV50_EVO_CRTC(0, UNK0800), 1); -@@ -190,6 +192,11 @@ - OUT_RING(evo, 0); - BEGIN_RING(evo, 0, NV50_EVO_CRTC(0, UNK082C), 1); - OUT_RING(evo, 0); -+ /* required to make display sync channels not hate life */ -+ BEGIN_RING(evo, 0, NV50_EVO_CRTC(0, UNK900), 1); -+ OUT_RING (evo, 0x00000311); -+ BEGIN_RING(evo, 0, NV50_EVO_CRTC(1, UNK900), 1); -+ OUT_RING (evo, 0x00000311); - FIRE_RING(evo); - if (!nv_wait(dev, 0x640004, 0xffffffff, evo->dma.put << 2)) - NV_ERROR(dev, "evo pushbuf stalled\n"); -@@ -201,6 +208,8 @@ - static int nv50_display_disable(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nv50_display *disp = nv50_display(dev); -+ struct nouveau_channel *evo = disp->master; - struct drm_crtc *drm_crtc; - int ret, i; - -@@ -212,12 +221,12 @@ - nv50_crtc_blank(crtc, true); - } - -- ret = RING_SPACE(dev_priv->evo, 2); -+ ret = RING_SPACE(evo, 2); - if (ret == 0) { -- BEGIN_RING(dev_priv->evo, 0, NV50_EVO_UPDATE, 1); -- OUT_RING(dev_priv->evo, 0); -+ BEGIN_RING(evo, 0, NV50_EVO_UPDATE, 1); -+ OUT_RING(evo, 0); - } -- FIRE_RING(dev_priv->evo); -+ FIRE_RING(evo); - - /* Almost like ack'ing a vblank interrupt, maybe in the spirit of - * cleaning up? -@@ -267,10 +276,16 @@ - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct dcb_table *dcb = &dev_priv->vbios.dcb; - struct drm_connector *connector, *ct; -+ struct nv50_display *priv; - int ret, i; - - NV_DEBUG_KMS(dev, "\n"); - -+ priv = kzalloc(sizeof(*priv), GFP_KERNEL); -+ if (!priv) -+ return -ENOMEM; -+ dev_priv->engine.display.priv = priv; -+ - /* init basic kernel modesetting */ - drm_mode_config_init(dev); - -@@ -330,7 +345,7 @@ - } - } - -- INIT_WORK(&dev_priv->irq_work, nv50_display_irq_handler_bh); -+ tasklet_init(&priv->tasklet, nv50_display_bh, (unsigned long)dev); - nouveau_irq_register(dev, 26, nv50_display_isr); - - ret = nv50_display_init(dev); -@@ -345,12 +360,131 @@ - void - nv50_display_destroy(struct drm_device *dev) - { -+ struct nv50_display *disp = nv50_display(dev); -+ - NV_DEBUG_KMS(dev, "\n"); - - drm_mode_config_cleanup(dev); - - nv50_display_disable(dev); - nouveau_irq_unregister(dev, 26); -+ kfree(disp); -+} -+ -+void -+nv50_display_flip_stop(struct drm_crtc *crtc) -+{ -+ struct nv50_display *disp = nv50_display(crtc->dev); -+ struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); -+ struct nv50_display_crtc *dispc = &disp->crtc[nv_crtc->index]; -+ struct nouveau_channel *evo = dispc->sync; -+ int ret; -+ -+ ret = RING_SPACE(evo, 8); -+ if (ret) { -+ WARN_ON(1); -+ return; -+ } -+ -+ BEGIN_RING(evo, 0, 0x0084, 1); -+ OUT_RING (evo, 0x00000000); -+ BEGIN_RING(evo, 0, 0x0094, 1); -+ OUT_RING (evo, 0x00000000); -+ BEGIN_RING(evo, 0, 0x00c0, 1); -+ OUT_RING (evo, 0x00000000); -+ BEGIN_RING(evo, 0, 0x0080, 1); -+ OUT_RING (evo, 0x00000000); -+ FIRE_RING (evo); -+} -+ -+int -+nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb, -+ struct nouveau_channel *chan) -+{ -+ struct drm_nouveau_private *dev_priv = crtc->dev->dev_private; -+ struct nouveau_framebuffer *nv_fb = nouveau_framebuffer(fb); -+ struct nv50_display *disp = nv50_display(crtc->dev); -+ struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); -+ struct nv50_display_crtc *dispc = &disp->crtc[nv_crtc->index]; -+ struct nouveau_channel *evo = dispc->sync; -+ int ret; -+ -+ ret = RING_SPACE(evo, 24); -+ if (unlikely(ret)) -+ return ret; -+ -+ /* synchronise with the rendering channel, if necessary */ -+ if (likely(chan)) { -+ u64 offset = dispc->sem.bo->vma.offset + dispc->sem.offset; -+ -+ ret = RING_SPACE(chan, 10); -+ if (ret) { -+ WIND_RING(evo); -+ return ret; -+ } -+ -+ if (dev_priv->chipset < 0xc0) { -+ BEGIN_RING(chan, NvSubSw, 0x0060, 2); -+ OUT_RING (chan, NvEvoSema0 + nv_crtc->index); -+ OUT_RING (chan, dispc->sem.offset); -+ BEGIN_RING(chan, NvSubSw, 0x006c, 1); -+ OUT_RING (chan, 0xf00d0000 | dispc->sem.value); -+ BEGIN_RING(chan, NvSubSw, 0x0064, 2); -+ OUT_RING (chan, dispc->sem.offset ^ 0x10); -+ OUT_RING (chan, 0x74b1e000); -+ BEGIN_RING(chan, NvSubSw, 0x0060, 1); -+ if (dev_priv->chipset < 0x84) -+ OUT_RING (chan, NvSema); -+ else -+ OUT_RING (chan, chan->vram_handle); -+ } else { -+ BEGIN_NVC0(chan, 2, NvSubM2MF, 0x0010, 4); -+ OUT_RING (chan, upper_32_bits(offset)); -+ OUT_RING (chan, lower_32_bits(offset)); -+ OUT_RING (chan, 0xf00d0000 | dispc->sem.value); -+ OUT_RING (chan, 0x1002); -+ BEGIN_NVC0(chan, 2, NvSubM2MF, 0x0010, 4); -+ OUT_RING (chan, upper_32_bits(offset)); -+ OUT_RING (chan, lower_32_bits(offset ^ 0x10)); -+ OUT_RING (chan, 0x74b1e000); -+ OUT_RING (chan, 0x1001); -+ } -+ FIRE_RING (chan); -+ } else { -+ nouveau_bo_wr32(dispc->sem.bo, dispc->sem.offset / 4, -+ 0xf00d0000 | dispc->sem.value); -+ } -+ -+ /* queue the flip on the crtc's "display sync" channel */ -+ BEGIN_RING(evo, 0, 0x0100, 1); -+ OUT_RING (evo, 0xfffe0000); -+ BEGIN_RING(evo, 0, 0x0084, 5); -+ OUT_RING (evo, chan ? 0x00000100 : 0x00000010); -+ OUT_RING (evo, dispc->sem.offset); -+ OUT_RING (evo, 0xf00d0000 | dispc->sem.value); -+ OUT_RING (evo, 0x74b1e000); -+ OUT_RING (evo, NvEvoSync); -+ BEGIN_RING(evo, 0, 0x00a0, 2); -+ OUT_RING (evo, 0x00000000); -+ OUT_RING (evo, 0x00000000); -+ BEGIN_RING(evo, 0, 0x00c0, 1); -+ OUT_RING (evo, nv_fb->r_dma); -+ BEGIN_RING(evo, 0, 0x0110, 2); -+ OUT_RING (evo, 0x00000000); -+ OUT_RING (evo, 0x00000000); -+ BEGIN_RING(evo, 0, 0x0800, 5); -+ OUT_RING (evo, (nv_fb->nvbo->bo.mem.start << PAGE_SHIFT) >> 8); -+ OUT_RING (evo, 0); -+ OUT_RING (evo, (fb->height << 16) | fb->width); -+ OUT_RING (evo, nv_fb->r_pitch); -+ OUT_RING (evo, nv_fb->r_format); -+ BEGIN_RING(evo, 0, 0x0080, 1); -+ OUT_RING (evo, 0x00000000); -+ FIRE_RING (evo); -+ -+ dispc->sem.offset ^= 0x10; -+ dispc->sem.value++; -+ return 0; - } - - static u16 -@@ -466,11 +600,12 @@ - nv50_display_unk10_handler(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nv50_display *disp = nv50_display(dev); - u32 unk30 = nv_rd32(dev, 0x610030), mc; - int i, crtc, or, type = OUTPUT_ANY; - - NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30); -- dev_priv->evo_irq.dcb = NULL; -+ disp->irq.dcb = NULL; - - nv_wr32(dev, 0x619494, nv_rd32(dev, 0x619494) & ~8); - -@@ -541,7 +676,7 @@ - - if (dcb->type == type && (dcb->or & (1 << or))) { - nouveau_bios_run_display_table(dev, dcb, 0, -1); -- dev_priv->evo_irq.dcb = dcb; -+ disp->irq.dcb = dcb; - goto ack; - } - } -@@ -587,15 +722,16 @@ - nv50_display_unk20_handler(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -- u32 unk30 = nv_rd32(dev, 0x610030), tmp, pclk, script, mc; -+ struct nv50_display *disp = nv50_display(dev); -+ u32 unk30 = nv_rd32(dev, 0x610030), tmp, pclk, script, mc = 0; - struct dcb_entry *dcb; - int i, crtc, or, type = OUTPUT_ANY; - - NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30); -- dcb = dev_priv->evo_irq.dcb; -+ dcb = disp->irq.dcb; - if (dcb) { - nouveau_bios_run_display_table(dev, dcb, 0, -2); -- dev_priv->evo_irq.dcb = NULL; -+ disp->irq.dcb = NULL; - } - - /* CRTC clock change requested? */ -@@ -692,9 +828,9 @@ - nv_wr32(dev, NV50_PDISPLAY_DAC_CLK_CTRL2(or), 0); - } - -- dev_priv->evo_irq.dcb = dcb; -- dev_priv->evo_irq.pclk = pclk; -- dev_priv->evo_irq.script = script; -+ disp->irq.dcb = dcb; -+ disp->irq.pclk = pclk; -+ disp->irq.script = script; - - ack: - nv_wr32(dev, NV50_PDISPLAY_INTR_1, NV50_PDISPLAY_INTR_1_CLK_UNK20); -@@ -735,13 +871,13 @@ - static void - nv50_display_unk40_handler(struct drm_device *dev) - { -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct dcb_entry *dcb = dev_priv->evo_irq.dcb; -- u16 script = dev_priv->evo_irq.script; -- u32 unk30 = nv_rd32(dev, 0x610030), pclk = dev_priv->evo_irq.pclk; -+ struct nv50_display *disp = nv50_display(dev); -+ struct dcb_entry *dcb = disp->irq.dcb; -+ u16 script = disp->irq.script; -+ u32 unk30 = nv_rd32(dev, 0x610030), pclk = disp->irq.pclk; - - NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30); -- dev_priv->evo_irq.dcb = NULL; -+ disp->irq.dcb = NULL; - if (!dcb) - goto ack; - -@@ -754,12 +890,10 @@ - nv_wr32(dev, 0x619494, nv_rd32(dev, 0x619494) | 8); - } - --void --nv50_display_irq_handler_bh(struct work_struct *work) -+static void -+nv50_display_bh(unsigned long data) - { -- struct drm_nouveau_private *dev_priv = -- container_of(work, struct drm_nouveau_private, irq_work); -- struct drm_device *dev = dev_priv->dev; -+ struct drm_device *dev = (struct drm_device *)data; - - for (;;) { - uint32_t intr0 = nv_rd32(dev, NV50_PDISPLAY_INTR_0); -@@ -807,7 +941,7 @@ - static void - nv50_display_isr(struct drm_device *dev) - { -- struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nv50_display *disp = nv50_display(dev); - uint32_t delayed = 0; - - while (nv_rd32(dev, NV50_PMC_INTR_0) & NV50_PMC_INTR_0_DISPLAY) { -@@ -835,8 +969,7 @@ - NV50_PDISPLAY_INTR_1_CLK_UNK40)); - if (clock) { - nv_wr32(dev, NV03_PMC_INTR_EN_0, 0); -- if (!work_pending(&dev_priv->irq_work)) -- queue_work(dev_priv->wq, &dev_priv->irq_work); -+ tasklet_schedule(&disp->tasklet); - delayed |= clock; - intr1 &= ~clock; - } -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_display.h linux-2.6/drivers/gpu/drm/nouveau/nv50_display.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_display.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_display.h 2011-02-22 14:16:21.599230095 +0100 -@@ -35,7 +35,36 @@ - #include "nouveau_crtc.h" - #include "nv50_evo.h" - --void nv50_display_irq_handler_bh(struct work_struct *work); -+struct nv50_display_crtc { -+ struct nouveau_channel *sync; -+ struct { -+ struct nouveau_bo *bo; -+ u32 offset; -+ u16 value; -+ } sem; -+}; -+ -+struct nv50_display { -+ struct nouveau_channel *master; -+ struct nouveau_gpuobj *ntfy; -+ -+ struct nv50_display_crtc crtc[2]; -+ -+ struct tasklet_struct tasklet; -+ struct { -+ struct dcb_entry *dcb; -+ u16 script; -+ u32 pclk; -+ } irq; -+}; -+ -+static inline struct nv50_display * -+nv50_display(struct drm_device *dev) -+{ -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ return dev_priv->engine.display.priv; -+} -+ - int nv50_display_early_init(struct drm_device *dev); - void nv50_display_late_takedown(struct drm_device *dev); - int nv50_display_create(struct drm_device *dev); -@@ -44,4 +73,15 @@ - int nv50_crtc_blank(struct nouveau_crtc *, bool blank); - int nv50_crtc_set_clock(struct drm_device *, int head, int pclk); - -+int nv50_display_flip_next(struct drm_crtc *, struct drm_framebuffer *, -+ struct nouveau_channel *chan); -+void nv50_display_flip_stop(struct drm_crtc *); -+ -+int nv50_evo_init(struct drm_device *dev); -+void nv50_evo_fini(struct drm_device *dev); -+void nv50_evo_dmaobj_init(struct nouveau_gpuobj *, u32 memtype, u64 base, -+ u64 size); -+int nv50_evo_dmaobj_new(struct nouveau_channel *, u32 handle, u32 memtype, -+ u64 base, u64 size, struct nouveau_gpuobj **); -+ - #endif /* __NV50_DISPLAY_H__ */ -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_evo.c linux-2.6/drivers/gpu/drm/nouveau/nv50_evo.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_evo.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_evo.c 2011-02-22 14:16:21.599230095 +0100 -@@ -27,20 +27,17 @@ - #include "nouveau_drv.h" - #include "nouveau_dma.h" - #include "nouveau_ramht.h" -+#include "nv50_display.h" - - static void - nv50_evo_channel_del(struct nouveau_channel **pevo) - { -- struct drm_nouveau_private *dev_priv; - struct nouveau_channel *evo = *pevo; - - if (!evo) - return; - *pevo = NULL; - -- dev_priv = evo->dev->dev_private; -- dev_priv->evo_alloc &= ~(1 << evo->id); -- - nouveau_gpuobj_channel_takedown(evo); - nouveau_bo_unmap(evo->pushbuf_bo); - nouveau_bo_ref(NULL, &evo->pushbuf_bo); -@@ -51,42 +48,61 @@ - kfree(evo); - } - -+void -+nv50_evo_dmaobj_init(struct nouveau_gpuobj *obj, u32 memtype, u64 base, u64 size) -+{ -+ struct drm_nouveau_private *dev_priv = obj->dev->dev_private; -+ u32 flags5; -+ -+ if (dev_priv->chipset < 0xc0) { -+ /* not supported on 0x50, specified in format mthd */ -+ if (dev_priv->chipset == 0x50) -+ memtype = 0; -+ flags5 = 0x00010000; -+ } else { -+ if (memtype & 0x80000000) -+ flags5 = 0x00000000; /* large pages */ -+ else -+ flags5 = 0x00020000; -+ } -+ -+ nv50_gpuobj_dma_init(obj, 0, 0x3d, base, size, NV_MEM_TARGET_VRAM, -+ NV_MEM_ACCESS_RW, (memtype >> 8) & 0xff, 0); -+ nv_wo32(obj, 0x14, flags5); -+ dev_priv->engine.instmem.flush(obj->dev); -+} -+ - int --nv50_evo_dmaobj_new(struct nouveau_channel *evo, u32 class, u32 name, -- u32 tile_flags, u32 magic_flags, u32 offset, u32 limit, -- u32 flags5) -+nv50_evo_dmaobj_new(struct nouveau_channel *evo, u32 handle, u32 memtype, -+ u64 base, u64 size, struct nouveau_gpuobj **pobj) - { -- struct drm_nouveau_private *dev_priv = evo->dev->dev_private; -- struct drm_device *dev = evo->dev; -+ struct nv50_display *disp = nv50_display(evo->dev); - struct nouveau_gpuobj *obj = NULL; - int ret; - -- ret = nouveau_gpuobj_new(dev, dev_priv->evo, 6*4, 32, 0, &obj); -+ ret = nouveau_gpuobj_new(evo->dev, disp->master, 6*4, 32, 0, &obj); - if (ret) - return ret; - obj->engine = NVOBJ_ENGINE_DISPLAY; - -- nv_wo32(obj, 0, (tile_flags << 22) | (magic_flags << 16) | class); -- nv_wo32(obj, 4, limit); -- nv_wo32(obj, 8, offset); -- nv_wo32(obj, 12, 0x00000000); -- nv_wo32(obj, 16, 0x00000000); -- nv_wo32(obj, 20, flags5); -- dev_priv->engine.instmem.flush(dev); -+ nv50_evo_dmaobj_init(obj, memtype, base, size); - -- ret = nouveau_ramht_insert(evo, name, obj); -- nouveau_gpuobj_ref(NULL, &obj); -- if (ret) { -- return ret; -- } -+ ret = nouveau_ramht_insert(evo, handle, obj); -+ if (ret) -+ goto out; - -- return 0; -+ if (pobj) -+ nouveau_gpuobj_ref(obj, pobj); -+out: -+ nouveau_gpuobj_ref(NULL, &obj); -+ return ret; - } - - static int --nv50_evo_channel_new(struct drm_device *dev, struct nouveau_channel **pevo) -+nv50_evo_channel_new(struct drm_device *dev, int chid, -+ struct nouveau_channel **pevo) - { -- struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nv50_display *disp = nv50_display(dev); - struct nouveau_channel *evo; - int ret; - -@@ -95,25 +111,13 @@ - return -ENOMEM; - *pevo = evo; - -- for (evo->id = 0; evo->id < 5; evo->id++) { -- if (dev_priv->evo_alloc & (1 << evo->id)) -- continue; -- -- dev_priv->evo_alloc |= (1 << evo->id); -- break; -- } -- -- if (evo->id == 5) { -- kfree(evo); -- return -ENODEV; -- } -- -+ evo->id = chid; - evo->dev = dev; - evo->user_get = 4; - evo->user_put = 0; - - ret = nouveau_bo_new(dev, NULL, 4096, 0, TTM_PL_FLAG_VRAM, 0, 0, -- false, true, &evo->pushbuf_bo); -+ &evo->pushbuf_bo); - if (ret == 0) - ret = nouveau_bo_pin(evo->pushbuf_bo, TTM_PL_FLAG_VRAM); - if (ret) { -@@ -138,8 +142,8 @@ - } - - /* bind primary evo channel's ramht to the channel */ -- if (dev_priv->evo && evo != dev_priv->evo) -- nouveau_ramht_ref(dev_priv->evo->ramht, &evo->ramht, NULL); -+ if (disp->master && evo != disp->master) -+ nouveau_ramht_ref(disp->master->ramht, &evo->ramht, NULL); - - return 0; - } -@@ -212,21 +216,39 @@ - } - } - -+static void -+nv50_evo_destroy(struct drm_device *dev) -+{ -+ struct nv50_display *disp = nv50_display(dev); -+ int i; -+ -+ for (i = 0; i < 2; i++) { -+ if (disp->crtc[i].sem.bo) { -+ nouveau_bo_unmap(disp->crtc[i].sem.bo); -+ nouveau_bo_ref(NULL, &disp->crtc[i].sem.bo); -+ } -+ nv50_evo_channel_del(&disp->crtc[i].sync); -+ } -+ nouveau_gpuobj_ref(NULL, &disp->ntfy); -+ nv50_evo_channel_del(&disp->master); -+} -+ - static int - nv50_evo_create(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nv50_display *disp = nv50_display(dev); - struct nouveau_gpuobj *ramht = NULL; - struct nouveau_channel *evo; -- int ret; -+ int ret, i, j; - - /* create primary evo channel, the one we use for modesetting - * purporses - */ -- ret = nv50_evo_channel_new(dev, &dev_priv->evo); -+ ret = nv50_evo_channel_new(dev, 0, &disp->master); - if (ret) - return ret; -- evo = dev_priv->evo; -+ evo = disp->master; - - /* setup object management on it, any other evo channel will - * use this also as there's no per-channel support on the -@@ -236,109 +258,167 @@ - NVOBJ_FLAG_ZERO_ALLOC, &evo->ramin); - if (ret) { - NV_ERROR(dev, "Error allocating EVO channel memory: %d\n", ret); -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -+ goto err; - } - - ret = drm_mm_init(&evo->ramin_heap, 0, 32768); - if (ret) { - NV_ERROR(dev, "Error initialising EVO PRAMIN heap: %d\n", ret); -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -+ goto err; - } - - ret = nouveau_gpuobj_new(dev, evo, 4096, 16, 0, &ramht); - if (ret) { - NV_ERROR(dev, "Unable to allocate EVO RAMHT: %d\n", ret); -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -+ goto err; - } - - ret = nouveau_ramht_new(dev, ramht, &evo->ramht); - nouveau_gpuobj_ref(NULL, &ramht); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -- } -+ if (ret) -+ goto err; -+ -+ /* not sure exactly what this is.. -+ * -+ * the first dword of the structure is used by nvidia to wait on -+ * full completion of an EVO "update" command. -+ * -+ * method 0x8c on the master evo channel will fill a lot more of -+ * this structure with some undefined info -+ */ -+ ret = nouveau_gpuobj_new(dev, disp->master, 0x1000, 0, -+ NVOBJ_FLAG_ZERO_ALLOC, &disp->ntfy); -+ if (ret) -+ goto err; -+ -+ ret = nv50_evo_dmaobj_new(disp->master, NvEvoSync, 0x0000, -+ disp->ntfy->vinst, disp->ntfy->size, NULL); -+ if (ret) -+ goto err; - - /* create some default objects for the scanout memtypes we support */ -- if (dev_priv->card_type >= NV_C0) { -- ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoFB32, 0xfe, 0x19, -- 0, 0xffffffff, 0x00000000); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -- } -+ ret = nv50_evo_dmaobj_new(disp->master, NvEvoVRAM, 0x0000, -+ 0, dev_priv->vram_size, NULL); -+ if (ret) -+ goto err; - -- ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoVRAM, 0, 0x19, -- 0, dev_priv->vram_size, 0x00020000); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -- } -+ ret = nv50_evo_dmaobj_new(disp->master, NvEvoVRAM_LP, 0x80000000, -+ 0, dev_priv->vram_size, NULL); -+ if (ret) -+ goto err; - -- ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoVRAM_LP, 0, 0x19, -- 0, dev_priv->vram_size, 0x00000000); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -- } -- } else { -- ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoFB16, 0x70, 0x19, -- 0, 0xffffffff, 0x00010000); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -- } -+ ret = nv50_evo_dmaobj_new(disp->master, NvEvoFB32, 0x80000000 | -+ (dev_priv->chipset < 0xc0 ? 0x7a00 : 0xfe00), -+ 0, dev_priv->vram_size, NULL); -+ if (ret) -+ goto err; - -+ ret = nv50_evo_dmaobj_new(disp->master, NvEvoFB16, 0x80000000 | -+ (dev_priv->chipset < 0xc0 ? 0x7000 : 0xfe00), -+ 0, dev_priv->vram_size, NULL); -+ if (ret) -+ goto err; - -- ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoFB32, 0x7a, 0x19, -- 0, 0xffffffff, 0x00010000); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -- } -+ /* create "display sync" channels and other structures we need -+ * to implement page flipping -+ */ -+ for (i = 0; i < 2; i++) { -+ struct nv50_display_crtc *dispc = &disp->crtc[i]; -+ u64 offset; - -- ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoVRAM, 0, 0x19, -- 0, dev_priv->vram_size, 0x00010000); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -- } -+ ret = nv50_evo_channel_new(dev, 1 + i, &dispc->sync); -+ if (ret) -+ goto err; - -- ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoVRAM_LP, 0, 0x19, -- 0, dev_priv->vram_size, 0x00010000); -- if (ret) { -- nv50_evo_channel_del(&dev_priv->evo); -- return ret; -+ ret = nouveau_bo_new(dev, NULL, 4096, 0x1000, TTM_PL_FLAG_VRAM, -+ 0, 0x0000, &dispc->sem.bo); -+ if (!ret) { -+ offset = dispc->sem.bo->bo.mem.start << PAGE_SHIFT; -+ -+ ret = nouveau_bo_pin(dispc->sem.bo, TTM_PL_FLAG_VRAM); -+ if (!ret) -+ ret = nouveau_bo_map(dispc->sem.bo); -+ if (ret) -+ nouveau_bo_ref(NULL, &dispc->sem.bo); - } -+ -+ if (ret) -+ goto err; -+ -+ ret = nv50_evo_dmaobj_new(dispc->sync, NvEvoSync, 0x0000, -+ offset, 4096, NULL); -+ if (ret) -+ goto err; -+ -+ ret = nv50_evo_dmaobj_new(dispc->sync, NvEvoVRAM_LP, 0x80000000, -+ 0, dev_priv->vram_size, NULL); -+ if (ret) -+ goto err; -+ -+ ret = nv50_evo_dmaobj_new(dispc->sync, NvEvoFB32, 0x80000000 | -+ (dev_priv->chipset < 0xc0 ? -+ 0x7a00 : 0xfe00), -+ 0, dev_priv->vram_size, NULL); -+ if (ret) -+ goto err; -+ -+ ret = nv50_evo_dmaobj_new(dispc->sync, NvEvoFB16, 0x80000000 | -+ (dev_priv->chipset < 0xc0 ? -+ 0x7000 : 0xfe00), -+ 0, dev_priv->vram_size, NULL); -+ if (ret) -+ goto err; -+ -+ for (j = 0; j < 4096; j += 4) -+ nouveau_bo_wr32(dispc->sem.bo, j / 4, 0x74b1e000); -+ dispc->sem.offset = 0; - } - - return 0; -+ -+err: -+ nv50_evo_destroy(dev); -+ return ret; - } - - int - nv50_evo_init(struct drm_device *dev) - { -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- int ret; -+ struct nv50_display *disp = nv50_display(dev); -+ int ret, i; - -- if (!dev_priv->evo) { -+ if (!disp->master) { - ret = nv50_evo_create(dev); - if (ret) - return ret; - } - -- return nv50_evo_channel_init(dev_priv->evo); -+ ret = nv50_evo_channel_init(disp->master); -+ if (ret) -+ return ret; -+ -+ for (i = 0; i < 2; i++) { -+ ret = nv50_evo_channel_init(disp->crtc[i].sync); -+ if (ret) -+ return ret; -+ } -+ -+ return 0; - } - - void - nv50_evo_fini(struct drm_device *dev) - { -- struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nv50_display *disp = nv50_display(dev); -+ int i; - -- if (dev_priv->evo) { -- nv50_evo_channel_fini(dev_priv->evo); -- nv50_evo_channel_del(&dev_priv->evo); -+ for (i = 0; i < 2; i++) { -+ if (disp->crtc[i].sync) -+ nv50_evo_channel_fini(disp->crtc[i].sync); - } -+ -+ if (disp->master) -+ nv50_evo_channel_fini(disp->master); -+ -+ nv50_evo_destroy(dev); - } -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_evo.h linux-2.6/drivers/gpu/drm/nouveau/nv50_evo.h ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_evo.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_evo.h 2011-02-22 14:16:21.600230075 +0100 -@@ -27,12 +27,6 @@ - #ifndef __NV50_EVO_H__ - #define __NV50_EVO_H__ - --int nv50_evo_init(struct drm_device *dev); --void nv50_evo_fini(struct drm_device *dev); --int nv50_evo_dmaobj_new(struct nouveau_channel *, u32 class, u32 name, -- u32 tile_flags, u32 magic_flags, -- u32 offset, u32 limit); -- - #define NV50_EVO_UPDATE 0x00000080 - #define NV50_EVO_UNK84 0x00000084 - #define NV50_EVO_UNK84_NOTIFY 0x40000000 -@@ -119,5 +113,7 @@ - /* Both of these are needed, otherwise nothing happens. */ - #define NV50_EVO_CRTC_SCALE_RES1 0x000008d8 - #define NV50_EVO_CRTC_SCALE_RES2 0x000008dc -+#define NV50_EVO_CRTC_UNK900 0x00000900 -+#define NV50_EVO_CRTC_UNK904 0x00000904 - - #endif -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_fb.c linux-2.6/drivers/gpu/drm/nouveau/nv50_fb.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_fb.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_fb.c 2011-02-22 14:16:21.600230075 +0100 -@@ -8,31 +8,61 @@ - dma_addr_t r100c08; - }; - -+static void -+nv50_fb_destroy(struct drm_device *dev) -+{ -+ struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nouveau_fb_engine *pfb = &dev_priv->engine.fb; -+ struct nv50_fb_priv *priv = pfb->priv; -+ -+ if (pfb->tag_heap.free_stack.next) -+ drm_mm_takedown(&pfb->tag_heap); -+ -+ if (priv->r100c08_page) { -+ pci_unmap_page(dev->pdev, priv->r100c08, PAGE_SIZE, -+ PCI_DMA_BIDIRECTIONAL); -+ __free_page(priv->r100c08_page); -+ } -+ -+ kfree(priv); -+ pfb->priv = NULL; -+} -+ - static int - nv50_fb_create(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -+ struct nouveau_fb_engine *pfb = &dev_priv->engine.fb; - struct nv50_fb_priv *priv; -+ u32 tagmem; -+ int ret; - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; -+ pfb->priv = priv; - - priv->r100c08_page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!priv->r100c08_page) { -- kfree(priv); -+ nv50_fb_destroy(dev); - return -ENOMEM; - } - - priv->r100c08 = pci_map_page(dev->pdev, priv->r100c08_page, 0, - PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - if (pci_dma_mapping_error(dev->pdev, priv->r100c08)) { -- __free_page(priv->r100c08_page); -- kfree(priv); -+ nv50_fb_destroy(dev); - return -EFAULT; - } - -- dev_priv->engine.fb.priv = priv; -+ tagmem = nv_rd32(dev, 0x100320); -+ NV_DEBUG(dev, "%d tags available\n", tagmem); -+ ret = drm_mm_init(&pfb->tag_heap, 0, tagmem); -+ if (ret) { -+ nv50_fb_destroy(dev); -+ return ret; -+ } -+ - return 0; - } - -@@ -81,18 +111,7 @@ - void - nv50_fb_takedown(struct drm_device *dev) - { -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nv50_fb_priv *priv; -- -- priv = dev_priv->engine.fb.priv; -- if (!priv) -- return; -- dev_priv->engine.fb.priv = NULL; -- -- pci_unmap_page(dev->pdev, priv->r100c08, PAGE_SIZE, -- PCI_DMA_BIDIRECTIONAL); -- __free_page(priv->r100c08_page); -- kfree(priv); -+ nv50_fb_destroy(dev); - } - - void -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_fifo.c linux-2.6/drivers/gpu/drm/nouveau/nv50_fifo.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_fifo.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_fifo.c 2011-02-22 14:16:21.600230075 +0100 -@@ -149,6 +149,7 @@ - nv_wr32(dev, 0x3204, 0); - nv_wr32(dev, 0x3210, 0); - nv_wr32(dev, 0x3270, 0); -+ nv_wr32(dev, 0x2044, 0x01003fff); - - /* Enable dummy channels setup by nv50_instmem.c */ - nv50_fifo_channel_enable(dev, 0); -@@ -273,7 +274,7 @@ - nv_wo32(ramfc, 0x80, ((chan->ramht->bits - 9) << 27) | - (4 << 24) /* SEARCH_FULL */ | - (chan->ramht->gpuobj->cinst >> 4)); -- nv_wo32(ramfc, 0x44, 0x2101ffff); -+ nv_wo32(ramfc, 0x44, 0x01003fff); - nv_wo32(ramfc, 0x60, 0x7fffffff); - nv_wo32(ramfc, 0x40, 0x00000000); - nv_wo32(ramfc, 0x7c, 0x30000001); -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_gpio.c linux-2.6/drivers/gpu/drm/nouveau/nv50_gpio.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_gpio.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_gpio.c 2011-02-22 14:16:21.600230075 +0100 -@@ -137,6 +137,7 @@ - struct nv50_gpio_priv *priv = pgpio->priv; - struct nv50_gpio_handler *gpioh, *tmp; - struct dcb_gpio_entry *gpio; -+ LIST_HEAD(tofree); - unsigned long flags; - - gpio = nouveau_bios_gpio_entry(dev, tag); -@@ -149,10 +150,14 @@ - gpioh->handler != handler || - gpioh->data != data) - continue; -- list_del(&gpioh->head); -- kfree(gpioh); -+ list_move(&gpioh->head, &tofree); - } - spin_unlock_irqrestore(&priv->lock, flags); -+ -+ list_for_each_entry_safe(gpioh, tmp, &tofree, head) { -+ flush_work_sync(&gpioh->work); -+ kfree(gpioh); -+ } - } - - bool -@@ -205,7 +210,6 @@ - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_gpio_engine *pgpio = &dev_priv->engine.gpio; -- struct nv50_gpio_priv *priv; - int ret; - - if (!pgpio->priv) { -@@ -213,7 +217,6 @@ - if (ret) - return ret; - } -- priv = pgpio->priv; - - /* disable, and ack any pending gpio interrupts */ - nv_wr32(dev, 0xe050, 0x00000000); -@@ -293,7 +296,7 @@ - continue; - gpioh->inhibit = true; - -- queue_work(dev_priv->wq, &gpioh->work); -+ schedule_work(&gpioh->work); - } - spin_unlock(&priv->lock); - } -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_graph.c linux-2.6/drivers/gpu/drm/nouveau/nv50_graph.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_graph.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_graph.c 2011-02-22 14:16:21.601230054 +0100 -@@ -409,12 +409,7 @@ - nv50_graph_nvsw_mthd_page_flip(struct nouveau_channel *chan, - u32 class, u32 mthd, u32 data) - { -- struct nouveau_page_flip_state s; -- -- if (!nouveau_finish_page_flip(chan, &s)) { -- /* XXX - Do something here */ -- } -- -+ nouveau_finish_page_flip(chan, NULL); - return 0; - } - -@@ -912,10 +907,10 @@ - printk("\n"); - NV_INFO(dev, "PGRAPH - TRAP_CCACHE %08x %08x %08x %08x" - " %08x %08x %08x\n", -- nv_rd32(dev, 0x405800), nv_rd32(dev, 0x405804), -- nv_rd32(dev, 0x405808), nv_rd32(dev, 0x40580c), -- nv_rd32(dev, 0x405810), nv_rd32(dev, 0x405814), -- nv_rd32(dev, 0x40581c)); -+ nv_rd32(dev, 0x405000), nv_rd32(dev, 0x405004), -+ nv_rd32(dev, 0x405008), nv_rd32(dev, 0x40500c), -+ nv_rd32(dev, 0x405010), nv_rd32(dev, 0x405014), -+ nv_rd32(dev, 0x40501c)); - - } - -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_instmem.c linux-2.6/drivers/gpu/drm/nouveau/nv50_instmem.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_instmem.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_instmem.c 2011-02-22 14:16:21.602230033 +0100 -@@ -300,7 +300,7 @@ - } - - struct nv50_gpuobj_node { -- struct nouveau_vram *vram; -+ struct nouveau_mem *vram; - struct nouveau_vma chan_vma; - u32 align; - }; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_sor.c linux-2.6/drivers/gpu/drm/nouveau/nv50_sor.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_sor.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_sor.c 2011-02-22 14:16:21.603230013 +0100 -@@ -41,8 +41,7 @@ - { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - struct drm_device *dev = encoder->dev; -- struct drm_nouveau_private *dev_priv = dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(dev)->master; - int ret; - - if (!nv_encoder->crtc) -@@ -184,8 +183,7 @@ - nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) - { -- struct drm_nouveau_private *dev_priv = encoder->dev->dev_private; -- struct nouveau_channel *evo = dev_priv->evo; -+ struct nouveau_channel *evo = nv50_display(encoder->dev)->master; - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - struct drm_device *dev = encoder->dev; - struct nouveau_crtc *crtc = nouveau_crtc(encoder->crtc); -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_vm.c linux-2.6/drivers/gpu/drm/nouveau/nv50_vm.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_vm.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_vm.c 2011-02-22 14:16:21.603230013 +0100 -@@ -31,7 +31,6 @@ - nv50_vm_map_pgt(struct nouveau_gpuobj *pgd, u32 pde, - struct nouveau_gpuobj *pgt[2]) - { -- struct drm_nouveau_private *dev_priv = pgd->dev->dev_private; - u64 phys = 0xdeadcafe00000000ULL; - u32 coverage = 0; - -@@ -58,10 +57,9 @@ - } - - static inline u64 --nv50_vm_addr(struct nouveau_vma *vma, struct nouveau_gpuobj *pgt, -- u64 phys, u32 memtype, u32 target) -+nv50_vm_addr(struct nouveau_vma *vma, u64 phys, u32 memtype, u32 target) - { -- struct drm_nouveau_private *dev_priv = pgt->dev->dev_private; -+ struct drm_nouveau_private *dev_priv = vma->vm->dev->dev_private; - - phys |= 1; /* present */ - phys |= (u64)memtype << 40; -@@ -85,12 +83,13 @@ - - void - nv50_vm_map(struct nouveau_vma *vma, struct nouveau_gpuobj *pgt, -- struct nouveau_vram *mem, u32 pte, u32 cnt, u64 phys) -+ struct nouveau_mem *mem, u32 pte, u32 cnt, u64 phys, u64 delta) - { -+ u32 comp = (mem->memtype & 0x180) >> 7; - u32 block; - int i; - -- phys = nv50_vm_addr(vma, pgt, phys, mem->memtype, 0); -+ phys = nv50_vm_addr(vma, phys, mem->memtype, 0); - pte <<= 3; - cnt <<= 3; - -@@ -107,6 +106,11 @@ - - phys += block << (vma->node->type - 3); - cnt -= block; -+ if (comp) { -+ u32 tag = mem->tag->start + ((delta >> 16) * comp); -+ offset_h |= (tag << 17); -+ delta += block << (vma->node->type - 3); -+ } - - while (block) { - nv_wo32(pgt, pte + 0, offset_l); -@@ -119,11 +123,11 @@ - - void - nv50_vm_map_sg(struct nouveau_vma *vma, struct nouveau_gpuobj *pgt, -- u32 pte, dma_addr_t *list, u32 cnt) -+ struct nouveau_mem *mem, u32 pte, u32 cnt, dma_addr_t *list) - { - pte <<= 3; - while (cnt--) { -- u64 phys = nv50_vm_addr(vma, pgt, (u64)*list++, 0, 2); -+ u64 phys = nv50_vm_addr(vma, (u64)*list++, mem->memtype, 2); - nv_wo32(pgt, pte + 0, lower_32_bits(phys)); - nv_wo32(pgt, pte + 4, upper_32_bits(phys)); - pte += 8; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_vram.c linux-2.6/drivers/gpu/drm/nouveau/nv50_vram.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nv50_vram.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nv50_vram.c 2011-02-22 14:16:21.603230013 +0100 -@@ -48,42 +48,49 @@ - } - - void --nv50_vram_del(struct drm_device *dev, struct nouveau_vram **pvram) -+nv50_vram_del(struct drm_device *dev, struct nouveau_mem **pmem) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct ttm_bo_device *bdev = &dev_priv->ttm.bdev; - struct ttm_mem_type_manager *man = &bdev->man[TTM_PL_VRAM]; - struct nouveau_mm *mm = man->priv; - struct nouveau_mm_node *this; -- struct nouveau_vram *vram; -+ struct nouveau_mem *mem; - -- vram = *pvram; -- *pvram = NULL; -- if (unlikely(vram == NULL)) -+ mem = *pmem; -+ *pmem = NULL; -+ if (unlikely(mem == NULL)) - return; - - mutex_lock(&mm->mutex); -- while (!list_empty(&vram->regions)) { -- this = list_first_entry(&vram->regions, struct nouveau_mm_node, rl_entry); -+ while (!list_empty(&mem->regions)) { -+ this = list_first_entry(&mem->regions, struct nouveau_mm_node, rl_entry); - - list_del(&this->rl_entry); - nouveau_mm_put(mm, this); - } -+ -+ if (mem->tag) { -+ drm_mm_put_block(mem->tag); -+ mem->tag = NULL; -+ } - mutex_unlock(&mm->mutex); - -- kfree(vram); -+ kfree(mem); - } - - int - nv50_vram_new(struct drm_device *dev, u64 size, u32 align, u32 size_nc, -- u32 type, struct nouveau_vram **pvram) -+ u32 memtype, struct nouveau_mem **pmem) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct ttm_bo_device *bdev = &dev_priv->ttm.bdev; - struct ttm_mem_type_manager *man = &bdev->man[TTM_PL_VRAM]; - struct nouveau_mm *mm = man->priv; - struct nouveau_mm_node *r; -- struct nouveau_vram *vram; -+ struct nouveau_mem *mem; -+ int comp = (memtype & 0x300) >> 8; -+ int type = (memtype & 0x07f); - int ret; - - if (!types[type]) -@@ -92,32 +99,46 @@ - align >>= 12; - size_nc >>= 12; - -- vram = kzalloc(sizeof(*vram), GFP_KERNEL); -- if (!vram) -+ mem = kzalloc(sizeof(*mem), GFP_KERNEL); -+ if (!mem) - return -ENOMEM; - -- INIT_LIST_HEAD(&vram->regions); -- vram->dev = dev_priv->dev; -- vram->memtype = type; -- vram->size = size; -- - mutex_lock(&mm->mutex); -+ if (comp) { -+ if (align == 16) { -+ struct nouveau_fb_engine *pfb = &dev_priv->engine.fb; -+ int n = (size >> 4) * comp; -+ -+ mem->tag = drm_mm_search_free(&pfb->tag_heap, n, 0, 0); -+ if (mem->tag) -+ mem->tag = drm_mm_get_block(mem->tag, n, 0); -+ } -+ -+ if (unlikely(!mem->tag)) -+ comp = 0; -+ } -+ -+ INIT_LIST_HEAD(&mem->regions); -+ mem->dev = dev_priv->dev; -+ mem->memtype = (comp << 7) | type; -+ mem->size = size; -+ - do { - ret = nouveau_mm_get(mm, types[type], size, size_nc, align, &r); - if (ret) { - mutex_unlock(&mm->mutex); -- nv50_vram_del(dev, &vram); -+ nv50_vram_del(dev, &mem); - return ret; - } - -- list_add_tail(&r->rl_entry, &vram->regions); -+ list_add_tail(&r->rl_entry, &mem->regions); - size -= r->length; - } while (size); - mutex_unlock(&mm->mutex); - -- r = list_first_entry(&vram->regions, struct nouveau_mm_node, rl_entry); -- vram->offset = (u64)r->offset << 12; -- *pvram = vram; -+ r = list_first_entry(&mem->regions, struct nouveau_mm_node, rl_entry); -+ mem->offset = (u64)r->offset << 12; -+ *pmem = mem; - return 0; - } - -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_fifo.c linux-2.6/drivers/gpu/drm/nouveau/nvc0_fifo.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_fifo.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nvc0_fifo.c 2011-02-22 14:16:21.604229993 +0100 -@@ -116,7 +116,7 @@ - - /* allocate vram for control regs, map into polling area */ - ret = nouveau_bo_new(dev, NULL, 0x1000, 0, TTM_PL_FLAG_VRAM, -- 0, 0, true, true, &fifoch->user); -+ 0, 0, &fifoch->user); - if (ret) - goto error; - -@@ -418,6 +418,12 @@ - { - u32 stat = nv_rd32(dev, 0x002100); - -+ if (stat & 0x00000100) { -+ NV_INFO(dev, "PFIFO: unknown status 0x00000100\n"); -+ nv_wr32(dev, 0x002100, 0x00000100); -+ stat &= ~0x00000100; -+ } -+ - if (stat & 0x10000000) { - u32 units = nv_rd32(dev, 0x00259c); - u32 u = units; -@@ -446,10 +452,15 @@ - stat &= ~0x20000000; - } - -+ if (stat & 0x40000000) { -+ NV_INFO(dev, "PFIFO: unknown status 0x40000000\n"); -+ nv_mask(dev, 0x002a00, 0x00000000, 0x00000000); -+ stat &= ~0x40000000; -+ } -+ - if (stat) { - NV_INFO(dev, "PFIFO: unhandled status 0x%08x\n", stat); - nv_wr32(dev, 0x002100, stat); -+ nv_wr32(dev, 0x002140, 0); - } -- -- nv_wr32(dev, 0x2140, 0); - } -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_graph.c linux-2.6/drivers/gpu/drm/nouveau/nvc0_graph.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_graph.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nvc0_graph.c 2011-02-22 14:16:21.604229993 +0100 -@@ -299,6 +299,14 @@ - } - - static int -+nvc0_graph_mthd_page_flip(struct nouveau_channel *chan, -+ u32 class, u32 mthd, u32 data) -+{ -+ nouveau_finish_page_flip(chan, NULL); -+ return 0; -+} -+ -+static int - nvc0_graph_create(struct drm_device *dev) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; -@@ -395,6 +403,7 @@ - nouveau_irq_register(dev, 25, nvc0_runk140_isr); - NVOBJ_CLASS(dev, 0x902d, GR); /* 2D */ - NVOBJ_CLASS(dev, 0x9039, GR); /* M2MF */ -+ NVOBJ_MTHD (dev, 0x9039, 0x0500, nvc0_graph_mthd_page_flip); - NVOBJ_CLASS(dev, 0x9097, GR); /* 3D */ - NVOBJ_CLASS(dev, 0x90c0, GR); /* COMPUTE */ - return 0; -@@ -640,7 +649,6 @@ - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; -- struct nvc0_graph_priv *priv; - int ret; - - dev_priv->engine.graph.accel_blocked = true; -@@ -665,7 +673,6 @@ - if (ret) - return ret; - } -- priv = pgraph->priv; - - nvc0_graph_init_obj418880(dev); - nvc0_graph_init_regs(dev); -@@ -730,9 +737,12 @@ - u32 class = nv_rd32(dev, 0x404200 + (subc * 4)); - - if (stat & 0x00000010) { -- NV_INFO(dev, "PGRAPH: ILLEGAL_MTHD ch %d [0x%010llx] subc %d " -- "class 0x%04x mthd 0x%04x data 0x%08x\n", -- chid, inst, subc, class, mthd, data); -+ if (nouveau_gpuobj_mthd_call2(dev, chid, class, mthd, data)) { -+ NV_INFO(dev, "PGRAPH: ILLEGAL_MTHD ch %d [0x%010llx] " -+ "subc %d class 0x%04x mthd 0x%04x " -+ "data 0x%08x\n", -+ chid, inst, subc, class, mthd, data); -+ } - nv_wr32(dev, 0x400100, 0x00000010); - stat &= ~0x00000010; - } -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_vm.c linux-2.6/drivers/gpu/drm/nouveau/nvc0_vm.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_vm.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nvc0_vm.c 2011-02-22 14:16:21.606229953 +0100 -@@ -59,7 +59,7 @@ - - void - nvc0_vm_map(struct nouveau_vma *vma, struct nouveau_gpuobj *pgt, -- struct nouveau_vram *mem, u32 pte, u32 cnt, u64 phys) -+ struct nouveau_mem *mem, u32 pte, u32 cnt, u64 phys, u64 delta) - { - u32 next = 1 << (vma->node->type - 8); - -@@ -75,11 +75,11 @@ - - void - nvc0_vm_map_sg(struct nouveau_vma *vma, struct nouveau_gpuobj *pgt, -- u32 pte, dma_addr_t *list, u32 cnt) -+ struct nouveau_mem *mem, u32 pte, u32 cnt, dma_addr_t *list) - { - pte <<= 3; - while (cnt--) { -- u64 phys = nvc0_vm_addr(vma, *list++, 0, 5); -+ u64 phys = nvc0_vm_addr(vma, *list++, mem->memtype, 5); - nv_wo32(pgt, pte + 0, lower_32_bits(phys)); - nv_wo32(pgt, pte + 4, upper_32_bits(phys)); - pte += 8; -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_vram.c linux-2.6/drivers/gpu/drm/nouveau/nvc0_vram.c ---- linux-2.6.38-rc5/drivers/gpu/drm/nouveau/nvc0_vram.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/nouveau/nvc0_vram.c 2011-02-22 14:16:21.606229953 +0100 -@@ -26,64 +26,78 @@ - #include "nouveau_drv.h" - #include "nouveau_mm.h" - -+/* 0 = unsupported -+ * 1 = non-compressed -+ * 3 = compressed -+ */ -+static const u8 types[256] = { -+ 1, 1, 3, 3, 3, 3, 0, 3, 3, 3, 3, 0, 0, 0, 0, 0, -+ 0, 1, 0, 0, 0, 0, 0, 3, 3, 3, 3, 0, 0, 0, 0, 0, -+ 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, -+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 3, 3, 3, 3, -+ 3, 3, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, -+ 0, 3, 3, 3, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, -+ 0, 0, 0, 0, 0, 0, 3, 3, 3, 3, 0, 1, 1, 1, 1, 0, -+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -+ 0, 0, 0, 3, 3, 3, 3, 1, 1, 1, 1, 0, 0, 0, 0, 0, -+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, -+ 3, 3, 3, 3, 0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 3, 3, -+ 3, 3, 0, 0, 0, 0, 0, 0, 3, 0, 0, 3, 0, 3, 0, 3, -+ 3, 0, 3, 3, 3, 3, 3, 0, 0, 3, 0, 3, 0, 3, 3, 0, -+ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 0, 1, 1, 0 -+}; -+ - bool - nvc0_vram_flags_valid(struct drm_device *dev, u32 tile_flags) - { -- switch (tile_flags & NOUVEAU_GEM_TILE_LAYOUT_MASK) { -- case 0x0000: -- case 0xfe00: -- case 0xdb00: -- case 0x1100: -- return true; -- default: -- break; -- } -- -- return false; -+ u8 memtype = (tile_flags & NOUVEAU_GEM_TILE_LAYOUT_MASK) >> 8; -+ return likely((types[memtype] == 1)); - } - - int - nvc0_vram_new(struct drm_device *dev, u64 size, u32 align, u32 ncmin, -- u32 type, struct nouveau_vram **pvram) -+ u32 type, struct nouveau_mem **pmem) - { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct ttm_bo_device *bdev = &dev_priv->ttm.bdev; - struct ttm_mem_type_manager *man = &bdev->man[TTM_PL_VRAM]; - struct nouveau_mm *mm = man->priv; - struct nouveau_mm_node *r; -- struct nouveau_vram *vram; -+ struct nouveau_mem *mem; - int ret; - - size >>= 12; - align >>= 12; - ncmin >>= 12; - -- vram = kzalloc(sizeof(*vram), GFP_KERNEL); -- if (!vram) -+ mem = kzalloc(sizeof(*mem), GFP_KERNEL); -+ if (!mem) - return -ENOMEM; - -- INIT_LIST_HEAD(&vram->regions); -- vram->dev = dev_priv->dev; -- vram->memtype = type; -- vram->size = size; -+ INIT_LIST_HEAD(&mem->regions); -+ mem->dev = dev_priv->dev; -+ mem->memtype = (type & 0xff); -+ mem->size = size; - - mutex_lock(&mm->mutex); - do { - ret = nouveau_mm_get(mm, 1, size, ncmin, align, &r); - if (ret) { - mutex_unlock(&mm->mutex); -- nv50_vram_del(dev, &vram); -+ nv50_vram_del(dev, &mem); - return ret; - } - -- list_add_tail(&r->rl_entry, &vram->regions); -+ list_add_tail(&r->rl_entry, &mem->regions); - size -= r->length; - } while (size); - mutex_unlock(&mm->mutex); - -- r = list_first_entry(&vram->regions, struct nouveau_mm_node, rl_entry); -- vram->offset = (u64)r->offset << 12; -- *pvram = vram; -+ r = list_first_entry(&mem->regions, struct nouveau_mm_node, rl_entry); -+ mem->offset = (u64)r->offset << 12; -+ *pmem = mem; - return 0; - } - -diff -Naur linux-2.6.38-rc5/drivers/gpu/drm/ttm/ttm_bo.c linux-2.6/drivers/gpu/drm/ttm/ttm_bo.c ---- linux-2.6.38-rc5/drivers/gpu/drm/ttm/ttm_bo.c 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/drivers/gpu/drm/ttm/ttm_bo.c 2011-02-22 14:16:21.822225582 +0100 -@@ -406,11 +406,12 @@ - } - - if (bo->mem.mem_type == TTM_PL_SYSTEM) { -+ if (bdev->driver->move_notify) -+ bdev->driver->move_notify(bo, mem); - bo->mem = *mem; - mem->mm_node = NULL; - goto moved; - } -- - } - - if (bdev->driver->move_notify) -diff -Naur linux-2.6.38-rc5/include/drm/nouveau_drm.h linux-2.6/include/drm/nouveau_drm.h ---- linux-2.6.38-rc5/include/drm/nouveau_drm.h 2011-02-16 04:23:45.000000000 +0100 -+++ linux-2.6/include/drm/nouveau_drm.h 2011-02-22 14:16:28.891082551 +0100 -@@ -94,6 +94,7 @@ - #define NOUVEAU_GEM_DOMAIN_GART (1 << 2) - #define NOUVEAU_GEM_DOMAIN_MAPPABLE (1 << 3) - -+#define NOUVEAU_GEM_TILE_COMP 0x00030000 /* nv50-only */ - #define NOUVEAU_GEM_TILE_LAYOUT_MASK 0x0000ff00 - #define NOUVEAU_GEM_TILE_16BPP 0x00000001 - #define NOUVEAU_GEM_TILE_32BPP 0x00000002 diff --git a/packages/linux/patches/linux-2.6.38-rc8-700_701-730_BFS_patches.txt b/packages/linux/patches/linux-2.6.38-rc8-700_701-730_BFS_patches.txt deleted file mode 100644 index 61f91594ef..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-700_701-730_BFS_patches.txt +++ /dev/null @@ -1,20 +0,0 @@ -http://www.kernel.org/pub/linux/kernel/people/ck/patches/2.6/2.6.37/2.6.37-ck2/patches/ - -2.6.37-sched-bfs-363.patch -2637-bfs363-nonhotplug_fix.patch -sched-add-above-background-load-function.patch -mm-zero_swappiness.patch -mm-enable_swaptoken_only_when_swap_full.patch -mm-drop_swap_cache_aggressively.patch -mm-kswapd_inherit_prio-1.patch -mm-background_scan.patch -mm-idleprio_prio-1.patch -mm-lru_cache_add_lru_tail.patch -mm-decrease_default_dirty_ratio.patch -kconfig-expose_vmsplit_option.patch -hz-default_1000.patch -hz-no_default_250.patch -hz-raise_max.patch -preempt-desktop-tune.patch -cpufreq-bfs_tweaks.patch -ck2-version.patch \ No newline at end of file diff --git a/packages/linux/patches/linux-2.6.38-rc8-701_sched-bfs-363.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-701_sched-bfs-363.patch.disabled deleted file mode 100644 index 77a4076fdc..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-701_sched-bfs-363.patch.disabled +++ /dev/null @@ -1,8243 +0,0 @@ -The Brain Fuck Scheduler v0.363 by Con Kolivas. - -A single shared runqueue O(n) strict fairness earliest deadline first design. - -Ultra low latency and excellent desktop performance for 1 to many CPUs. -Not recommended for 4096 cpus. - -Scalability is optimal when your workload is equal to the number of CPUs on -bfs. ie you should ONLY do make -j4 on quad core, -j2 on dual core and so on. - -Features SCHED_IDLEPRIO and SCHED_ISO scheduling policies as well. -You do NOT need to use these policies for good performance, they are purely -optional for even better performance in extreme conditions. - -To run something idleprio, use schedtool like so: - -schedtool -D -e make -j4 - -To run something isoprio, use schedtool like so: - -schedtool -I -e amarok - -Includes accurate sub-tick accounting of tasks so userspace reported -cpu usage may be very different if you have very short lived tasks. - --ck - ---- - Documentation/scheduler/sched-BFS.txt | 351 + - Documentation/sysctl/kernel.txt | 26 - arch/powerpc/platforms/cell/spufs/sched.c | 5 - fs/proc/base.c | 2 - include/linux/init_task.h | 63 - include/linux/ioprio.h | 2 - include/linux/jiffies.h | 2 - include/linux/sched.h | 91 - init/Kconfig | 16 - init/main.c | 1 - kernel/delayacct.c | 2 - kernel/exit.c | 2 - kernel/kthread.c | 2 - kernel/posix-cpu-timers.c | 14 - kernel/sched.c | 4 - kernel/sched_bfs.c | 7223 ++++++++++++++++++++++++++++++ - kernel/sysctl.c | 31 - lib/Kconfig.debug | 2 - 18 files changed, 7812 insertions(+), 27 deletions(-) - -Index: linux-2.6.37-ck2/arch/powerpc/platforms/cell/spufs/sched.c -=================================================================== ---- linux-2.6.37-ck2.orig/arch/powerpc/platforms/cell/spufs/sched.c 2010-05-17 18:51:19.000000000 +1000 -+++ linux-2.6.37-ck2/arch/powerpc/platforms/cell/spufs/sched.c 2011-02-14 09:47:50.982252001 +1100 -@@ -64,11 +64,6 @@ - static struct timer_list spuloadavg_timer; - - /* -- * Priority of a normal, non-rt, non-niced'd process (aka nice level 0). -- */ --#define NORMAL_PRIO 120 -- --/* - * Frequency of the spu scheduler tick. By default we do one SPU scheduler - * tick for every 10 CPU scheduler ticks. - */ -Index: linux-2.6.37-ck2/Documentation/scheduler/sched-BFS.txt -=================================================================== ---- /dev/null 1970-01-01 00:00:00.000000000 +0000 -+++ linux-2.6.37-ck2/Documentation/scheduler/sched-BFS.txt 2011-02-14 09:47:50.984252001 +1100 -@@ -0,0 +1,351 @@ -+BFS - The Brain Fuck Scheduler by Con Kolivas. -+ -+Goals. -+ -+The goal of the Brain Fuck Scheduler, referred to as BFS from here on, is to -+completely do away with the complex designs of the past for the cpu process -+scheduler and instead implement one that is very simple in basic design. -+The main focus of BFS is to achieve excellent desktop interactivity and -+responsiveness without heuristics and tuning knobs that are difficult to -+understand, impossible to model and predict the effect of, and when tuned to -+one workload cause massive detriment to another. -+ -+ -+Design summary. -+ -+BFS is best described as a single runqueue, O(n) lookup, earliest effective -+virtual deadline first design, loosely based on EEVDF (earliest eligible virtual -+deadline first) and my previous Staircase Deadline scheduler. Each component -+shall be described in order to understand the significance of, and reasoning for -+it. The codebase when the first stable version was released was approximately -+9000 lines less code than the existing mainline linux kernel scheduler (in -+2.6.31). This does not even take into account the removal of documentation and -+the cgroups code that is not used. -+ -+Design reasoning. -+ -+The single runqueue refers to the queued but not running processes for the -+entire system, regardless of the number of CPUs. The reason for going back to -+a single runqueue design is that once multiple runqueues are introduced, -+per-CPU or otherwise, there will be complex interactions as each runqueue will -+be responsible for the scheduling latency and fairness of the tasks only on its -+own runqueue, and to achieve fairness and low latency across multiple CPUs, any -+advantage in throughput of having CPU local tasks causes other disadvantages. -+This is due to requiring a very complex balancing system to at best achieve some -+semblance of fairness across CPUs and can only maintain relatively low latency -+for tasks bound to the same CPUs, not across them. To increase said fairness -+and latency across CPUs, the advantage of local runqueue locking, which makes -+for better scalability, is lost due to having to grab multiple locks. -+ -+A significant feature of BFS is that all accounting is done purely based on CPU -+used and nowhere is sleep time used in any way to determine entitlement or -+interactivity. Interactivity "estimators" that use some kind of sleep/run -+algorithm are doomed to fail to detect all interactive tasks, and to falsely tag -+tasks that aren't interactive as being so. The reason for this is that it is -+close to impossible to determine that when a task is sleeping, whether it is -+doing it voluntarily, as in a userspace application waiting for input in the -+form of a mouse click or otherwise, or involuntarily, because it is waiting for -+another thread, process, I/O, kernel activity or whatever. Thus, such an -+estimator will introduce corner cases, and more heuristics will be required to -+cope with those corner cases, introducing more corner cases and failed -+interactivity detection and so on. Interactivity in BFS is built into the design -+by virtue of the fact that tasks that are waking up have not used up their quota -+of CPU time, and have earlier effective deadlines, thereby making it very likely -+they will preempt any CPU bound task of equivalent nice level. See below for -+more information on the virtual deadline mechanism. Even if they do not preempt -+a running task, because the rr interval is guaranteed to have a bound upper -+limit on how long a task will wait for, it will be scheduled within a timeframe -+that will not cause visible interface jitter. -+ -+ -+Design details. -+ -+Task insertion. -+ -+BFS inserts tasks into each relevant queue as an O(1) insertion into a double -+linked list. On insertion, *every* running queue is checked to see if the newly -+queued task can run on any idle queue, or preempt the lowest running task on the -+system. This is how the cross-CPU scheduling of BFS achieves significantly lower -+latency per extra CPU the system has. In this case the lookup is, in the worst -+case scenario, O(n) where n is the number of CPUs on the system. -+ -+Data protection. -+ -+BFS has one single lock protecting the process local data of every task in the -+global queue. Thus every insertion, removal and modification of task data in the -+global runqueue needs to grab the global lock. However, once a task is taken by -+a CPU, the CPU has its own local data copy of the running process' accounting -+information which only that CPU accesses and modifies (such as during a -+timer tick) thus allowing the accounting data to be updated lockless. Once a -+CPU has taken a task to run, it removes it from the global queue. Thus the -+global queue only ever has, at most, -+ -+ (number of tasks requesting cpu time) - (number of logical CPUs) + 1 -+ -+tasks in the global queue. This value is relevant for the time taken to look up -+tasks during scheduling. This will increase if many tasks with CPU affinity set -+in their policy to limit which CPUs they're allowed to run on if they outnumber -+the number of CPUs. The +1 is because when rescheduling a task, the CPU's -+currently running task is put back on the queue. Lookup will be described after -+the virtual deadline mechanism is explained. -+ -+Virtual deadline. -+ -+The key to achieving low latency, scheduling fairness, and "nice level" -+distribution in BFS is entirely in the virtual deadline mechanism. The one -+tunable in BFS is the rr_interval, or "round robin interval". This is the -+maximum time two SCHED_OTHER (or SCHED_NORMAL, the common scheduling policy) -+tasks of the same nice level will be running for, or looking at it the other -+way around, the longest duration two tasks of the same nice level will be -+delayed for. When a task requests cpu time, it is given a quota (time_slice) -+equal to the rr_interval and a virtual deadline. The virtual deadline is -+offset from the current time in jiffies by this equation: -+ -+ jiffies + (prio_ratio * rr_interval) -+ -+The prio_ratio is determined as a ratio compared to the baseline of nice -20 -+and increases by 10% per nice level. The deadline is a virtual one only in that -+no guarantee is placed that a task will actually be scheduled by this time, but -+it is used to compare which task should go next. There are three components to -+how a task is next chosen. First is time_slice expiration. If a task runs out -+of its time_slice, it is descheduled, the time_slice is refilled, and the -+deadline reset to that formula above. Second is sleep, where a task no longer -+is requesting CPU for whatever reason. The time_slice and deadline are _not_ -+adjusted in this case and are just carried over for when the task is next -+scheduled. Third is preemption, and that is when a newly waking task is deemed -+higher priority than a currently running task on any cpu by virtue of the fact -+that it has an earlier virtual deadline than the currently running task. The -+earlier deadline is the key to which task is next chosen for the first and -+second cases. Once a task is descheduled, it is put back on the queue, and an -+O(n) lookup of all queued-but-not-running tasks is done to determine which has -+the earliest deadline and that task is chosen to receive CPU next. -+ -+The CPU proportion of different nice tasks works out to be approximately the -+ -+ (prio_ratio difference)^2 -+ -+The reason it is squared is that a task's deadline does not change while it is -+running unless it runs out of time_slice. Thus, even if the time actually -+passes the deadline of another task that is queued, it will not get CPU time -+unless the current running task deschedules, and the time "base" (jiffies) is -+constantly moving. -+ -+Task lookup. -+ -+BFS has 103 priority queues. 100 of these are dedicated to the static priority -+of realtime tasks, and the remaining 3 are, in order of best to worst priority, -+SCHED_ISO (isochronous), SCHED_NORMAL, and SCHED_IDLEPRIO (idle priority -+scheduling). When a task of these priorities is queued, a bitmap of running -+priorities is set showing which of these priorities has tasks waiting for CPU -+time. When a CPU is made to reschedule, the lookup for the next task to get -+CPU time is performed in the following way: -+ -+First the bitmap is checked to see what static priority tasks are queued. If -+any realtime priorities are found, the corresponding queue is checked and the -+first task listed there is taken (provided CPU affinity is suitable) and lookup -+is complete. If the priority corresponds to a SCHED_ISO task, they are also -+taken in FIFO order (as they behave like SCHED_RR). If the priority corresponds -+to either SCHED_NORMAL or SCHED_IDLEPRIO, then the lookup becomes O(n). At this -+stage, every task in the runlist that corresponds to that priority is checked -+to see which has the earliest set deadline, and (provided it has suitable CPU -+affinity) it is taken off the runqueue and given the CPU. If a task has an -+expired deadline, it is taken and the rest of the lookup aborted (as they are -+chosen in FIFO order). -+ -+Thus, the lookup is O(n) in the worst case only, where n is as described -+earlier, as tasks may be chosen before the whole task list is looked over. -+ -+ -+Scalability. -+ -+The major limitations of BFS will be that of scalability, as the separate -+runqueue designs will have less lock contention as the number of CPUs rises. -+However they do not scale linearly even with separate runqueues as multiple -+runqueues will need to be locked concurrently on such designs to be able to -+achieve fair CPU balancing, to try and achieve some sort of nice-level fairness -+across CPUs, and to achieve low enough latency for tasks on a busy CPU when -+other CPUs would be more suited. BFS has the advantage that it requires no -+balancing algorithm whatsoever, as balancing occurs by proxy simply because -+all CPUs draw off the global runqueue, in priority and deadline order. Despite -+the fact that scalability is _not_ the prime concern of BFS, it both shows very -+good scalability to smaller numbers of CPUs and is likely a more scalable design -+at these numbers of CPUs. -+ -+It also has some very low overhead scalability features built into the design -+when it has been deemed their overhead is so marginal that they're worth adding. -+The first is the local copy of the running process' data to the CPU it's running -+on to allow that data to be updated lockless where possible. Then there is -+deference paid to the last CPU a task was running on, by trying that CPU first -+when looking for an idle CPU to use the next time it's scheduled. Finally there -+is the notion of cache locality beyond the last running CPU. The sched_domains -+information is used to determine the relative virtual "cache distance" that -+other CPUs have from the last CPU a task was running on. CPUs with shared -+caches, such as SMT siblings, or multicore CPUs with shared caches, are treated -+as cache local. CPUs without shared caches are treated as not cache local, and -+CPUs on different NUMA nodes are treated as very distant. This "relative cache -+distance" is used by modifying the virtual deadline value when doing lookups. -+Effectively, the deadline is unaltered between "cache local" CPUs, doubled for -+"cache distant" CPUs, and quadrupled for "very distant" CPUs. The reasoning -+behind the doubling of deadlines is as follows. The real cost of migrating a -+task from one CPU to another is entirely dependant on the cache footprint of -+the task, how cache intensive the task is, how long it's been running on that -+CPU to take up the bulk of its cache, how big the CPU cache is, how fast and -+how layered the CPU cache is, how fast a context switch is... and so on. In -+other words, it's close to random in the real world where we do more than just -+one sole workload. The only thing we can be sure of is that it's not free. So -+BFS uses the principle that an idle CPU is a wasted CPU and utilising idle CPUs -+is more important than cache locality, and cache locality only plays a part -+after that. Doubling the effective deadline is based on the premise that the -+"cache local" CPUs will tend to work on the same tasks up to double the number -+of cache local CPUs, and once the workload is beyond that amount, it is likely -+that none of the tasks are cache warm anywhere anyway. The quadrupling for NUMA -+is a value I pulled out of my arse. -+ -+When choosing an idle CPU for a waking task, the cache locality is determined -+according to where the task last ran and then idle CPUs are ranked from best -+to worst to choose the most suitable idle CPU based on cache locality, NUMA -+node locality and hyperthread sibling business. They are chosen in the -+following preference (if idle): -+ -+* Same core, idle or busy cache, idle threads -+* Other core, same cache, idle or busy cache, idle threads. -+* Same node, other CPU, idle cache, idle threads. -+* Same node, other CPU, busy cache, idle threads. -+* Same core, busy threads. -+* Other core, same cache, busy threads. -+* Same node, other CPU, busy threads. -+* Other node, other CPU, idle cache, idle threads. -+* Other node, other CPU, busy cache, idle threads. -+* Other node, other CPU, busy threads. -+ -+This shows the SMT or "hyperthread" awareness in the design as well which will -+choose a real idle core first before a logical SMT sibling which already has -+tasks on the physical CPU. -+ -+Early benchmarking of BFS suggested scalability dropped off at the 16 CPU mark. -+However this benchmarking was performed on an earlier design that was far less -+scalable than the current one so it's hard to know how scalable it is in terms -+of both CPUs (due to the global runqueue) and heavily loaded machines (due to -+O(n) lookup) at this stage. Note that in terms of scalability, the number of -+_logical_ CPUs matters, not the number of _physical_ CPUs. Thus, a dual (2x) -+quad core (4X) hyperthreaded (2X) machine is effectively a 16X. Newer benchmark -+results are very promising indeed, without needing to tweak any knobs, features -+or options. Benchmark contributions are most welcome. -+ -+ -+Features -+ -+As the initial prime target audience for BFS was the average desktop user, it -+was designed to not need tweaking, tuning or have features set to obtain benefit -+from it. Thus the number of knobs and features has been kept to an absolute -+minimum and should not require extra user input for the vast majority of cases. -+There are precisely 2 tunables, and 2 extra scheduling policies. The rr_interval -+and iso_cpu tunables, and the SCHED_ISO and SCHED_IDLEPRIO policies. In addition -+to this, BFS also uses sub-tick accounting. What BFS does _not_ now feature is -+support for CGROUPS. The average user should neither need to know what these -+are, nor should they need to be using them to have good desktop behaviour. -+ -+rr_interval -+ -+There is only one "scheduler" tunable, the round robin interval. This can be -+accessed in -+ -+ /proc/sys/kernel/rr_interval -+ -+The value is in milliseconds, and the default value is set to 6 on a -+uniprocessor machine, and automatically set to a progressively higher value on -+multiprocessor machines. The reasoning behind increasing the value on more CPUs -+is that the effective latency is decreased by virtue of there being more CPUs on -+BFS (for reasons explained above), and increasing the value allows for less -+cache contention and more throughput. Valid values are from 1 to 1000 -+Decreasing the value will decrease latencies at the cost of decreasing -+throughput, while increasing it will improve throughput, but at the cost of -+worsening latencies. The accuracy of the rr interval is limited by HZ resolution -+of the kernel configuration. Thus, the worst case latencies are usually slightly -+higher than this actual value. The default value of 6 is not an arbitrary one. -+It is based on the fact that humans can detect jitter at approximately 7ms, so -+aiming for much lower latencies is pointless under most circumstances. It is -+worth noting this fact when comparing the latency performance of BFS to other -+schedulers. Worst case latencies being higher than 7ms are far worse than -+average latencies not being in the microsecond range. -+ -+Isochronous scheduling. -+ -+Isochronous scheduling is a unique scheduling policy designed to provide -+near-real-time performance to unprivileged (ie non-root) users without the -+ability to starve the machine indefinitely. Isochronous tasks (which means -+"same time") are set using, for example, the schedtool application like so: -+ -+ schedtool -I -e amarok -+ -+This will start the audio application "amarok" as SCHED_ISO. How SCHED_ISO works -+is that it has a priority level between true realtime tasks and SCHED_NORMAL -+which would allow them to preempt all normal tasks, in a SCHED_RR fashion (ie, -+if multiple SCHED_ISO tasks are running, they purely round robin at rr_interval -+rate). However if ISO tasks run for more than a tunable finite amount of time, -+they are then demoted back to SCHED_NORMAL scheduling. This finite amount of -+time is the percentage of _total CPU_ available across the machine, configurable -+as a percentage in the following "resource handling" tunable (as opposed to a -+scheduler tunable): -+ -+ /proc/sys/kernel/iso_cpu -+ -+and is set to 70% by default. It is calculated over a rolling 5 second average -+Because it is the total CPU available, it means that on a multi CPU machine, it -+is possible to have an ISO task running as realtime scheduling indefinitely on -+just one CPU, as the other CPUs will be available. Setting this to 100 is the -+equivalent of giving all users SCHED_RR access and setting it to 0 removes the -+ability to run any pseudo-realtime tasks. -+ -+A feature of BFS is that it detects when an application tries to obtain a -+realtime policy (SCHED_RR or SCHED_FIFO) and the caller does not have the -+appropriate privileges to use those policies. When it detects this, it will -+give the task SCHED_ISO policy instead. Thus it is transparent to the user. -+Because some applications constantly set their policy as well as their nice -+level, there is potential for them to undo the override specified by the user -+on the command line of setting the policy to SCHED_ISO. To counter this, once -+a task has been set to SCHED_ISO policy, it needs superuser privileges to set -+it back to SCHED_NORMAL. This will ensure the task remains ISO and all child -+processes and threads will also inherit the ISO policy. -+ -+Idleprio scheduling. -+ -+Idleprio scheduling is a scheduling policy designed to give out CPU to a task -+_only_ when the CPU would be otherwise idle. The idea behind this is to allow -+ultra low priority tasks to be run in the background that have virtually no -+effect on the foreground tasks. This is ideally suited to distributed computing -+clients (like setiathome, folding, mprime etc) but can also be used to start -+a video encode or so on without any slowdown of other tasks. To avoid this -+policy from grabbing shared resources and holding them indefinitely, if it -+detects a state where the task is waiting on I/O, the machine is about to -+suspend to ram and so on, it will transiently schedule them as SCHED_NORMAL. As -+per the Isochronous task management, once a task has been scheduled as IDLEPRIO, -+it cannot be put back to SCHED_NORMAL without superuser privileges. Tasks can -+be set to start as SCHED_IDLEPRIO with the schedtool command like so: -+ -+ schedtool -D -e ./mprime -+ -+Subtick accounting. -+ -+It is surprisingly difficult to get accurate CPU accounting, and in many cases, -+the accounting is done by simply determining what is happening at the precise -+moment a timer tick fires off. This becomes increasingly inaccurate as the -+timer tick frequency (HZ) is lowered. It is possible to create an application -+which uses almost 100% CPU, yet by being descheduled at the right time, records -+zero CPU usage. While the main problem with this is that there are possible -+security implications, it is also difficult to determine how much CPU a task -+really does use. BFS tries to use the sub-tick accounting from the TSC clock, -+where possible, to determine real CPU usage. This is not entirely reliable, but -+is far more likely to produce accurate CPU usage data than the existing designs -+and will not show tasks as consuming no CPU usage when they actually are. Thus, -+the amount of CPU reported as being used by BFS will more accurately represent -+how much CPU the task itself is using (as is shown for example by the 'time' -+application), so the reported values may be quite different to other schedulers. -+Values reported as the 'load' are more prone to problems with this design, but -+per process values are closer to real usage. When comparing throughput of BFS -+to other designs, it is important to compare the actual completed work in terms -+of total wall clock time taken and total work done, rather than the reported -+"cpu usage". -+ -+ -+Con Kolivas Fri Aug 27 2010 -Index: linux-2.6.37-ck2/Documentation/sysctl/kernel.txt -=================================================================== ---- linux-2.6.37-ck2.orig/Documentation/sysctl/kernel.txt 2011-01-06 14:04:07.000000000 +1100 -+++ linux-2.6.37-ck2/Documentation/sysctl/kernel.txt 2011-02-14 09:47:50.984252001 +1100 -@@ -32,6 +32,7 @@ - - domainname - - hostname - - hotplug -+- iso_cpu - - java-appletviewer [ binfmt_java, obsolete ] - - java-interpreter [ binfmt_java, obsolete ] - - kstack_depth_to_print [ X86 only ] -@@ -54,6 +55,7 @@ - - randomize_va_space - - real-root-dev ==> Documentation/initrd.txt - - reboot-cmd [ SPARC only ] -+- rr_interval - - rtsig-max - - rtsig-nr - - sem -@@ -254,6 +256,16 @@ - - ============================================================== - -+iso_cpu: (BFS CPU scheduler only). -+ -+This sets the percentage cpu that the unprivileged SCHED_ISO tasks can -+run effectively at realtime priority, averaged over a rolling five -+seconds over the -whole- system, meaning all cpus. -+ -+Set to 70 (percent) by default. -+ -+============================================================== -+ - l2cr: (PPC only) - - This flag controls the L2 cache of G3 processor boards. If -@@ -428,6 +440,20 @@ - - ============================================================== - -+rr_interval: (BFS CPU scheduler only) -+ -+This is the smallest duration that any cpu process scheduling unit -+will run for. Increasing this value can increase throughput of cpu -+bound tasks substantially but at the expense of increased latencies -+overall. Conversely decreasing it will decrease average and maximum -+latencies but at the expense of throughput. This value is in -+milliseconds and the default value chosen depends on the number of -+cpus available at scheduler initialisation with a minimum of 6. -+ -+Valid values are from 1-1000. -+ -+============================================================== -+ - rtsig-max & rtsig-nr: - - The file rtsig-max can be used to tune the maximum number -Index: linux-2.6.37-ck2/fs/proc/base.c -=================================================================== ---- linux-2.6.37-ck2.orig/fs/proc/base.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/fs/proc/base.c 2011-02-14 09:47:50.986252000 +1100 -@@ -356,7 +356,7 @@ - static int proc_pid_schedstat(struct task_struct *task, char *buffer) - { - return sprintf(buffer, "%llu %llu %lu\n", -- (unsigned long long)task->se.sum_exec_runtime, -+ (unsigned long long)tsk_seruntime(task), - (unsigned long long)task->sched_info.run_delay, - task->sched_info.pcount); - } -Index: linux-2.6.37-ck2/include/linux/init_task.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/init_task.h 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/include/linux/init_task.h 2011-02-14 09:47:50.986252001 +1100 -@@ -114,6 +114,67 @@ - * INIT_TASK is used to set up the first task table, touch at - * your own risk!. Base=0, limit=0x1fffff (=2MB) - */ -+#ifdef CONFIG_SCHED_BFS -+#define INIT_TASK(tsk) \ -+{ \ -+ .state = 0, \ -+ .stack = &init_thread_info, \ -+ .usage = ATOMIC_INIT(2), \ -+ .flags = PF_KTHREAD, \ -+ .lock_depth = -1, \ -+ .prio = NORMAL_PRIO, \ -+ .static_prio = MAX_PRIO-20, \ -+ .normal_prio = NORMAL_PRIO, \ -+ .deadline = 0, \ -+ .policy = SCHED_NORMAL, \ -+ .cpus_allowed = CPU_MASK_ALL, \ -+ .mm = NULL, \ -+ .active_mm = &init_mm, \ -+ .run_list = LIST_HEAD_INIT(tsk.run_list), \ -+ .time_slice = HZ, \ -+ .tasks = LIST_HEAD_INIT(tsk.tasks), \ -+ .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \ -+ .ptraced = LIST_HEAD_INIT(tsk.ptraced), \ -+ .ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \ -+ .real_parent = &tsk, \ -+ .parent = &tsk, \ -+ .children = LIST_HEAD_INIT(tsk.children), \ -+ .sibling = LIST_HEAD_INIT(tsk.sibling), \ -+ .group_leader = &tsk, \ -+ RCU_INIT_POINTER(.real_cred, &init_cred), \ -+ RCU_INIT_POINTER(.cred, &init_cred), \ -+ .comm = "swapper", \ -+ .thread = INIT_THREAD, \ -+ .fs = &init_fs, \ -+ .files = &init_files, \ -+ .signal = &init_signals, \ -+ .sighand = &init_sighand, \ -+ .nsproxy = &init_nsproxy, \ -+ .pending = { \ -+ .list = LIST_HEAD_INIT(tsk.pending.list), \ -+ .signal = {{0}}}, \ -+ .blocked = {{0}}, \ -+ .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ -+ .journal_info = NULL, \ -+ .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ -+ .fs_excl = ATOMIC_INIT(0), \ -+ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ -+ .timer_slack_ns = 50000, /* 50 usec default slack */ \ -+ .pids = { \ -+ [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ -+ [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ -+ [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \ -+ }, \ -+ .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \ -+ INIT_IDS \ -+ INIT_PERF_EVENTS(tsk) \ -+ INIT_TRACE_IRQFLAGS \ -+ INIT_LOCKDEP \ -+ INIT_FTRACE_GRAPH \ -+ INIT_TRACE_RECURSION \ -+ INIT_TASK_RCU_PREEMPT(tsk) \ -+} -+#else /* CONFIG_SCHED_BFS */ - #define INIT_TASK(tsk) \ - { \ - .state = 0, \ -@@ -179,7 +240,7 @@ - INIT_TRACE_RECURSION \ - INIT_TASK_RCU_PREEMPT(tsk) \ - } -- -+#endif /* CONFIG_SCHED_BFS */ - - #define INIT_CPU_TIMERS(cpu_timers) \ - { \ -Index: linux-2.6.37-ck2/include/linux/ioprio.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/ioprio.h 2009-06-10 13:05:27.000000000 +1000 -+++ linux-2.6.37-ck2/include/linux/ioprio.h 2011-02-14 09:47:50.986252001 +1100 -@@ -64,6 +64,8 @@ - - static inline int task_nice_ioprio(struct task_struct *task) - { -+ if (iso_task(task)) -+ return 0; - return (task_nice(task) + 20) / 5; - } - -Index: linux-2.6.37-ck2/include/linux/sched.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/sched.h 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/include/linux/sched.h 2011-02-14 09:47:50.988252000 +1100 -@@ -36,8 +36,15 @@ - #define SCHED_FIFO 1 - #define SCHED_RR 2 - #define SCHED_BATCH 3 --/* SCHED_ISO: reserved but not implemented yet */ -+/* SCHED_ISO: Implemented on BFS only */ - #define SCHED_IDLE 5 -+#ifdef CONFIG_SCHED_BFS -+#define SCHED_ISO 4 -+#define SCHED_IDLEPRIO SCHED_IDLE -+#define SCHED_MAX (SCHED_IDLEPRIO) -+#define SCHED_RANGE(policy) ((policy) <= SCHED_MAX) -+#endif -+ - /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ - #define SCHED_RESET_ON_FORK 0x40000000 - -@@ -268,8 +275,6 @@ - extern void init_idle(struct task_struct *idle, int cpu); - extern void init_idle_bootup_task(struct task_struct *idle); - --extern int runqueue_is_locked(int cpu); -- - extern cpumask_var_t nohz_cpu_mask; - #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) - extern void select_nohz_load_balancer(int stop_tick); -@@ -1188,17 +1193,31 @@ - - int lock_depth; /* BKL lock depth */ - -+#ifndef CONFIG_SCHED_BFS - #ifdef CONFIG_SMP - #ifdef __ARCH_WANT_UNLOCKED_CTXSW - int oncpu; - #endif - #endif -+#else /* CONFIG_SCHED_BFS */ -+ int oncpu; -+#endif - - int prio, static_prio, normal_prio; - unsigned int rt_priority; -+#ifdef CONFIG_SCHED_BFS -+ int time_slice; -+ u64 deadline; -+ struct list_head run_list; -+ u64 last_ran; -+ u64 sched_time; /* sched_clock time spent running */ -+ -+ unsigned long rt_timeout; -+#else /* CONFIG_SCHED_BFS */ - const struct sched_class *sched_class; - struct sched_entity se; - struct sched_rt_entity rt; -+#endif - - #ifdef CONFIG_PREEMPT_NOTIFIERS - /* list of struct preempt_notifier: */ -@@ -1295,6 +1314,9 @@ - int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ - - cputime_t utime, stime, utimescaled, stimescaled; -+#ifdef CONFIG_SCHED_BFS -+ unsigned long utime_pc, stime_pc; -+#endif - cputime_t gtime; - #ifndef CONFIG_VIRT_CPU_ACCOUNTING - cputime_t prev_utime, prev_stime; -@@ -1514,6 +1536,53 @@ - #endif - }; - -+#ifdef CONFIG_SCHED_BFS -+extern int grunqueue_is_locked(void); -+extern void grq_unlock_wait(void); -+#define tsk_seruntime(t) ((t)->sched_time) -+#define tsk_rttimeout(t) ((t)->rt_timeout) -+ -+static inline void tsk_cpus_current(struct task_struct *p) -+{ -+} -+ -+#define runqueue_is_locked(cpu) grunqueue_is_locked() -+ -+static inline void print_scheduler_version(void) -+{ -+ printk(KERN_INFO"BFS CPU scheduler v0.363 by Con Kolivas.\n"); -+} -+ -+static inline int iso_task(struct task_struct *p) -+{ -+ return (p->policy == SCHED_ISO); -+} -+extern void remove_cpu(unsigned long cpu); -+#else /* CFS */ -+extern int runqueue_is_locked(int cpu); -+#define tsk_seruntime(t) ((t)->se.sum_exec_runtime) -+#define tsk_rttimeout(t) ((t)->rt.timeout) -+ -+static inline void tsk_cpus_current(struct task_struct *p) -+{ -+ p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed; -+} -+ -+static inline void print_scheduler_version(void) -+{ -+ printk(KERN_INFO"CFS CPU scheduler.\n"); -+} -+ -+static inline int iso_task(struct task_struct *p) -+{ -+ return 0; -+} -+ -+static inline void remove_cpu(unsigned long cpu) -+{ -+} -+#endif /* CONFIG_SCHED_BFS */ -+ - /* Future-safe accessor for struct task_struct's cpus_allowed. */ - #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) - -@@ -1531,10 +1600,20 @@ - */ - - #define MAX_USER_RT_PRIO 100 --#define MAX_RT_PRIO MAX_USER_RT_PRIO -+#define MAX_RT_PRIO (MAX_USER_RT_PRIO + 1) -+#define DEFAULT_PRIO (MAX_RT_PRIO + 20) - -+#ifdef CONFIG_SCHED_BFS -+#define PRIO_RANGE (40) -+#define MAX_PRIO (MAX_RT_PRIO + PRIO_RANGE) -+#define ISO_PRIO (MAX_RT_PRIO) -+#define NORMAL_PRIO (MAX_RT_PRIO + 1) -+#define IDLE_PRIO (MAX_RT_PRIO + 2) -+#define PRIO_LIMIT ((IDLE_PRIO) + 1) -+#else /* CONFIG_SCHED_BFS */ - #define MAX_PRIO (MAX_RT_PRIO + 40) --#define DEFAULT_PRIO (MAX_RT_PRIO + 20) -+#define NORMAL_PRIO DEFAULT_PRIO -+#endif /* CONFIG_SCHED_BFS */ - - static inline int rt_prio(int prio) - { -@@ -1862,7 +1941,7 @@ - extern unsigned long long thread_group_sched_runtime(struct task_struct *task); - - /* sched_exec is called by processes performing an exec */ --#ifdef CONFIG_SMP -+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_BFS) - extern void sched_exec(void); - #else - #define sched_exec() {} -Index: linux-2.6.37-ck2/init/Kconfig -=================================================================== ---- linux-2.6.37-ck2.orig/init/Kconfig 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/init/Kconfig 2011-02-14 09:47:50.988252001 +1100 -@@ -30,6 +30,19 @@ - - menu "General setup" - -+config SCHED_BFS -+ bool "BFS cpu scheduler" -+ ---help--- -+ The Brain Fuck CPU Scheduler for excellent interactivity and -+ responsiveness on the desktop and solid scalability on normal -+ hardware. Not recommended for 4096 CPUs. -+ -+ Currently incompatible with the Group CPU scheduler, and RCU TORTURE -+ TEST so these options are disabled. -+ -+ Say Y here. -+ default y -+ - config EXPERIMENTAL - bool "Prompt for development and/or incomplete code/drivers" - ---help--- -@@ -563,6 +576,7 @@ - - config CGROUP_CPUACCT - bool "Simple CPU accounting cgroup subsystem" -+ depends on !SCHED_BFS - help - Provides a simple Resource Controller for monitoring the - total CPU consumed by the tasks in a cgroup. -@@ -629,7 +643,7 @@ - - menuconfig CGROUP_SCHED - bool "Group CPU scheduler" -- depends on EXPERIMENTAL -+ depends on EXPERIMENTAL && !SCHED_BFS - default n - help - This feature lets CPU scheduler recognize task groups and control CPU -Index: linux-2.6.37-ck2/init/main.c -=================================================================== ---- linux-2.6.37-ck2.orig/init/main.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/init/main.c 2011-02-14 09:47:50.989252001 +1100 -@@ -824,6 +824,7 @@ - system_state = SYSTEM_RUNNING; - numa_default_policy(); - -+ print_scheduler_version(); - - current->signal->flags |= SIGNAL_UNKILLABLE; - -Index: linux-2.6.37-ck2/kernel/delayacct.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/delayacct.c 2009-12-03 21:40:09.000000000 +1100 -+++ linux-2.6.37-ck2/kernel/delayacct.c 2011-02-14 09:47:50.989252001 +1100 -@@ -128,7 +128,7 @@ - */ - t1 = tsk->sched_info.pcount; - t2 = tsk->sched_info.run_delay; -- t3 = tsk->se.sum_exec_runtime; -+ t3 = tsk_seruntime(tsk); - - d->cpu_count += t1; - -Index: linux-2.6.37-ck2/kernel/exit.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/exit.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/kernel/exit.c 2011-02-14 09:47:50.989252001 +1100 -@@ -132,7 +132,7 @@ - sig->inblock += task_io_get_inblock(tsk); - sig->oublock += task_io_get_oublock(tsk); - task_io_accounting_add(&sig->ioac, &tsk->ioac); -- sig->sum_sched_runtime += tsk->se.sum_exec_runtime; -+ sig->sum_sched_runtime += tsk_seruntime(tsk); - } - - sig->nr_threads--; -Index: linux-2.6.37-ck2/kernel/kthread.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/kthread.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/kernel/kthread.c 2011-02-14 09:47:50.989252001 +1100 -@@ -184,7 +184,9 @@ - } - - p->cpus_allowed = cpumask_of_cpu(cpu); -+#ifndef CONFIG_SCHED_BFS - p->rt.nr_cpus_allowed = 1; -+#endif - p->flags |= PF_THREAD_BOUND; - } - EXPORT_SYMBOL(kthread_bind); -Index: linux-2.6.37-ck2/kernel/posix-cpu-timers.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/posix-cpu-timers.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/kernel/posix-cpu-timers.c 2011-02-14 09:47:50.990252001 +1100 -@@ -248,7 +248,7 @@ - do { - times->utime = cputime_add(times->utime, t->utime); - times->stime = cputime_add(times->stime, t->stime); -- times->sum_exec_runtime += t->se.sum_exec_runtime; -+ times->sum_exec_runtime += tsk_seruntime(t); - } while_each_thread(tsk, t); - out: - rcu_read_unlock(); -@@ -508,7 +508,7 @@ - void posix_cpu_timers_exit(struct task_struct *tsk) - { - cleanup_timers(tsk->cpu_timers, -- tsk->utime, tsk->stime, tsk->se.sum_exec_runtime); -+ tsk->utime, tsk->stime, tsk_seruntime(tsk)); - - } - void posix_cpu_timers_exit_group(struct task_struct *tsk) -@@ -518,7 +518,7 @@ - cleanup_timers(tsk->signal->cpu_timers, - cputime_add(tsk->utime, sig->utime), - cputime_add(tsk->stime, sig->stime), -- tsk->se.sum_exec_runtime + sig->sum_sched_runtime); -+ tsk_seruntime(tsk) + sig->sum_sched_runtime); - } - - static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) -@@ -949,7 +949,7 @@ - struct cpu_timer_list *t = list_first_entry(timers, - struct cpu_timer_list, - entry); -- if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { -+ if (!--maxfire || tsk_seruntime(tsk) < t->expires.sched) { - tsk->cputime_expires.sched_exp = t->expires.sched; - break; - } -@@ -966,7 +966,7 @@ - ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); - - if (hard != RLIM_INFINITY && -- tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { -+ tsk_rttimeout(tsk) > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { - /* - * At the hard limit, we just die. - * No need to calculate anything else now. -@@ -974,7 +974,7 @@ - __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); - return; - } -- if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) { -+ if (tsk_rttimeout(tsk) > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) { - /* - * At the soft limit, send a SIGXCPU every second. - */ -@@ -1276,7 +1276,7 @@ - struct task_cputime task_sample = { - .utime = tsk->utime, - .stime = tsk->stime, -- .sum_exec_runtime = tsk->se.sum_exec_runtime -+ .sum_exec_runtime = tsk_seruntime(tsk) - }; - - if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) -Index: linux-2.6.37-ck2/kernel/sched_bfs.c -=================================================================== ---- /dev/null 1970-01-01 00:00:00.000000000 +0000 -+++ linux-2.6.37-ck2/kernel/sched_bfs.c 2011-02-14 09:47:50.993252001 +1100 -@@ -0,0 +1,7223 @@ -+/* -+ * kernel/sched_bfs.c, was sched.c -+ * -+ * Kernel scheduler and related syscalls -+ * -+ * Copyright (C) 1991-2002 Linus Torvalds -+ * -+ * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and -+ * make semaphores SMP safe -+ * 1998-11-19 Implemented schedule_timeout() and related stuff -+ * by Andrea Arcangeli -+ * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: -+ * hybrid priority-list and round-robin design with -+ * an array-switch method of distributing timeslices -+ * and per-CPU runqueues. Cleanups and useful suggestions -+ * by Davide Libenzi, preemptible kernel bits by Robert Love. -+ * 2003-09-03 Interactivity tuning by Con Kolivas. -+ * 2004-04-02 Scheduler domains code by Nick Piggin -+ * 2007-04-15 Work begun on replacing all interactivity tuning with a -+ * fair scheduling design by Con Kolivas. -+ * 2007-05-05 Load balancing (smp-nice) and other improvements -+ * by Peter Williams -+ * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith -+ * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri -+ * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, -+ * Thomas Gleixner, Mike Kravetz -+ * now Brainfuck deadline scheduling policy by Con Kolivas deletes -+ * a whole lot of those previous things. -+ */ -+ -+#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 -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+ -+#include -+#include -+ -+#include "sched_cpupri.h" -+#include "workqueue_sched.h" -+ -+#define CREATE_TRACE_POINTS -+#include -+ -+#define rt_prio(prio) unlikely((prio) < MAX_RT_PRIO) -+#define rt_task(p) rt_prio((p)->prio) -+#define rt_queue(rq) rt_prio((rq)->rq_prio) -+#define batch_task(p) (unlikely((p)->policy == SCHED_BATCH)) -+#define is_rt_policy(policy) ((policy) == SCHED_FIFO || \ -+ (policy) == SCHED_RR) -+#define has_rt_policy(p) unlikely(is_rt_policy((p)->policy)) -+#define idleprio_task(p) unlikely((p)->policy == SCHED_IDLEPRIO) -+#define iso_task(p) unlikely((p)->policy == SCHED_ISO) -+#define iso_queue(rq) unlikely((rq)->rq_policy == SCHED_ISO) -+#define ISO_PERIOD ((5 * HZ * num_online_cpus()) + 1) -+ -+/* -+ * Convert user-nice values [ -20 ... 0 ... 19 ] -+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], -+ * and back. -+ */ -+#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) -+#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) -+#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) -+ -+/* -+ * 'User priority' is the nice value converted to something we -+ * can work with better when scaling various scheduler parameters, -+ * it's a [ 0 ... 39 ] range. -+ */ -+#define USER_PRIO(p) ((p) - MAX_RT_PRIO) -+#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) -+#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) -+#define SCHED_PRIO(p) ((p) + MAX_RT_PRIO) -+#define STOP_PRIO (MAX_RT_PRIO - 1) -+ -+/* -+ * Some helpers for converting to/from various scales. Use shifts to get -+ * approximate multiples of ten for less overhead. -+ */ -+#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ)) -+#define JIFFY_NS (1000000000 / HZ) -+#define HALF_JIFFY_NS (1000000000 / HZ / 2) -+#define HALF_JIFFY_US (1000000 / HZ / 2) -+#define MS_TO_NS(TIME) ((TIME) << 20) -+#define MS_TO_US(TIME) ((TIME) << 10) -+#define NS_TO_MS(TIME) ((TIME) >> 20) -+#define NS_TO_US(TIME) ((TIME) >> 10) -+ -+#define RESCHED_US (100) /* Reschedule if less than this many μs left */ -+ -+/* -+ * This is the time all tasks within the same priority round robin. -+ * Value is in ms and set to a minimum of 6ms. Scales with number of cpus. -+ * Tunable via /proc interface. -+ */ -+int rr_interval __read_mostly = 6; -+ -+/* -+ * sched_iso_cpu - sysctl which determines the cpu percentage SCHED_ISO tasks -+ * are allowed to run five seconds as real time tasks. This is the total over -+ * all online cpus. -+ */ -+int sched_iso_cpu __read_mostly = 70; -+ -+/* -+ * The relative length of deadline for each priority(nice) level. -+ */ -+static int prio_ratios[PRIO_RANGE] __read_mostly; -+ -+/* -+ * The quota handed out to tasks of all priority levels when refilling their -+ * time_slice. -+ */ -+static inline unsigned long timeslice(void) -+{ -+ return MS_TO_US(rr_interval); -+} -+ -+/* -+ * The global runqueue data that all CPUs work off. Data is protected either -+ * by the global grq lock, or the discrete lock that precedes the data in this -+ * struct. -+ */ -+struct global_rq { -+ raw_spinlock_t lock; -+ unsigned long nr_running; -+ unsigned long nr_uninterruptible; -+ unsigned long long nr_switches; -+ struct list_head queue[PRIO_LIMIT]; -+ DECLARE_BITMAP(prio_bitmap, PRIO_LIMIT + 1); -+#ifdef CONFIG_SMP -+ unsigned long qnr; /* queued not running */ -+ cpumask_t cpu_idle_map; -+ int idle_cpus; -+#endif -+ u64 niffies; /* Nanosecond jiffies */ -+ unsigned long last_jiffy; /* Last jiffy we updated niffies */ -+ -+ raw_spinlock_t iso_lock; -+ int iso_ticks; -+ int iso_refractory; -+}; -+ -+/* There can be only one */ -+static struct global_rq grq; -+ -+/* -+ * This is the main, per-CPU runqueue data structure. -+ * This data should only be modified by the local cpu. -+ */ -+struct rq { -+#ifdef CONFIG_SMP -+#ifdef CONFIG_NO_HZ -+ u64 nohz_stamp; -+ unsigned char in_nohz_recently; -+#endif -+#endif -+ -+ struct task_struct *curr, *idle, *stop; -+ struct mm_struct *prev_mm; -+ -+ /* Stored data about rq->curr to work outside grq lock */ -+ u64 rq_deadline; -+ unsigned int rq_policy; -+ int rq_time_slice; -+ u64 rq_last_ran; -+ int rq_prio; -+ int rq_running; /* There is a task running */ -+ -+ /* Accurate timekeeping data */ -+ u64 timekeep_clock; -+ unsigned long user_pc, nice_pc, irq_pc, softirq_pc, system_pc, -+ iowait_pc, idle_pc; -+ atomic_t nr_iowait; -+ -+#ifdef CONFIG_SMP -+ int cpu; /* cpu of this runqueue */ -+ int online; -+ -+ struct root_domain *rd; -+ struct sched_domain *sd; -+ unsigned long *cpu_locality; /* CPU relative cache distance */ -+#ifdef CONFIG_SCHED_SMT -+ int (*siblings_idle)(unsigned long cpu); -+ /* See if all smt siblings are idle */ -+ cpumask_t smt_siblings; -+#endif -+#ifdef CONFIG_SCHED_MC -+ int (*cache_idle)(unsigned long cpu); -+ /* See if all cache siblings are idle */ -+ cpumask_t cache_siblings; -+#endif -+ u64 last_niffy; /* Last time this RQ updated grq.niffies */ -+#endif -+#ifdef CONFIG_IRQ_TIME_ACCOUNTING -+ u64 prev_irq_time; -+#endif -+ u64 clock, old_clock, last_tick; -+ u64 clock_task; -+ int dither; -+ -+#ifdef CONFIG_SCHEDSTATS -+ -+ /* latency stats */ -+ struct sched_info rq_sched_info; -+ unsigned long long rq_cpu_time; -+ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ -+ -+ /* sys_sched_yield() stats */ -+ unsigned int yld_count; -+ -+ /* schedule() stats */ -+ unsigned int sched_switch; -+ unsigned int sched_count; -+ unsigned int sched_goidle; -+ -+ /* try_to_wake_up() stats */ -+ unsigned int ttwu_count; -+ unsigned int ttwu_local; -+ -+ /* BKL stats */ -+ unsigned int bkl_count; -+#endif -+}; -+ -+static DEFINE_PER_CPU(struct rq, runqueues) ____cacheline_aligned_in_smp; -+static DEFINE_MUTEX(sched_hotcpu_mutex); -+ -+#ifdef CONFIG_SMP -+/* -+ * sched_domains_mutex serializes calls to arch_init_sched_domains, -+ * detach_destroy_domains and partition_sched_domains. -+ */ -+static DEFINE_MUTEX(sched_domains_mutex); -+ -+/* -+ * By default the system creates a single root-domain with all cpus as -+ * members (mimicking the global state we have today). -+ */ -+static struct root_domain def_root_domain; -+ -+int __weak arch_sd_sibling_asym_packing(void) -+{ -+ return 0*SD_ASYM_PACKING; -+} -+#endif -+ -+/* -+ * We add the notion of a root-domain which will be used to define per-domain -+ * variables. Each exclusive cpuset essentially defines an island domain by -+ * fully partitioning the member cpus from any other cpuset. Whenever a new -+ * exclusive cpuset is created, we also create and attach a new root-domain -+ * object. -+ * -+ */ -+struct root_domain { -+ atomic_t refcount; -+ cpumask_var_t span; -+ cpumask_var_t online; -+ -+ /* -+ * The "RT overload" flag: it gets set if a CPU has more than -+ * one runnable RT task. -+ */ -+ cpumask_var_t rto_mask; -+ atomic_t rto_count; -+#ifdef CONFIG_SMP -+ struct cpupri cpupri; -+#endif -+}; -+ -+#define rcu_dereference_check_sched_domain(p) \ -+ rcu_dereference_check((p), \ -+ rcu_read_lock_sched_held() || \ -+ lockdep_is_held(&sched_domains_mutex)) -+ -+/* -+ * The domain tree (rq->sd) is protected by RCU's quiescent state transition. -+ * See detach_destroy_domains: synchronize_sched for details. -+ * -+ * The domain tree of any CPU may only be accessed from within -+ * preempt-disabled sections. -+ */ -+#define for_each_domain(cpu, __sd) \ -+ for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) -+ -+static inline void update_rq_clock(struct rq *rq); -+ -+/* -+ * Sanity check should sched_clock return bogus values. We make sure it does -+ * not appear to go backwards, and use jiffies to determine the maximum and -+ * minimum it could possibly have increased, and round down to the nearest -+ * jiffy when it falls outside this. -+ */ -+static inline void niffy_diff(s64 *niff_diff, int jiff_diff) -+{ -+ unsigned long min_diff, max_diff; -+ -+ if (jiff_diff > 1) -+ min_diff = JIFFIES_TO_NS(jiff_diff - 1); -+ else -+ min_diff = 1; -+ /* Round up to the nearest tick for maximum */ -+ max_diff = JIFFIES_TO_NS(jiff_diff + 1); -+ -+ if (unlikely(*niff_diff < min_diff || *niff_diff > max_diff)) -+ *niff_diff = min_diff; -+} -+ -+#ifdef CONFIG_SMP -+#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) -+#define this_rq() (&__get_cpu_var(runqueues)) -+#define task_rq(p) cpu_rq(task_cpu(p)) -+#define cpu_curr(cpu) (cpu_rq(cpu)->curr) -+static inline int cpu_of(struct rq *rq) -+{ -+ return rq->cpu; -+} -+ -+/* -+ * Niffies are a globally increasing nanosecond counter. Whenever a runqueue -+ * clock is updated with the grq.lock held, it is an opportunity to update the -+ * niffies value. Any CPU can update it by adding how much its clock has -+ * increased since it last updated niffies, minus any added niffies by other -+ * CPUs. -+ */ -+static inline void update_clocks(struct rq *rq) -+{ -+ s64 ndiff; -+ long jdiff; -+ -+ update_rq_clock(rq); -+ ndiff = rq->clock - rq->old_clock; -+ /* old_clock is only updated when we are updating niffies */ -+ rq->old_clock = rq->clock; -+ ndiff -= grq.niffies - rq->last_niffy; -+ jdiff = jiffies - grq.last_jiffy; -+ niffy_diff(&ndiff, jdiff); -+ grq.last_jiffy += jdiff; -+ grq.niffies += ndiff; -+ rq->last_niffy = grq.niffies; -+} -+#else /* CONFIG_SMP */ -+static struct rq *uprq; -+#define cpu_rq(cpu) (uprq) -+#define this_rq() (uprq) -+#define task_rq(p) (uprq) -+#define cpu_curr(cpu) ((uprq)->curr) -+static inline int cpu_of(struct rq *rq) -+{ -+ return 0; -+} -+ -+static inline void update_clocks(struct rq *rq) -+{ -+ s64 ndiff; -+ long jdiff; -+ -+ update_rq_clock(rq); -+ ndiff = rq->clock - rq->old_clock; -+ rq->old_clock = rq->clock; -+ jdiff = jiffies - grq.last_jiffy; -+ niffy_diff(&ndiff, jdiff); -+ grq.last_jiffy += jdiff; -+ grq.niffies += ndiff; -+} -+#endif -+#define raw_rq() (&__raw_get_cpu_var(runqueues)) -+ -+#include "sched_stats.h" -+ -+#ifndef prepare_arch_switch -+# define prepare_arch_switch(next) do { } while (0) -+#endif -+#ifndef finish_arch_switch -+# define finish_arch_switch(prev) do { } while (0) -+#endif -+ -+/* -+ * All common locking functions performed on grq.lock. rq->clock is local to -+ * the CPU accessing it so it can be modified just with interrupts disabled -+ * when we're not updating niffies. -+ * Looking up task_rq must be done under grq.lock to be safe. -+ */ -+static void update_rq_clock_task(struct rq *rq, s64 delta); -+ -+static inline void update_rq_clock(struct rq *rq) -+{ -+ s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; -+ -+ rq->clock += delta; -+ update_rq_clock_task(rq, delta); -+} -+ -+static inline int task_running(struct task_struct *p) -+{ -+ return p->oncpu; -+} -+ -+static inline void grq_lock(void) -+ __acquires(grq.lock) -+{ -+ raw_spin_lock(&grq.lock); -+} -+ -+static inline void grq_unlock(void) -+ __releases(grq.lock) -+{ -+ raw_spin_unlock(&grq.lock); -+} -+ -+static inline void grq_lock_irq(void) -+ __acquires(grq.lock) -+{ -+ raw_spin_lock_irq(&grq.lock); -+} -+ -+static inline void time_lock_grq(struct rq *rq) -+ __acquires(grq.lock) -+{ -+ grq_lock(); -+ update_clocks(rq); -+} -+ -+static inline void grq_unlock_irq(void) -+ __releases(grq.lock) -+{ -+ raw_spin_unlock_irq(&grq.lock); -+} -+ -+static inline void grq_lock_irqsave(unsigned long *flags) -+ __acquires(grq.lock) -+{ -+ raw_spin_lock_irqsave(&grq.lock, *flags); -+} -+ -+static inline void grq_unlock_irqrestore(unsigned long *flags) -+ __releases(grq.lock) -+{ -+ raw_spin_unlock_irqrestore(&grq.lock, *flags); -+} -+ -+static inline struct rq -+*task_grq_lock(struct task_struct *p, unsigned long *flags) -+ __acquires(grq.lock) -+{ -+ grq_lock_irqsave(flags); -+ return task_rq(p); -+} -+ -+static inline struct rq -+*time_task_grq_lock(struct task_struct *p, unsigned long *flags) -+ __acquires(grq.lock) -+{ -+ struct rq *rq = task_grq_lock(p, flags); -+ update_clocks(rq); -+ return rq; -+} -+ -+static inline struct rq *task_grq_lock_irq(struct task_struct *p) -+ __acquires(grq.lock) -+{ -+ grq_lock_irq(); -+ return task_rq(p); -+} -+ -+static inline void time_task_grq_lock_irq(struct task_struct *p) -+ __acquires(grq.lock) -+{ -+ struct rq *rq = task_grq_lock_irq(p); -+ update_clocks(rq); -+} -+ -+static inline void task_grq_unlock_irq(void) -+ __releases(grq.lock) -+{ -+ grq_unlock_irq(); -+} -+ -+static inline void task_grq_unlock(unsigned long *flags) -+ __releases(grq.lock) -+{ -+ grq_unlock_irqrestore(flags); -+} -+ -+/** -+ * grunqueue_is_locked -+ * -+ * Returns true if the global runqueue is locked. -+ * This interface allows printk to be called with the runqueue lock -+ * held and know whether or not it is OK to wake up the klogd. -+ */ -+inline int grunqueue_is_locked(void) -+{ -+ return raw_spin_is_locked(&grq.lock); -+} -+ -+inline void grq_unlock_wait(void) -+ __releases(grq.lock) -+{ -+ smp_mb(); /* spin-unlock-wait is not a full memory barrier */ -+ raw_spin_unlock_wait(&grq.lock); -+} -+ -+static inline void time_grq_lock(struct rq *rq, unsigned long *flags) -+ __acquires(grq.lock) -+{ -+ local_irq_save(*flags); -+ time_lock_grq(rq); -+} -+ -+static inline struct rq *__task_grq_lock(struct task_struct *p) -+ __acquires(grq.lock) -+{ -+ grq_lock(); -+ return task_rq(p); -+} -+ -+static inline void __task_grq_unlock(void) -+ __releases(grq.lock) -+{ -+ grq_unlock(); -+} -+ -+#ifndef __ARCH_WANT_UNLOCKED_CTXSW -+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) -+{ -+} -+ -+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) -+{ -+#ifdef CONFIG_DEBUG_SPINLOCK -+ /* this is a valid case when another task releases the spinlock */ -+ grq.lock.owner = current; -+#endif -+ /* -+ * If we are tracking spinlock dependencies then we have to -+ * fix up the runqueue lock - which gets 'carried over' from -+ * prev into current: -+ */ -+ spin_acquire(&grq.lock.dep_map, 0, 0, _THIS_IP_); -+ -+ grq_unlock_irq(); -+} -+ -+#else /* __ARCH_WANT_UNLOCKED_CTXSW */ -+ -+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) -+{ -+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -+ grq_unlock_irq(); -+#else -+ grq_unlock(); -+#endif -+} -+ -+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) -+{ -+ smp_wmb(); -+#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW -+ local_irq_enable(); -+#endif -+} -+#endif /* __ARCH_WANT_UNLOCKED_CTXSW */ -+ -+static inline int deadline_before(u64 deadline, u64 time) -+{ -+ return (deadline < time); -+} -+ -+static inline int deadline_after(u64 deadline, u64 time) -+{ -+ return (deadline > time); -+} -+ -+/* -+ * A task that is queued but not running will be on the grq run list. -+ * A task that is not running or queued will not be on the grq run list. -+ * A task that is currently running will have ->oncpu set but not on the -+ * grq run list. -+ */ -+static inline int task_queued(struct task_struct *p) -+{ -+ return (!list_empty(&p->run_list)); -+} -+ -+/* -+ * Removing from the global runqueue. Enter with grq locked. -+ */ -+static void dequeue_task(struct task_struct *p) -+{ -+ list_del_init(&p->run_list); -+ if (list_empty(grq.queue + p->prio)) -+ __clear_bit(p->prio, grq.prio_bitmap); -+} -+ -+/* -+ * To determine if it's safe for a task of SCHED_IDLEPRIO to actually run as -+ * an idle task, we ensure none of the following conditions are met. -+ */ -+static int idleprio_suitable(struct task_struct *p) -+{ -+ return (!freezing(p) && !signal_pending(p) && -+ !(task_contributes_to_load(p)) && !(p->flags & (PF_EXITING))); -+} -+ -+/* -+ * To determine if a task of SCHED_ISO can run in pseudo-realtime, we check -+ * that the iso_refractory flag is not set. -+ */ -+static int isoprio_suitable(void) -+{ -+ return !grq.iso_refractory; -+} -+ -+/* -+ * Adding to the global runqueue. Enter with grq locked. -+ */ -+static void enqueue_task(struct task_struct *p) -+{ -+ if (!rt_task(p)) { -+ /* Check it hasn't gotten rt from PI */ -+ if ((idleprio_task(p) && idleprio_suitable(p)) || -+ (iso_task(p) && isoprio_suitable())) -+ p->prio = p->normal_prio; -+ else -+ p->prio = NORMAL_PRIO; -+ } -+ __set_bit(p->prio, grq.prio_bitmap); -+ list_add_tail(&p->run_list, grq.queue + p->prio); -+ sched_info_queued(p); -+} -+ -+/* Only idle task does this as a real time task*/ -+static inline void enqueue_task_head(struct task_struct *p) -+{ -+ __set_bit(p->prio, grq.prio_bitmap); -+ list_add(&p->run_list, grq.queue + p->prio); -+ sched_info_queued(p); -+} -+ -+static inline void requeue_task(struct task_struct *p) -+{ -+ sched_info_queued(p); -+} -+ -+/* -+ * Returns the relative length of deadline all compared to the shortest -+ * deadline which is that of nice -20. -+ */ -+static inline int task_prio_ratio(struct task_struct *p) -+{ -+ return prio_ratios[TASK_USER_PRIO(p)]; -+} -+ -+/* -+ * task_timeslice - all tasks of all priorities get the exact same timeslice -+ * length. CPU distribution is handled by giving different deadlines to -+ * tasks of different priorities. Use 128 as the base value for fast shifts. -+ */ -+static inline int task_timeslice(struct task_struct *p) -+{ -+ return (rr_interval * task_prio_ratio(p) / 128); -+} -+ -+#ifdef CONFIG_SMP -+/* -+ * qnr is the "queued but not running" count which is the total number of -+ * tasks on the global runqueue list waiting for cpu time but not actually -+ * currently running on a cpu. -+ */ -+static inline void inc_qnr(void) -+{ -+ grq.qnr++; -+} -+ -+static inline void dec_qnr(void) -+{ -+ grq.qnr--; -+} -+ -+static inline int queued_notrunning(void) -+{ -+ return grq.qnr; -+} -+ -+/* -+ * The cpu_idle_map stores a bitmap of all the CPUs currently idle to -+ * allow easy lookup of whether any suitable idle CPUs are available. -+ * It's cheaper to maintain a binary yes/no if there are any idle CPUs on the -+ * idle_cpus variable than to do a full bitmask check when we are busy. -+ */ -+static inline void set_cpuidle_map(unsigned long cpu) -+{ -+ if (likely(cpu_online(cpu))) { -+ cpu_set(cpu, grq.cpu_idle_map); -+ grq.idle_cpus = 1; -+ } -+} -+ -+static inline void clear_cpuidle_map(unsigned long cpu) -+{ -+ cpu_clear(cpu, grq.cpu_idle_map); -+ if (cpus_empty(grq.cpu_idle_map)) -+ grq.idle_cpus = 0; -+} -+ -+static int suitable_idle_cpus(struct task_struct *p) -+{ -+ if (!grq.idle_cpus) -+ return 0; -+ return (cpus_intersects(p->cpus_allowed, grq.cpu_idle_map)); -+} -+ -+static void resched_task(struct task_struct *p); -+ -+#define CPUIDLE_DIFF_THREAD (1) -+#define CPUIDLE_DIFF_CORE (2) -+#define CPUIDLE_CACHE_BUSY (4) -+#define CPUIDLE_DIFF_CPU (8) -+#define CPUIDLE_THREAD_BUSY (16) -+#define CPUIDLE_DIFF_NODE (32) -+ -+/* -+ * The best idle CPU is chosen according to the CPUIDLE ranking above where the -+ * lowest value would give the most suitable CPU to schedule p onto next. We -+ * iterate from the last CPU upwards instead of using for_each_cpu_mask so as -+ * to be able to break out immediately if the last CPU is idle. The order works -+ * out to be the following: -+ * -+ * Same core, idle or busy cache, idle threads -+ * Other core, same cache, idle or busy cache, idle threads. -+ * Same node, other CPU, idle cache, idle threads. -+ * Same node, other CPU, busy cache, idle threads. -+ * Same core, busy threads. -+ * Other core, same cache, busy threads. -+ * Same node, other CPU, busy threads. -+ * Other node, other CPU, idle cache, idle threads. -+ * Other node, other CPU, busy cache, idle threads. -+ * Other node, other CPU, busy threads. -+ * -+ * If p was the last task running on this rq, then regardless of where -+ * it has been running since then, it is cache warm on this rq. -+ */ -+static void resched_best_idle(struct task_struct *p) -+{ -+ unsigned long cpu_tmp, best_cpu, best_ranking; -+ cpumask_t tmpmask; -+ struct rq *rq; -+ int iterate; -+ -+ cpus_and(tmpmask, p->cpus_allowed, grq.cpu_idle_map); -+ iterate = cpus_weight(tmpmask); -+ best_cpu = task_cpu(p); -+ /* -+ * Start below the last CPU and work up with next_cpu as the last -+ * CPU might not be idle or affinity might not allow it. -+ */ -+ cpu_tmp = best_cpu - 1; -+ rq = cpu_rq(best_cpu); -+ best_ranking = ~0UL; -+ -+ do { -+ unsigned long ranking; -+ struct rq *tmp_rq; -+ -+ ranking = 0; -+ cpu_tmp = next_cpu(cpu_tmp, tmpmask); -+ if (cpu_tmp >= nr_cpu_ids) { -+ cpu_tmp = -1; -+ cpu_tmp = next_cpu(cpu_tmp, tmpmask); -+ } -+ tmp_rq = cpu_rq(cpu_tmp); -+ -+#ifdef CONFIG_NUMA -+ if (rq->cpu_locality[cpu_tmp] > 3) -+ ranking |= CPUIDLE_DIFF_NODE; -+ else -+#endif -+ if (rq->cpu_locality[cpu_tmp] > 2) -+ ranking |= CPUIDLE_DIFF_CPU; -+#ifdef CONFIG_SCHED_MC -+ if (rq->cpu_locality[cpu_tmp] == 2) -+ ranking |= CPUIDLE_DIFF_CORE; -+ if (!(tmp_rq->cache_idle(cpu_tmp))) -+ ranking |= CPUIDLE_CACHE_BUSY; -+#endif -+#ifdef CONFIG_SCHED_SMT -+ if (rq->cpu_locality[cpu_tmp] == 1) -+ ranking |= CPUIDLE_DIFF_THREAD; -+ if (!(tmp_rq->siblings_idle(cpu_tmp))) -+ ranking |= CPUIDLE_THREAD_BUSY; -+#endif -+ if (ranking < best_ranking) { -+ best_cpu = cpu_tmp; -+ if (ranking == 0) -+ break; -+ best_ranking = ranking; -+ } -+ } while (--iterate > 0); -+ -+ resched_task(cpu_rq(best_cpu)->curr); -+} -+ -+static inline void resched_suitable_idle(struct task_struct *p) -+{ -+ if (suitable_idle_cpus(p)) -+ resched_best_idle(p); -+} -+ -+/* -+ * The cpu cache locality difference between CPUs is used to determine how far -+ * to offset the virtual deadline. <2 difference in locality means that one -+ * timeslice difference is allowed longer for the cpu local tasks. This is -+ * enough in the common case when tasks are up to 2* number of CPUs to keep -+ * tasks within their shared cache CPUs only. CPUs on different nodes or not -+ * even in this domain (NUMA) have "4" difference, allowing 4 times longer -+ * deadlines before being taken onto another cpu, allowing for 2* the double -+ * seen by separate CPUs above. -+ * Simple summary: Virtual deadlines are equal on shared cache CPUs, double -+ * on separate CPUs and quadruple in separate NUMA nodes. -+ */ -+static inline int -+cache_distance(struct rq *task_rq, struct rq *rq, struct task_struct *p) -+{ -+ int locality = rq->cpu_locality[cpu_of(task_rq)] - 2; -+ -+ if (locality > 0) -+ return task_timeslice(p) << locality; -+ return 0; -+} -+#else /* CONFIG_SMP */ -+static inline void inc_qnr(void) -+{ -+} -+ -+static inline void dec_qnr(void) -+{ -+} -+ -+static inline int queued_notrunning(void) -+{ -+ return grq.nr_running; -+} -+ -+static inline void set_cpuidle_map(unsigned long cpu) -+{ -+} -+ -+static inline void clear_cpuidle_map(unsigned long cpu) -+{ -+} -+ -+static inline int suitable_idle_cpus(struct task_struct *p) -+{ -+ return uprq->curr == uprq->idle; -+} -+ -+static inline void resched_suitable_idle(struct task_struct *p) -+{ -+} -+ -+static inline int -+cache_distance(struct rq *task_rq, struct rq *rq, struct task_struct *p) -+{ -+ return 0; -+} -+#endif /* CONFIG_SMP */ -+ -+/* -+ * activate_idle_task - move idle task to the _front_ of runqueue. -+ */ -+static inline void activate_idle_task(struct task_struct *p) -+{ -+ enqueue_task_head(p); -+ grq.nr_running++; -+ inc_qnr(); -+} -+ -+static inline int normal_prio(struct task_struct *p) -+{ -+ if (has_rt_policy(p)) -+ return MAX_RT_PRIO - 1 - p->rt_priority; -+ if (idleprio_task(p)) -+ return IDLE_PRIO; -+ if (iso_task(p)) -+ return ISO_PRIO; -+ return NORMAL_PRIO; -+} -+ -+/* -+ * Calculate the current priority, i.e. the priority -+ * taken into account by the scheduler. This value might -+ * be boosted by RT tasks as it will be RT if the task got -+ * RT-boosted. If not then it returns p->normal_prio. -+ */ -+static int effective_prio(struct task_struct *p) -+{ -+ p->normal_prio = normal_prio(p); -+ /* -+ * If we are RT tasks or we were boosted to RT priority, -+ * keep the priority unchanged. Otherwise, update priority -+ * to the normal priority: -+ */ -+ if (!rt_prio(p->prio)) -+ return p->normal_prio; -+ return p->prio; -+} -+ -+/* -+ * activate_task - move a task to the runqueue. Enter with grq locked. -+ */ -+static void activate_task(struct task_struct *p, struct rq *rq) -+{ -+ update_clocks(rq); -+ -+ /* -+ * Sleep time is in units of nanosecs, so shift by 20 to get a -+ * milliseconds-range estimation of the amount of time that the task -+ * spent sleeping: -+ */ -+ if (unlikely(prof_on == SLEEP_PROFILING)) { -+ if (p->state == TASK_UNINTERRUPTIBLE) -+ profile_hits(SLEEP_PROFILING, (void *)get_wchan(p), -+ (rq->clock - p->last_ran) >> 20); -+ } -+ -+ p->prio = effective_prio(p); -+ if (task_contributes_to_load(p)) -+ grq.nr_uninterruptible--; -+ enqueue_task(p); -+ grq.nr_running++; -+ inc_qnr(); -+} -+ -+/* -+ * deactivate_task - If it's running, it's not on the grq and we can just -+ * decrement the nr_running. Enter with grq locked. -+ */ -+static inline void deactivate_task(struct task_struct *p) -+{ -+ if (task_contributes_to_load(p)) -+ grq.nr_uninterruptible++; -+ grq.nr_running--; -+} -+ -+#ifdef CONFIG_SMP -+void set_task_cpu(struct task_struct *p, unsigned int cpu) -+{ -+ trace_sched_migrate_task(p, cpu); -+ if (task_cpu(p) != cpu) -+ perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0); -+ -+ /* -+ * After ->cpu is set up to a new value, task_grq_lock(p, ...) can be -+ * successfuly executed on another CPU. We must ensure that updates of -+ * per-task data have been completed by this moment. -+ */ -+ smp_wmb(); -+ task_thread_info(p)->cpu = cpu; -+} -+#endif -+ -+/* -+ * Move a task off the global queue and take it to a cpu for it will -+ * become the running task. -+ */ -+static inline void take_task(struct rq *rq, struct task_struct *p) -+{ -+ set_task_cpu(p, cpu_of(rq)); -+ dequeue_task(p); -+ dec_qnr(); -+} -+ -+/* -+ * Returns a descheduling task to the grq runqueue unless it is being -+ * deactivated. -+ */ -+static inline void return_task(struct task_struct *p, int deactivate) -+{ -+ if (deactivate) -+ deactivate_task(p); -+ else { -+ inc_qnr(); -+ enqueue_task(p); -+ } -+} -+ -+/* -+ * resched_task - mark a task 'to be rescheduled now'. -+ * -+ * On UP this means the setting of the need_resched flag, on SMP it -+ * might also involve a cross-CPU call to trigger the scheduler on -+ * the target CPU. -+ */ -+#ifdef CONFIG_SMP -+ -+#ifndef tsk_is_polling -+#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) -+#endif -+ -+static void resched_task(struct task_struct *p) -+{ -+ int cpu; -+ -+ assert_raw_spin_locked(&grq.lock); -+ -+ if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED))) -+ return; -+ -+ set_tsk_thread_flag(p, TIF_NEED_RESCHED); -+ -+ cpu = task_cpu(p); -+ if (cpu == smp_processor_id()) -+ return; -+ -+ /* NEED_RESCHED must be visible before we test polling */ -+ smp_mb(); -+ if (!tsk_is_polling(p)) -+ smp_send_reschedule(cpu); -+} -+ -+#else -+static inline void resched_task(struct task_struct *p) -+{ -+ assert_raw_spin_locked(&grq.lock); -+ set_tsk_need_resched(p); -+} -+#endif -+ -+/** -+ * task_curr - is this task currently executing on a CPU? -+ * @p: the task in question. -+ */ -+inline int task_curr(const struct task_struct *p) -+{ -+ return cpu_curr(task_cpu(p)) == p; -+} -+ -+#ifdef CONFIG_SMP -+struct migration_req { -+ struct task_struct *task; -+ int dest_cpu; -+}; -+ -+/* -+ * wait_task_inactive - wait for a thread to unschedule. -+ * -+ * If @match_state is nonzero, it's the @p->state value just checked and -+ * not expected to change. If it changes, i.e. @p might have woken up, -+ * then return zero. When we succeed in waiting for @p to be off its CPU, -+ * we return a positive number (its total switch count). If a second call -+ * a short while later returns the same number, the caller can be sure that -+ * @p has remained unscheduled the whole time. -+ * -+ * The caller must ensure that the task *will* unschedule sometime soon, -+ * else this function might spin for a *long* time. This function can't -+ * be called with interrupts off, or it may introduce deadlock with -+ * smp_call_function() if an IPI is sent by the same process we are -+ * waiting to become inactive. -+ */ -+unsigned long wait_task_inactive(struct task_struct *p, long match_state) -+{ -+ unsigned long flags; -+ int running, on_rq; -+ unsigned long ncsw; -+ struct rq *rq; -+ -+ for (;;) { -+ /* -+ * We do the initial early heuristics without holding -+ * any task-queue locks at all. We'll only try to get -+ * the runqueue lock when things look like they will -+ * work out! In the unlikely event rq is dereferenced -+ * since we're lockless, grab it again. -+ */ -+#ifdef CONFIG_SMP -+retry_rq: -+ rq = task_rq(p); -+ if (unlikely(!rq)) -+ goto retry_rq; -+#else /* CONFIG_SMP */ -+ rq = task_rq(p); -+#endif -+ /* -+ * If the task is actively running on another CPU -+ * still, just relax and busy-wait without holding -+ * any locks. -+ * -+ * NOTE! Since we don't hold any locks, it's not -+ * even sure that "rq" stays as the right runqueue! -+ * But we don't care, since this will return false -+ * if the runqueue has changed and p is actually now -+ * running somewhere else! -+ */ -+ while (task_running(p) && p == rq->curr) { -+ if (match_state && unlikely(p->state != match_state)) -+ return 0; -+ cpu_relax(); -+ } -+ -+ /* -+ * Ok, time to look more closely! We need the grq -+ * lock now, to be *sure*. If we're wrong, we'll -+ * just go back and repeat. -+ */ -+ rq = task_grq_lock(p, &flags); -+ trace_sched_wait_task(p); -+ running = task_running(p); -+ on_rq = task_queued(p); -+ ncsw = 0; -+ if (!match_state || p->state == match_state) -+ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ -+ task_grq_unlock(&flags); -+ -+ /* -+ * If it changed from the expected state, bail out now. -+ */ -+ if (unlikely(!ncsw)) -+ break; -+ -+ /* -+ * Was it really running after all now that we -+ * checked with the proper locks actually held? -+ * -+ * Oops. Go back and try again.. -+ */ -+ if (unlikely(running)) { -+ cpu_relax(); -+ continue; -+ } -+ -+ /* -+ * It's not enough that it's not actively running, -+ * it must be off the runqueue _entirely_, and not -+ * preempted! -+ * -+ * So if it was still runnable (but just not actively -+ * running right now), it's preempted, and we should -+ * yield - it could be a while. -+ */ -+ if (unlikely(on_rq)) { -+ schedule_timeout_uninterruptible(1); -+ continue; -+ } -+ -+ /* -+ * Ahh, all good. It wasn't running, and it wasn't -+ * runnable, which means that it will never become -+ * running in the future either. We're all done! -+ */ -+ break; -+ } -+ -+ return ncsw; -+} -+ -+/*** -+ * kick_process - kick a running thread to enter/exit the kernel -+ * @p: the to-be-kicked thread -+ * -+ * Cause a process which is running on another CPU to enter -+ * kernel-mode, without any delay. (to get signals handled.) -+ * -+ * NOTE: this function doesnt have to take the runqueue lock, -+ * because all it wants to ensure is that the remote task enters -+ * the kernel. If the IPI races and the task has been migrated -+ * to another CPU then no harm is done and the purpose has been -+ * achieved as well. -+ */ -+void kick_process(struct task_struct *p) -+{ -+ int cpu; -+ -+ preempt_disable(); -+ cpu = task_cpu(p); -+ if ((cpu != smp_processor_id()) && task_curr(p)) -+ smp_send_reschedule(cpu); -+ preempt_enable(); -+} -+EXPORT_SYMBOL_GPL(kick_process); -+#endif -+ -+#define rq_idle(rq) ((rq)->rq_prio == PRIO_LIMIT) -+ -+/* -+ * RT tasks preempt purely on priority. SCHED_NORMAL tasks preempt on the -+ * basis of earlier deadlines. SCHED_IDLEPRIO don't preempt anything else or -+ * between themselves, they cooperatively multitask. An idle rq scores as -+ * prio PRIO_LIMIT so it is always preempted. -+ */ -+static inline int -+can_preempt(struct task_struct *p, int prio, u64 deadline, -+ unsigned int policy) -+{ -+ /* Better static priority RT task or better policy preemption */ -+ if (p->prio < prio) -+ return 1; -+ if (p->prio > prio) -+ return 0; -+ /* SCHED_NORMAL, BATCH and ISO will preempt based on deadline */ -+ if (!deadline_before(p->deadline, deadline)) -+ return 0; -+ return 1; -+} -+#ifdef CONFIG_SMP -+#ifdef CONFIG_HOTPLUG_CPU -+/* -+ * Check to see if there is a task that is affined only to offline CPUs but -+ * still wants runtime. This happens to kernel threads during suspend/halt and -+ * disabling of CPUs. -+ */ -+static inline int online_cpus(struct task_struct *p) -+{ -+ return (likely(cpus_intersects(cpu_online_map, p->cpus_allowed))); -+} -+#else /* CONFIG_HOTPLUG_CPU */ -+/* All available CPUs are always online without hotplug. */ -+static inline int online_cpus(struct task_struct *p) -+{ -+ return 1; -+} -+#endif -+ -+/* -+ * Check to see if p can run on cpu, and if not, whether there are any online -+ * CPUs it can run on instead. -+ */ -+static inline int needs_other_cpu(struct task_struct *p, int cpu) -+{ -+ if (unlikely(!cpu_isset(cpu, p->cpus_allowed))) -+ return 1; -+ return 0; -+} -+ -+/* -+ * latest_deadline and highest_prio_rq are initialised only to silence the -+ * compiler. When all else is equal, still prefer this_rq. -+ */ -+static void try_preempt(struct task_struct *p, struct rq *this_rq) -+{ -+ struct rq *highest_prio_rq = this_rq; -+ u64 latest_deadline; -+ unsigned long cpu; -+ int highest_prio; -+ cpumask_t tmp; -+ -+ if (suitable_idle_cpus(p)) { -+ resched_best_idle(p); -+ return; -+ } -+ -+ /* IDLEPRIO tasks never preempt anything */ -+ if (p->policy == SCHED_IDLEPRIO) -+ return; -+ -+ if (likely(online_cpus(p))) -+ cpus_and(tmp, cpu_online_map, p->cpus_allowed); -+ else -+ return; -+ -+ latest_deadline = 0; -+ highest_prio = -1; -+ -+ for_each_cpu_mask(cpu, tmp) { -+ u64 offset_deadline; -+ struct rq *rq; -+ int rq_prio; -+ -+ rq = cpu_rq(cpu); -+ rq_prio = rq->rq_prio; -+ if (rq_prio < highest_prio) -+ continue; -+ -+ offset_deadline = rq->rq_deadline - -+ cache_distance(this_rq, rq, p); -+ -+ if (rq_prio > highest_prio || (rq_prio == highest_prio && -+ deadline_after(offset_deadline, latest_deadline))) { -+ latest_deadline = offset_deadline; -+ highest_prio = rq_prio; -+ highest_prio_rq = rq; -+ } -+ } -+ -+ if (!can_preempt(p, highest_prio, highest_prio_rq->rq_deadline, -+ highest_prio_rq->rq_policy)) -+ return; -+ -+ resched_task(highest_prio_rq->curr); -+} -+#else /* CONFIG_SMP */ -+static inline int needs_other_cpu(struct task_struct *p, int cpu) -+{ -+ return 0; -+} -+ -+static void try_preempt(struct task_struct *p, struct rq *this_rq) -+{ -+ if (p->policy == SCHED_IDLEPRIO) -+ return; -+ if (can_preempt(p, uprq->rq_prio, uprq->rq_deadline, -+ uprq->rq_policy)) -+ resched_task(uprq->curr); -+} -+#endif /* CONFIG_SMP */ -+ -+/** -+ * task_oncpu_function_call - call a function on the cpu on which a task runs -+ * @p: the task to evaluate -+ * @func: the function to be called -+ * @info: the function call argument -+ * -+ * Calls the function @func when the task is currently running. This might -+ * be on the current CPU, which just calls the function directly -+ */ -+void task_oncpu_function_call(struct task_struct *p, -+ void (*func) (void *info), void *info) -+{ -+ int cpu; -+ -+ preempt_disable(); -+ cpu = task_cpu(p); -+ if (task_curr(p)) -+ smp_call_function_single(cpu, func, info, 1); -+ preempt_enable(); -+} -+ -+static inline void ttwu_activate(struct task_struct *p, struct rq *rq, -+ bool is_sync) -+{ -+ activate_task(p, rq); -+ -+ /* -+ * Sync wakeups (i.e. those types of wakeups where the waker -+ * has indicated that it will leave the CPU in short order) -+ * don't trigger a preemption if there are no idle cpus, -+ * instead waiting for current to deschedule. -+ */ -+ if (!is_sync || suitable_idle_cpus(p)) -+ try_preempt(p, rq); -+} -+ -+static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, -+ bool success) -+{ -+ trace_sched_wakeup(p, success); -+ p->state = TASK_RUNNING; -+ -+ /* -+ * if a worker is waking up, notify workqueue. Note that on BFS, we -+ * don't really know what cpu it will be, so we fake it for -+ * wq_worker_waking_up :/ -+ */ -+ if ((p->flags & PF_WQ_WORKER) && success) -+ wq_worker_waking_up(p, cpu_of(rq)); -+} -+ -+/*** -+ * try_to_wake_up - wake up a thread -+ * @p: the thread to be awakened -+ * @state: the mask of task states that can be woken -+ * @wake_flags: wake modifier flags (WF_*) -+ * -+ * Put it on the run-queue if it's not already there. The "current" -+ * thread is always on the run-queue (except when the actual -+ * re-schedule is in progress), and as such you're allowed to do -+ * the simpler "current->state = TASK_RUNNING" to mark yourself -+ * runnable without the overhead of this. -+ * -+ * Returns %true if @p was woken up, %false if it was already running -+ * or @state didn't match @p's state. -+ */ -+static int try_to_wake_up(struct task_struct *p, unsigned int state, -+ int wake_flags) -+{ -+ unsigned long flags; -+ int success = 0; -+ struct rq *rq; -+ -+ get_cpu(); -+ -+ /* This barrier is undocumented, probably for p->state? くそ */ -+ smp_wmb(); -+ -+ /* -+ * No need to do time_lock_grq as we only need to update the rq clock -+ * if we activate the task -+ */ -+ rq = task_grq_lock(p, &flags); -+ -+ /* state is a volatile long, どうして、分からない */ -+ if (!((unsigned int)p->state & state)) -+ goto out_unlock; -+ -+ if (task_queued(p) || task_running(p)) -+ goto out_running; -+ -+ ttwu_activate(p, rq, wake_flags & WF_SYNC); -+ success = true; -+ -+out_running: -+ ttwu_post_activation(p, rq, success); -+out_unlock: -+ task_grq_unlock(&flags); -+ put_cpu(); -+ -+ return success; -+} -+ -+/** -+ * try_to_wake_up_local - try to wake up a local task with grq lock held -+ * @p: the thread to be awakened -+ * -+ * Put @p on the run-queue if it's not already there. The caller must -+ * ensure that grq is locked and, @p is not the current task. -+ * grq stays locked over invocation. -+ */ -+static void try_to_wake_up_local(struct task_struct *p) -+{ -+ struct rq *rq = task_rq(p); -+ bool success = false; -+ -+ WARN_ON(rq != this_rq()); -+ BUG_ON(p == current); -+ lockdep_assert_held(&grq.lock); -+ -+ if (!(p->state & TASK_NORMAL)) -+ return; -+ -+ if (!task_queued(p)) { -+ if (likely(!task_running(p))) { -+ schedstat_inc(rq, ttwu_count); -+ schedstat_inc(rq, ttwu_local); -+ } -+ ttwu_activate(p, rq, false); -+ success = true; -+ } -+ ttwu_post_activation(p, rq, success); -+} -+ -+/** -+ * wake_up_process - Wake up a specific process -+ * @p: The process to be woken up. -+ * -+ * Attempt to wake up the nominated process and move it to the set of runnable -+ * processes. Returns 1 if the process was woken up, 0 if it was already -+ * running. -+ * -+ * It may be assumed that this function implies a write memory barrier before -+ * changing the task state if and only if any tasks are woken up. -+ */ -+int wake_up_process(struct task_struct *p) -+{ -+ return try_to_wake_up(p, TASK_ALL, 0); -+} -+EXPORT_SYMBOL(wake_up_process); -+ -+int wake_up_state(struct task_struct *p, unsigned int state) -+{ -+ return try_to_wake_up(p, state, 0); -+} -+ -+static void time_slice_expired(struct task_struct *p); -+ -+/* -+ * Perform scheduler related setup for a newly forked process p. -+ * p is forked by current. -+ */ -+void sched_fork(struct task_struct *p, int clone_flags) -+{ -+ struct task_struct *curr; -+ int cpu = get_cpu(); -+ struct rq *rq; -+ -+#ifdef CONFIG_PREEMPT_NOTIFIERS -+ INIT_HLIST_HEAD(&p->preempt_notifiers); -+#endif -+ /* -+ * We mark the process as running here. This guarantees that -+ * nobody will actually run it, and a signal or other external -+ * event cannot wake it up and insert it on the runqueue either. -+ */ -+ p->state = TASK_RUNNING; -+ set_task_cpu(p, cpu); -+ -+ /* Should be reset in fork.c but done here for ease of bfs patching */ -+ p->sched_time = p->stime_pc = p->utime_pc = 0; -+ -+ /* -+ * Revert to default priority/policy on fork if requested. -+ */ -+ if (unlikely(p->sched_reset_on_fork)) { -+ if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { -+ p->policy = SCHED_NORMAL; -+ p->normal_prio = normal_prio(p); -+ } -+ -+ if (PRIO_TO_NICE(p->static_prio) < 0) { -+ p->static_prio = NICE_TO_PRIO(0); -+ p->normal_prio = p->static_prio; -+ } -+ -+ /* -+ * We don't need the reset flag anymore after the fork. It has -+ * fulfilled its duty: -+ */ -+ p->sched_reset_on_fork = 0; -+ } -+ -+ curr = current; -+ /* -+ * Make sure we do not leak PI boosting priority to the child. -+ */ -+ p->prio = curr->normal_prio; -+ -+ INIT_LIST_HEAD(&p->run_list); -+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) -+ if (unlikely(sched_info_on())) -+ memset(&p->sched_info, 0, sizeof(p->sched_info)); -+#endif -+ -+ p->oncpu = 0; -+ -+#ifdef CONFIG_PREEMPT -+ /* Want to start with kernel preemption disabled. */ -+ task_thread_info(p)->preempt_count = 1; -+#endif -+ if (unlikely(p->policy == SCHED_FIFO)) -+ goto out; -+ /* -+ * Share the timeslice between parent and child, thus the -+ * total amount of pending timeslices in the system doesn't change, -+ * resulting in more scheduling fairness. If it's negative, it won't -+ * matter since that's the same as being 0. current's time_slice is -+ * actually in rq_time_slice when it's running, as is its last_ran -+ * value. rq->rq_deadline is only modified within schedule() so it -+ * is always equal to current->deadline. -+ */ -+ rq = task_grq_lock_irq(curr); -+ if (likely(rq->rq_time_slice >= RESCHED_US * 2)) { -+ rq->rq_time_slice /= 2; -+ p->time_slice = rq->rq_time_slice; -+ } else { -+ /* -+ * Forking task has run out of timeslice. Reschedule it and -+ * start its child with a new time slice and deadline. The -+ * child will end up running first because its deadline will -+ * be slightly earlier. -+ */ -+ rq->rq_time_slice = 0; -+ set_tsk_need_resched(curr); -+ time_slice_expired(p); -+ } -+ p->last_ran = rq->rq_last_ran; -+ task_grq_unlock_irq(); -+out: -+ put_cpu(); -+} -+ -+/* -+ * wake_up_new_task - wake up a newly created task for the first time. -+ * -+ * This function will do some initial scheduler statistics housekeeping -+ * that must be done for every newly created context, then puts the task -+ * on the runqueue and wakes it. -+ */ -+void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) -+{ -+ struct task_struct *parent; -+ unsigned long flags; -+ struct rq *rq; -+ -+ rq = task_grq_lock(p, &flags); -+ p->state = TASK_RUNNING; -+ parent = p->parent; -+ /* Unnecessary but small chance that the parent changed CPU */ -+ set_task_cpu(p, task_cpu(parent)); -+ activate_task(p, rq); -+ trace_sched_wakeup_new(p, 1); -+ if (!(clone_flags & CLONE_VM) && rq->curr == parent && -+ !suitable_idle_cpus(p)) { -+ /* -+ * The VM isn't cloned, so we're in a good position to -+ * do child-runs-first in anticipation of an exec. This -+ * usually avoids a lot of COW overhead. -+ */ -+ resched_task(parent); -+ } else -+ try_preempt(p, rq); -+ task_grq_unlock(&flags); -+} -+ -+#ifdef CONFIG_PREEMPT_NOTIFIERS -+ -+/** -+ * preempt_notifier_register - tell me when current is being preempted & rescheduled -+ * @notifier: notifier struct to register -+ */ -+void preempt_notifier_register(struct preempt_notifier *notifier) -+{ -+ hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); -+} -+EXPORT_SYMBOL_GPL(preempt_notifier_register); -+ -+/** -+ * preempt_notifier_unregister - no longer interested in preemption notifications -+ * @notifier: notifier struct to unregister -+ * -+ * This is safe to call from within a preemption notifier. -+ */ -+void preempt_notifier_unregister(struct preempt_notifier *notifier) -+{ -+ hlist_del(¬ifier->link); -+} -+EXPORT_SYMBOL_GPL(preempt_notifier_unregister); -+ -+static void fire_sched_in_preempt_notifiers(struct task_struct *curr) -+{ -+ struct preempt_notifier *notifier; -+ struct hlist_node *node; -+ -+ hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) -+ notifier->ops->sched_in(notifier, raw_smp_processor_id()); -+} -+ -+static void -+fire_sched_out_preempt_notifiers(struct task_struct *curr, -+ struct task_struct *next) -+{ -+ struct preempt_notifier *notifier; -+ struct hlist_node *node; -+ -+ hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) -+ notifier->ops->sched_out(notifier, next); -+} -+ -+#else /* !CONFIG_PREEMPT_NOTIFIERS */ -+ -+static void fire_sched_in_preempt_notifiers(struct task_struct *curr) -+{ -+} -+ -+static void -+fire_sched_out_preempt_notifiers(struct task_struct *curr, -+ struct task_struct *next) -+{ -+} -+ -+#endif /* CONFIG_PREEMPT_NOTIFIERS */ -+ -+/** -+ * prepare_task_switch - prepare to switch tasks -+ * @rq: the runqueue preparing to switch -+ * @next: the task we are going to switch to. -+ * -+ * This is called with the rq lock held and interrupts off. It must -+ * be paired with a subsequent finish_task_switch after the context -+ * switch. -+ * -+ * prepare_task_switch sets up locking and calls architecture specific -+ * hooks. -+ */ -+static inline void -+prepare_task_switch(struct rq *rq, struct task_struct *prev, -+ struct task_struct *next) -+{ -+ fire_sched_out_preempt_notifiers(prev, next); -+ prepare_lock_switch(rq, next); -+ prepare_arch_switch(next); -+} -+ -+/** -+ * finish_task_switch - clean up after a task-switch -+ * @rq: runqueue associated with task-switch -+ * @prev: the thread we just switched away from. -+ * -+ * finish_task_switch must be called after the context switch, paired -+ * with a prepare_task_switch call before the context switch. -+ * finish_task_switch will reconcile locking set up by prepare_task_switch, -+ * and do any other architecture-specific cleanup actions. -+ * -+ * Note that we may have delayed dropping an mm in context_switch(). If -+ * so, we finish that here outside of the runqueue lock. (Doing it -+ * with the lock held can cause deadlocks; see schedule() for -+ * details.) -+ */ -+static inline void finish_task_switch(struct rq *rq, struct task_struct *prev) -+ __releases(grq.lock) -+{ -+ struct mm_struct *mm = rq->prev_mm; -+ long prev_state; -+ -+ rq->prev_mm = NULL; -+ -+ /* -+ * A task struct has one reference for the use as "current". -+ * If a task dies, then it sets TASK_DEAD in tsk->state and calls -+ * schedule one last time. The schedule call will never return, and -+ * the scheduled task must drop that reference. -+ * The test for TASK_DEAD must occur while the runqueue locks are -+ * still held, otherwise prev could be scheduled on another cpu, die -+ * there before we look at prev->state, and then the reference would -+ * be dropped twice. -+ * Manfred Spraul -+ */ -+ prev_state = prev->state; -+ finish_arch_switch(prev); -+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -+ local_irq_disable(); -+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ -+ perf_event_task_sched_in(current); -+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -+ local_irq_enable(); -+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ -+ finish_lock_switch(rq, prev); -+ -+ fire_sched_in_preempt_notifiers(current); -+ if (mm) -+ mmdrop(mm); -+ if (unlikely(prev_state == TASK_DEAD)) { -+ /* -+ * Remove function-return probe instances associated with this -+ * task and put them back on the free list. -+ */ -+ kprobe_flush_task(prev); -+ put_task_struct(prev); -+ } -+} -+ -+/** -+ * schedule_tail - first thing a freshly forked thread must call. -+ * @prev: the thread we just switched away from. -+ */ -+asmlinkage void schedule_tail(struct task_struct *prev) -+ __releases(grq.lock) -+{ -+ struct rq *rq = this_rq(); -+ -+ finish_task_switch(rq, prev); -+#ifdef __ARCH_WANT_UNLOCKED_CTXSW -+ /* In this case, finish_task_switch does not reenable preemption */ -+ preempt_enable(); -+#endif -+ if (current->set_child_tid) -+ put_user(current->pid, current->set_child_tid); -+} -+ -+/* -+ * context_switch - switch to the new MM and the new -+ * thread's register state. -+ */ -+static inline void -+context_switch(struct rq *rq, struct task_struct *prev, -+ struct task_struct *next) -+{ -+ struct mm_struct *mm, *oldmm; -+ -+ prepare_task_switch(rq, prev, next); -+ trace_sched_switch(prev, next); -+ mm = next->mm; -+ oldmm = prev->active_mm; -+ /* -+ * For paravirt, this is coupled with an exit in switch_to to -+ * combine the page table reload and the switch backend into -+ * one hypercall. -+ */ -+ arch_start_context_switch(prev); -+ -+ if (!mm) { -+ next->active_mm = oldmm; -+ atomic_inc(&oldmm->mm_count); -+ enter_lazy_tlb(oldmm, next); -+ } else -+ switch_mm(oldmm, mm, next); -+ -+ if (!prev->mm) { -+ prev->active_mm = NULL; -+ rq->prev_mm = oldmm; -+ } -+ /* -+ * Since the runqueue lock will be released by the next -+ * task (which is an invalid locking op but in the case -+ * of the scheduler it's an obvious special-case), so we -+ * do an early lockdep release here: -+ */ -+#ifndef __ARCH_WANT_UNLOCKED_CTXSW -+ spin_release(&grq.lock.dep_map, 1, _THIS_IP_); -+#endif -+ -+ /* Here we just switch the register state and the stack. */ -+ switch_to(prev, next, prev); -+ -+ barrier(); -+ /* -+ * this_rq must be evaluated again because prev may have moved -+ * CPUs since it called schedule(), thus the 'rq' on its stack -+ * frame will be invalid. -+ */ -+ finish_task_switch(this_rq(), prev); -+} -+ -+/* -+ * nr_running, nr_uninterruptible and nr_context_switches: -+ * -+ * externally visible scheduler statistics: current number of runnable -+ * threads, current number of uninterruptible-sleeping threads, total -+ * number of context switches performed since bootup. All are measured -+ * without grabbing the grq lock but the occasional inaccurate result -+ * doesn't matter so long as it's positive. -+ */ -+unsigned long nr_running(void) -+{ -+ long nr = grq.nr_running; -+ -+ if (unlikely(nr < 0)) -+ nr = 0; -+ return (unsigned long)nr; -+} -+ -+unsigned long nr_uninterruptible(void) -+{ -+ long nu = grq.nr_uninterruptible; -+ -+ if (unlikely(nu < 0)) -+ nu = 0; -+ return nu; -+} -+ -+unsigned long long nr_context_switches(void) -+{ -+ long long ns = grq.nr_switches; -+ -+ /* This is of course impossible */ -+ if (unlikely(ns < 0)) -+ ns = 1; -+ return (long long)ns; -+} -+ -+unsigned long nr_iowait(void) -+{ -+ unsigned long i, sum = 0; -+ -+ for_each_possible_cpu(i) -+ sum += atomic_read(&cpu_rq(i)->nr_iowait); -+ -+ return sum; -+} -+ -+unsigned long nr_iowait_cpu(int cpu) -+{ -+ struct rq *this = cpu_rq(cpu); -+ return atomic_read(&this->nr_iowait); -+} -+ -+unsigned long nr_active(void) -+{ -+ return nr_running() + nr_uninterruptible(); -+} -+ -+/* Beyond a task running on this CPU, load is equal everywhere on BFS */ -+unsigned long this_cpu_load(void) -+{ -+ return this_rq()->rq_running + -+ (queued_notrunning() + nr_uninterruptible()) / -+ (1 + num_online_cpus()); -+} -+ -+/* Variables and functions for calc_load */ -+static unsigned long calc_load_update; -+unsigned long avenrun[3]; -+EXPORT_SYMBOL(avenrun); -+ -+/** -+ * get_avenrun - get the load average array -+ * @loads: pointer to dest load array -+ * @offset: offset to add -+ * @shift: shift count to shift the result left -+ * -+ * These values are estimates at best, so no need for locking. -+ */ -+void get_avenrun(unsigned long *loads, unsigned long offset, int shift) -+{ -+ loads[0] = (avenrun[0] + offset) << shift; -+ loads[1] = (avenrun[1] + offset) << shift; -+ loads[2] = (avenrun[2] + offset) << shift; -+} -+ -+static unsigned long -+calc_load(unsigned long load, unsigned long exp, unsigned long active) -+{ -+ load *= exp; -+ load += active * (FIXED_1 - exp); -+ return load >> FSHIFT; -+} -+ -+/* -+ * calc_load - update the avenrun load estimates every LOAD_FREQ seconds. -+ */ -+void calc_global_load(unsigned long ticks) -+{ -+ long active; -+ -+ if (time_before(jiffies, calc_load_update)) -+ return; -+ active = nr_active() * FIXED_1; -+ -+ avenrun[0] = calc_load(avenrun[0], EXP_1, active); -+ avenrun[1] = calc_load(avenrun[1], EXP_5, active); -+ avenrun[2] = calc_load(avenrun[2], EXP_15, active); -+ -+ calc_load_update = jiffies + LOAD_FREQ; -+} -+ -+DEFINE_PER_CPU(struct kernel_stat, kstat); -+ -+EXPORT_PER_CPU_SYMBOL(kstat); -+ -+#ifdef CONFIG_IRQ_TIME_ACCOUNTING -+ -+/* -+ * There are no locks covering percpu hardirq/softirq time. -+ * They are only modified in account_system_vtime, on corresponding CPU -+ * with interrupts disabled. So, writes are safe. -+ * They are read and saved off onto struct rq in update_rq_clock(). -+ * This may result in other CPU reading this CPU's irq time and can -+ * race with irq/account_system_vtime on this CPU. We would either get old -+ * or new value with a side effect of accounting a slice of irq time to wrong -+ * task when irq is in progress while we read rq->clock. That is a worthy -+ * compromise in place of having locks on each irq in account_system_time. -+ */ -+static DEFINE_PER_CPU(u64, cpu_hardirq_time); -+static DEFINE_PER_CPU(u64, cpu_softirq_time); -+ -+static DEFINE_PER_CPU(u64, irq_start_time); -+static int sched_clock_irqtime; -+ -+void enable_sched_clock_irqtime(void) -+{ -+ sched_clock_irqtime = 1; -+} -+ -+void disable_sched_clock_irqtime(void) -+{ -+ sched_clock_irqtime = 0; -+} -+ -+#ifndef CONFIG_64BIT -+static DEFINE_PER_CPU(seqcount_t, irq_time_seq); -+ -+static inline void irq_time_write_begin(void) -+{ -+ __this_cpu_inc(irq_time_seq.sequence); -+ smp_wmb(); -+} -+ -+static inline void irq_time_write_end(void) -+{ -+ smp_wmb(); -+ __this_cpu_inc(irq_time_seq.sequence); -+} -+ -+static inline u64 irq_time_read(int cpu) -+{ -+ u64 irq_time; -+ unsigned seq; -+ -+ do { -+ seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); -+ irq_time = per_cpu(cpu_softirq_time, cpu) + -+ per_cpu(cpu_hardirq_time, cpu); -+ } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); -+ -+ return irq_time; -+} -+#else /* CONFIG_64BIT */ -+static inline void irq_time_write_begin(void) -+{ -+} -+ -+static inline void irq_time_write_end(void) -+{ -+} -+ -+static inline u64 irq_time_read(int cpu) -+{ -+ return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); -+} -+#endif /* CONFIG_64BIT */ -+ -+/* -+ * Called before incrementing preempt_count on {soft,}irq_enter -+ * and before decrementing preempt_count on {soft,}irq_exit. -+ */ -+void account_system_vtime(struct task_struct *curr) -+{ -+ unsigned long flags; -+ s64 delta; -+ int cpu; -+ -+ if (!sched_clock_irqtime) -+ return; -+ -+ local_irq_save(flags); -+ -+ cpu = smp_processor_id(); -+ delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); -+ __this_cpu_add(irq_start_time, delta); -+ -+ irq_time_write_begin(); -+ /* -+ * We do not account for softirq time from ksoftirqd here. -+ * We want to continue accounting softirq time to ksoftirqd thread -+ * in that case, so as not to confuse scheduler with a special task -+ * that do not consume any time, but still wants to run. -+ */ -+ if (hardirq_count()) -+ __this_cpu_add(cpu_hardirq_time, delta); -+ else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD)) -+ __this_cpu_add(cpu_softirq_time, delta); -+ -+ irq_time_write_end(); -+ local_irq_restore(flags); -+} -+EXPORT_SYMBOL_GPL(account_system_vtime); -+ -+static void update_rq_clock_task(struct rq *rq, s64 delta) -+{ -+ s64 irq_delta; -+ -+ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; -+ -+ /* -+ * Since irq_time is only updated on {soft,}irq_exit, we might run into -+ * this case when a previous update_rq_clock() happened inside a -+ * {soft,}irq region. -+ * -+ * When this happens, we stop ->clock_task and only update the -+ * prev_irq_time stamp to account for the part that fit, so that a next -+ * update will consume the rest. This ensures ->clock_task is -+ * monotonic. -+ * -+ * It does however cause some slight miss-attribution of {soft,}irq -+ * time, a more accurate solution would be to update the irq_time using -+ * the current rq->clock timestamp, except that would require using -+ * atomic ops. -+ */ -+ if (irq_delta > delta) -+ irq_delta = delta; -+ -+ rq->prev_irq_time += irq_delta; -+ delta -= irq_delta; -+ rq->clock_task += delta; -+} -+ -+#else /* CONFIG_IRQ_TIME_ACCOUNTING */ -+ -+static void update_rq_clock_task(struct rq *rq, s64 delta) -+{ -+ rq->clock_task += delta; -+} -+ -+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ -+ -+/* -+ * On each tick, see what percentage of that tick was attributed to each -+ * component and add the percentage to the _pc values. Once a _pc value has -+ * accumulated one tick's worth, account for that. This means the total -+ * percentage of load components will always be 100 per tick. -+ */ -+static void pc_idle_time(struct rq *rq, unsigned long pc) -+{ -+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; -+ cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); -+ -+ if (atomic_read(&rq->nr_iowait) > 0) { -+ rq->iowait_pc += pc; -+ if (rq->iowait_pc >= 100) { -+ rq->iowait_pc %= 100; -+ cpustat->iowait = cputime64_add(cpustat->iowait, tmp); -+ } -+ } else { -+ rq->idle_pc += pc; -+ if (rq->idle_pc >= 100) { -+ rq->idle_pc %= 100; -+ cpustat->idle = cputime64_add(cpustat->idle, tmp); -+ } -+ } -+} -+ -+static void -+pc_system_time(struct rq *rq, struct task_struct *p, int hardirq_offset, -+ unsigned long pc, unsigned long ns) -+{ -+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; -+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); -+ cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); -+ -+ p->stime_pc += pc; -+ if (p->stime_pc >= 100) { -+ p->stime_pc -= 100; -+ p->stime = cputime_add(p->stime, cputime_one_jiffy); -+ p->stimescaled = cputime_add(p->stimescaled, one_jiffy_scaled); -+ account_group_system_time(p, cputime_one_jiffy); -+ acct_update_integrals(p); -+ } -+ p->sched_time += ns; -+ -+ if (hardirq_count() - hardirq_offset) { -+ rq->irq_pc += pc; -+ if (rq->irq_pc >= 100) { -+ rq->irq_pc %= 100; -+ cpustat->irq = cputime64_add(cpustat->irq, tmp); -+ } -+ } else if (in_serving_softirq()) { -+ rq->softirq_pc += pc; -+ if (rq->softirq_pc >= 100) { -+ rq->softirq_pc %= 100; -+ cpustat->softirq = cputime64_add(cpustat->softirq, tmp); -+ } -+ } else { -+ rq->system_pc += pc; -+ if (rq->system_pc >= 100) { -+ rq->system_pc %= 100; -+ cpustat->system = cputime64_add(cpustat->system, tmp); -+ } -+ } -+} -+ -+static void pc_user_time(struct rq *rq, struct task_struct *p, -+ unsigned long pc, unsigned long ns) -+{ -+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; -+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); -+ cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); -+ -+ p->utime_pc += pc; -+ if (p->utime_pc >= 100) { -+ p->utime_pc -= 100; -+ p->utime = cputime_add(p->utime, cputime_one_jiffy); -+ p->utimescaled = cputime_add(p->utimescaled, one_jiffy_scaled); -+ account_group_user_time(p, cputime_one_jiffy); -+ acct_update_integrals(p); -+ } -+ p->sched_time += ns; -+ -+ if (TASK_NICE(p) > 0 || idleprio_task(p)) { -+ rq->nice_pc += pc; -+ if (rq->nice_pc >= 100) { -+ rq->nice_pc %= 100; -+ cpustat->nice = cputime64_add(cpustat->nice, tmp); -+ } -+ } else { -+ rq->user_pc += pc; -+ if (rq->user_pc >= 100) { -+ rq->user_pc %= 100; -+ cpustat->user = cputime64_add(cpustat->user, tmp); -+ } -+ } -+} -+ -+/* Convert nanoseconds to percentage of one tick. */ -+#define NS_TO_PC(NS) (NS * 100 / JIFFY_NS) -+ -+/* -+ * This is called on clock ticks and on context switches. -+ * Bank in p->sched_time the ns elapsed since the last tick or switch. -+ * CPU scheduler quota accounting is also performed here in microseconds. -+ */ -+static void -+update_cpu_clock(struct rq *rq, struct task_struct *p, int tick) -+{ -+ long account_ns = rq->clock - rq->timekeep_clock; -+ struct task_struct *idle = rq->idle; -+ unsigned long account_pc; -+ -+ if (unlikely(account_ns < 0)) -+ account_ns = 0; -+ -+ account_pc = NS_TO_PC(account_ns); -+ -+ if (tick) { -+ int user_tick = user_mode(get_irq_regs()); -+ -+ /* Accurate tick timekeeping */ -+ if (user_tick) -+ pc_user_time(rq, p, account_pc, account_ns); -+ else if (p != idle || (irq_count() != HARDIRQ_OFFSET)) -+ pc_system_time(rq, p, HARDIRQ_OFFSET, -+ account_pc, account_ns); -+ else -+ pc_idle_time(rq, account_pc); -+ } else { -+ /* Accurate subtick timekeeping */ -+ if (p == idle) -+ pc_idle_time(rq, account_pc); -+ else -+ pc_user_time(rq, p, account_pc, account_ns); -+ } -+ -+ /* time_slice accounting is done in usecs to avoid overflow on 32bit */ -+ if (rq->rq_policy != SCHED_FIFO && p != idle) { -+ s64 time_diff = rq->clock - rq->rq_last_ran; -+ -+ niffy_diff(&time_diff, 1); -+ rq->rq_time_slice -= NS_TO_US(time_diff); -+ } -+ rq->rq_last_ran = rq->timekeep_clock = rq->clock; -+} -+ -+/* -+ * Return any ns on the sched_clock that have not yet been accounted in -+ * @p in case that task is currently running. -+ * -+ * Called with task_grq_lock() held. -+ */ -+static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) -+{ -+ u64 ns = 0; -+ -+ if (p == rq->curr) { -+ update_clocks(rq); -+ ns = rq->clock_task - rq->rq_last_ran; -+ if (unlikely((s64)ns < 0)) -+ ns = 0; -+ } -+ -+ return ns; -+} -+ -+unsigned long long task_delta_exec(struct task_struct *p) -+{ -+ unsigned long flags; -+ struct rq *rq; -+ u64 ns; -+ -+ rq = task_grq_lock(p, &flags); -+ ns = do_task_delta_exec(p, rq); -+ task_grq_unlock(&flags); -+ -+ return ns; -+} -+ -+/* -+ * Return accounted runtime for the task. -+ * In case the task is currently running, return the runtime plus current's -+ * pending runtime that have not been accounted yet. -+ */ -+unsigned long long task_sched_runtime(struct task_struct *p) -+{ -+ unsigned long flags; -+ struct rq *rq; -+ u64 ns; -+ -+ rq = task_grq_lock(p, &flags); -+ ns = p->sched_time + do_task_delta_exec(p, rq); -+ task_grq_unlock(&flags); -+ -+ return ns; -+} -+ -+/* -+ * Return sum_exec_runtime for the thread group. -+ * In case the task is currently running, return the sum plus current's -+ * pending runtime that have not been accounted yet. -+ * -+ * Note that the thread group might have other running tasks as well, -+ * so the return value not includes other pending runtime that other -+ * running tasks might have. -+ */ -+unsigned long long thread_group_sched_runtime(struct task_struct *p) -+{ -+ struct task_cputime totals; -+ unsigned long flags; -+ struct rq *rq; -+ u64 ns; -+ -+ rq = task_grq_lock(p, &flags); -+ thread_group_cputime(p, &totals); -+ ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); -+ task_grq_unlock(&flags); -+ -+ return ns; -+} -+ -+/* Compatibility crap for removal */ -+void account_user_time(struct task_struct *p, cputime_t cputime, -+ cputime_t cputime_scaled) -+{ -+} -+ -+void account_idle_time(cputime_t cputime) -+{ -+} -+ -+/* -+ * Account guest cpu time to a process. -+ * @p: the process that the cpu time gets accounted to -+ * @cputime: the cpu time spent in virtual machine since the last update -+ * @cputime_scaled: cputime scaled by cpu frequency -+ */ -+static void account_guest_time(struct task_struct *p, cputime_t cputime, -+ cputime_t cputime_scaled) -+{ -+ cputime64_t tmp; -+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; -+ -+ tmp = cputime_to_cputime64(cputime); -+ -+ /* Add guest time to process. */ -+ p->utime = cputime_add(p->utime, cputime); -+ p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); -+ account_group_user_time(p, cputime); -+ p->gtime = cputime_add(p->gtime, cputime); -+ -+ /* Add guest time to cpustat. */ -+ if (TASK_NICE(p) > 0) { -+ cpustat->nice = cputime64_add(cpustat->nice, tmp); -+ cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); -+ } else { -+ cpustat->user = cputime64_add(cpustat->user, tmp); -+ cpustat->guest = cputime64_add(cpustat->guest, tmp); -+ } -+} -+ -+/* -+ * Account system cpu time to a process. -+ * @p: the process that the cpu time gets accounted to -+ * @hardirq_offset: the offset to subtract from hardirq_count() -+ * @cputime: the cpu time spent in kernel space since the last update -+ * @cputime_scaled: cputime scaled by cpu frequency -+ * This is for guest only now. -+ */ -+void account_system_time(struct task_struct *p, int hardirq_offset, -+ cputime_t cputime, cputime_t cputime_scaled) -+{ -+ -+ if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) -+ account_guest_time(p, cputime, cputime_scaled); -+} -+ -+/* -+ * Account for involuntary wait time. -+ * @steal: the cpu time spent in involuntary wait -+ */ -+void account_steal_time(cputime_t cputime) -+{ -+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; -+ cputime64_t cputime64 = cputime_to_cputime64(cputime); -+ -+ cpustat->steal = cputime64_add(cpustat->steal, cputime64); -+} -+ -+/* -+ * Account for idle time. -+ * @cputime: the cpu time spent in idle wait -+ */ -+static void account_idle_times(cputime_t cputime) -+{ -+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; -+ cputime64_t cputime64 = cputime_to_cputime64(cputime); -+ struct rq *rq = this_rq(); -+ -+ if (atomic_read(&rq->nr_iowait) > 0) -+ cpustat->iowait = cputime64_add(cpustat->iowait, cputime64); -+ else -+ cpustat->idle = cputime64_add(cpustat->idle, cputime64); -+} -+ -+#ifndef CONFIG_VIRT_CPU_ACCOUNTING -+ -+void account_process_tick(struct task_struct *p, int user_tick) -+{ -+} -+ -+/* -+ * Account multiple ticks of steal time. -+ * @p: the process from which the cpu time has been stolen -+ * @ticks: number of stolen ticks -+ */ -+void account_steal_ticks(unsigned long ticks) -+{ -+ account_steal_time(jiffies_to_cputime(ticks)); -+} -+ -+/* -+ * Account multiple ticks of idle time. -+ * @ticks: number of stolen ticks -+ */ -+void account_idle_ticks(unsigned long ticks) -+{ -+ account_idle_times(jiffies_to_cputime(ticks)); -+} -+#endif -+ -+static inline void grq_iso_lock(void) -+ __acquires(grq.iso_lock) -+{ -+ raw_spin_lock(&grq.iso_lock); -+} -+ -+static inline void grq_iso_unlock(void) -+ __releases(grq.iso_lock) -+{ -+ raw_spin_unlock(&grq.iso_lock); -+} -+ -+/* -+ * Functions to test for when SCHED_ISO tasks have used their allocated -+ * quota as real time scheduling and convert them back to SCHED_NORMAL. -+ * Where possible, the data is tested lockless, to avoid grabbing iso_lock -+ * because the occasional inaccurate result won't matter. However the -+ * tick data is only ever modified under lock. iso_refractory is only simply -+ * set to 0 or 1 so it's not worth grabbing the lock yet again for that. -+ */ -+static void set_iso_refractory(void) -+{ -+ grq.iso_refractory = 1; -+} -+ -+static void clear_iso_refractory(void) -+{ -+ grq.iso_refractory = 0; -+} -+ -+/* -+ * Test if SCHED_ISO tasks have run longer than their alloted period as RT -+ * tasks and set the refractory flag if necessary. There is 10% hysteresis -+ * for unsetting the flag. 115/128 is ~90/100 as a fast shift instead of a -+ * slow division. -+ */ -+static unsigned int test_ret_isorefractory(struct rq *rq) -+{ -+ if (likely(!grq.iso_refractory)) { -+ if (grq.iso_ticks > ISO_PERIOD * sched_iso_cpu) -+ set_iso_refractory(); -+ } else { -+ if (grq.iso_ticks < ISO_PERIOD * (sched_iso_cpu * 115 / 128)) -+ clear_iso_refractory(); -+ } -+ return grq.iso_refractory; -+} -+ -+static void iso_tick(void) -+{ -+ grq_iso_lock(); -+ grq.iso_ticks += 100; -+ grq_iso_unlock(); -+} -+ -+/* No SCHED_ISO task was running so decrease rq->iso_ticks */ -+static inline void no_iso_tick(void) -+{ -+ if (grq.iso_ticks) { -+ grq_iso_lock(); -+ grq.iso_ticks -= grq.iso_ticks / ISO_PERIOD + 1; -+ if (unlikely(grq.iso_refractory && grq.iso_ticks < -+ ISO_PERIOD * (sched_iso_cpu * 115 / 128))) -+ clear_iso_refractory(); -+ grq_iso_unlock(); -+ } -+} -+ -+static int rq_running_iso(struct rq *rq) -+{ -+ return rq->rq_prio == ISO_PRIO; -+} -+ -+/* This manages tasks that have run out of timeslice during a scheduler_tick */ -+static void task_running_tick(struct rq *rq) -+{ -+ struct task_struct *p; -+ -+ /* -+ * If a SCHED_ISO task is running we increment the iso_ticks. In -+ * order to prevent SCHED_ISO tasks from causing starvation in the -+ * presence of true RT tasks we account those as iso_ticks as well. -+ */ -+ if ((rt_queue(rq) || (iso_queue(rq) && !grq.iso_refractory))) { -+ if (grq.iso_ticks <= (ISO_PERIOD * 100) - 100) -+ iso_tick(); -+ } else -+ no_iso_tick(); -+ -+ if (iso_queue(rq)) { -+ if (unlikely(test_ret_isorefractory(rq))) { -+ if (rq_running_iso(rq)) { -+ /* -+ * SCHED_ISO task is running as RT and limit -+ * has been hit. Force it to reschedule as -+ * SCHED_NORMAL by zeroing its time_slice -+ */ -+ rq->rq_time_slice = 0; -+ } -+ } -+ } -+ -+ /* SCHED_FIFO tasks never run out of timeslice. */ -+ if (rq->rq_policy == SCHED_FIFO) -+ return; -+ /* -+ * Tasks that were scheduled in the first half of a tick are not -+ * allowed to run into the 2nd half of the next tick if they will -+ * run out of time slice in the interim. Otherwise, if they have -+ * less than RESCHED_US μs of time slice left they will be rescheduled. -+ */ -+ if (rq->dither) { -+ if (rq->rq_time_slice > HALF_JIFFY_US) -+ return; -+ else -+ rq->rq_time_slice = 0; -+ } else if (rq->rq_time_slice >= RESCHED_US) -+ return; -+ -+ /* p->time_slice < RESCHED_US. We only modify task_struct under grq lock */ -+ p = rq->curr; -+ requeue_task(p); -+ grq_lock(); -+ set_tsk_need_resched(p); -+ grq_unlock(); -+} -+ -+void wake_up_idle_cpu(int cpu); -+ -+/* -+ * This function gets called by the timer code, with HZ frequency. -+ * We call it with interrupts disabled. The data modified is all -+ * local to struct rq so we don't need to grab grq lock. -+ */ -+void scheduler_tick(void) -+{ -+ int cpu __maybe_unused = smp_processor_id(); -+ struct rq *rq = cpu_rq(cpu); -+ -+ sched_clock_tick(); -+ /* grq lock not grabbed, so only update rq clock */ -+ update_rq_clock(rq); -+ update_cpu_clock(rq, rq->curr, 1); -+ if (!rq_idle(rq)) -+ task_running_tick(rq); -+ else -+ no_iso_tick(); -+ rq->last_tick = rq->clock; -+ perf_event_task_tick(); -+} -+ -+notrace unsigned long get_parent_ip(unsigned long addr) -+{ -+ if (in_lock_functions(addr)) { -+ addr = CALLER_ADDR2; -+ if (in_lock_functions(addr)) -+ addr = CALLER_ADDR3; -+ } -+ return addr; -+} -+ -+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ -+ defined(CONFIG_PREEMPT_TRACER)) -+void __kprobes add_preempt_count(int val) -+{ -+#ifdef CONFIG_DEBUG_PREEMPT -+ /* -+ * Underflow? -+ */ -+ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) -+ return; -+#endif -+ preempt_count() += val; -+#ifdef CONFIG_DEBUG_PREEMPT -+ /* -+ * Spinlock count overflowing soon? -+ */ -+ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= -+ PREEMPT_MASK - 10); -+#endif -+ if (preempt_count() == val) -+ trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); -+} -+EXPORT_SYMBOL(add_preempt_count); -+ -+void __kprobes sub_preempt_count(int val) -+{ -+#ifdef CONFIG_DEBUG_PREEMPT -+ /* -+ * Underflow? -+ */ -+ if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) -+ return; -+ /* -+ * Is the spinlock portion underflowing? -+ */ -+ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && -+ !(preempt_count() & PREEMPT_MASK))) -+ return; -+#endif -+ -+ if (preempt_count() == val) -+ trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); -+ preempt_count() -= val; -+} -+EXPORT_SYMBOL(sub_preempt_count); -+#endif -+ -+/* -+ * Deadline is "now" in niffies + (offset by priority). Setting the deadline -+ * is the key to everything. It distributes cpu fairly amongst tasks of the -+ * same nice value, it proportions cpu according to nice level, it means the -+ * task that last woke up the longest ago has the earliest deadline, thus -+ * ensuring that interactive tasks get low latency on wake up. The CPU -+ * proportion works out to the square of the virtual deadline difference, so -+ * this equation will give nice 19 3% CPU compared to nice 0. -+ */ -+static inline u64 prio_deadline_diff(int user_prio) -+{ -+ return (prio_ratios[user_prio] * rr_interval * (MS_TO_NS(1) / 128)); -+} -+ -+static inline u64 task_deadline_diff(struct task_struct *p) -+{ -+ return prio_deadline_diff(TASK_USER_PRIO(p)); -+} -+ -+static inline u64 static_deadline_diff(int static_prio) -+{ -+ return prio_deadline_diff(USER_PRIO(static_prio)); -+} -+ -+static inline int ms_longest_deadline_diff(void) -+{ -+ return NS_TO_MS(prio_deadline_diff(39)); -+} -+ -+/* -+ * The time_slice is only refilled when it is empty and that is when we set a -+ * new deadline. -+ */ -+static void time_slice_expired(struct task_struct *p) -+{ -+ p->time_slice = timeslice(); -+ p->deadline = grq.niffies + task_deadline_diff(p); -+} -+ -+/* -+ * Timeslices below RESCHED_US are considered as good as expired as there's no -+ * point rescheduling when there's so little time left. SCHED_BATCH tasks -+ * have been flagged be not latency sensitive and likely to be fully CPU -+ * bound so every time they're rescheduled they have their time_slice -+ * refilled, but get a new later deadline to have little effect on -+ * SCHED_NORMAL tasks. -+ -+ */ -+static inline void check_deadline(struct task_struct *p) -+{ -+ if (p->time_slice < RESCHED_US || batch_task(p)) -+ time_slice_expired(p); -+} -+ -+/* -+ * O(n) lookup of all tasks in the global runqueue. The real brainfuck -+ * of lock contention and O(n). It's not really O(n) as only the queued, -+ * but not running tasks are scanned, and is O(n) queued in the worst case -+ * scenario only because the right task can be found before scanning all of -+ * them. -+ * Tasks are selected in this order: -+ * Real time tasks are selected purely by their static priority and in the -+ * order they were queued, so the lowest value idx, and the first queued task -+ * of that priority value is chosen. -+ * If no real time tasks are found, the SCHED_ISO priority is checked, and -+ * all SCHED_ISO tasks have the same priority value, so they're selected by -+ * the earliest deadline value. -+ * If no SCHED_ISO tasks are found, SCHED_NORMAL tasks are selected by the -+ * earliest deadline. -+ * Finally if no SCHED_NORMAL tasks are found, SCHED_IDLEPRIO tasks are -+ * selected by the earliest deadline. -+ */ -+static inline struct -+task_struct *earliest_deadline_task(struct rq *rq, struct task_struct *idle) -+{ -+ u64 dl, earliest_deadline = 0; /* Initialise to silence compiler */ -+ struct task_struct *p, *edt = idle; -+ unsigned int cpu = cpu_of(rq); -+ struct list_head *queue; -+ int idx = 0; -+ -+retry: -+ idx = find_next_bit(grq.prio_bitmap, PRIO_LIMIT, idx); -+ if (idx >= PRIO_LIMIT) -+ goto out; -+ queue = grq.queue + idx; -+ list_for_each_entry(p, queue, run_list) { -+ /* Make sure cpu affinity is ok */ -+ if (needs_other_cpu(p, cpu)) -+ continue; -+ if (idx < MAX_RT_PRIO) { -+ /* We found an rt task */ -+ edt = p; -+ goto out_take; -+ } -+ -+ dl = p->deadline + cache_distance(task_rq(p), rq, p); -+ -+ /* -+ * No rt tasks. Find the earliest deadline task. Now we're in -+ * O(n) territory. This is what we silenced the compiler for: -+ * edt will always start as idle. -+ */ -+ if (edt == idle || -+ deadline_before(dl, earliest_deadline)) { -+ earliest_deadline = dl; -+ edt = p; -+ } -+ } -+ if (edt == idle) { -+ if (++idx < PRIO_LIMIT) -+ goto retry; -+ goto out; -+ } -+out_take: -+ take_task(rq, edt); -+out: -+ return edt; -+} -+ -+/* -+ * Print scheduling while atomic bug: -+ */ -+static noinline void __schedule_bug(struct task_struct *prev) -+{ -+ struct pt_regs *regs = get_irq_regs(); -+ -+ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", -+ prev->comm, prev->pid, preempt_count()); -+ -+ debug_show_held_locks(prev); -+ print_modules(); -+ if (irqs_disabled()) -+ print_irqtrace_events(prev); -+ -+ if (regs) -+ show_regs(regs); -+ else -+ dump_stack(); -+} -+ -+/* -+ * Various schedule()-time debugging checks and statistics: -+ */ -+static inline void schedule_debug(struct task_struct *prev) -+{ -+ /* -+ * Test if we are atomic. Since do_exit() needs to call into -+ * schedule() atomically, we ignore that path for now. -+ * Otherwise, whine if we are scheduling when we should not be. -+ */ -+ if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) -+ __schedule_bug(prev); -+ -+ profile_hit(SCHED_PROFILING, __builtin_return_address(0)); -+ -+ schedstat_inc(this_rq(), sched_count); -+#ifdef CONFIG_SCHEDSTATS -+ if (unlikely(prev->lock_depth >= 0)) { -+ schedstat_inc(this_rq(), bkl_count); -+ schedstat_inc(prev, sched_info.bkl_count); -+ } -+#endif -+} -+ -+/* -+ * The currently running task's information is all stored in rq local data -+ * which is only modified by the local CPU, thereby allowing the data to be -+ * changed without grabbing the grq lock. -+ */ -+static inline void set_rq_task(struct rq *rq, struct task_struct *p) -+{ -+ rq->rq_time_slice = p->time_slice; -+ rq->rq_deadline = p->deadline; -+ rq->rq_last_ran = p->last_ran; -+ rq->rq_policy = p->policy; -+ rq->rq_prio = p->prio; -+ if (p != rq->idle) -+ rq->rq_running = 1; -+ else -+ rq->rq_running = 0; -+} -+ -+static void reset_rq_task(struct rq *rq, struct task_struct *p) -+{ -+ rq->rq_policy = p->policy; -+ rq->rq_prio = p->prio; -+} -+ -+/* -+ * schedule() is the main scheduler function. -+ */ -+asmlinkage void __sched schedule(void) -+{ -+ struct task_struct *prev, *next, *idle; -+ unsigned long *switch_count; -+ int deactivate, cpu; -+ struct rq *rq; -+ -+need_resched: -+ preempt_disable(); -+ -+ cpu = smp_processor_id(); -+ rq = cpu_rq(cpu); -+ idle = rq->idle; -+ rcu_note_context_switch(cpu); -+ prev = rq->curr; -+ -+ release_kernel_lock(prev); -+need_resched_nonpreemptible: -+ -+ deactivate = 0; -+ schedule_debug(prev); -+ -+ grq_lock_irq(); -+ update_clocks(rq); -+ update_cpu_clock(rq, prev, 0); -+ if (rq->clock - rq->last_tick > HALF_JIFFY_NS) -+ rq->dither = 0; -+ else -+ rq->dither = 1; -+ -+ clear_tsk_need_resched(prev); -+ -+ switch_count = &prev->nivcsw; -+ if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { -+ if (unlikely(signal_pending_state(prev->state, prev))) { -+ prev->state = TASK_RUNNING; -+ } else { -+ deactivate = 1; -+ /* -+ * If a worker is going to sleep, notify and -+ * ask workqueue whether it wants to wake up a -+ * task to maintain concurrency. If so, wake -+ * up the task. -+ */ -+ if (prev->flags & PF_WQ_WORKER) { -+ struct task_struct *to_wakeup; -+ -+ to_wakeup = wq_worker_sleeping(prev, cpu); -+ if (to_wakeup) { -+ /* This shouldn't happen, but does */ -+ if (unlikely(to_wakeup == prev)) -+ deactivate = 0; -+ else -+ try_to_wake_up_local(to_wakeup); -+ } -+ } -+ } -+ switch_count = &prev->nvcsw; -+ } -+ -+ if (prev != idle) { -+ /* Update all the information stored on struct rq */ -+ prev->time_slice = rq->rq_time_slice; -+ prev->deadline = rq->rq_deadline; -+ check_deadline(prev); -+ prev->last_ran = rq->clock; -+ -+ /* Task changed affinity off this CPU */ -+ if (needs_other_cpu(prev, cpu)) -+ resched_suitable_idle(prev); -+ else if (!deactivate) { -+ if (!queued_notrunning()) { -+ /* -+ * We now know prev is the only thing that is -+ * awaiting CPU so we can bypass rechecking for -+ * the earliest deadline task and just run it -+ * again. -+ */ -+ grq_unlock_irq(); -+ goto rerun_prev_unlocked; -+ } else { -+ /* -+ * If prev got kicked off by a task that has to -+ * run on this CPU for affinity reasons then -+ * there may be an idle CPU it can go to. -+ */ -+ resched_suitable_idle(prev); -+ } -+ } -+ return_task(prev, deactivate); -+ } -+ -+ if (unlikely(!queued_notrunning())) { -+ /* -+ * This CPU is now truly idle as opposed to when idle is -+ * scheduled as a high priority task in its own right. -+ */ -+ next = idle; -+ schedstat_inc(rq, sched_goidle); -+ set_cpuidle_map(cpu); -+ } else { -+ next = earliest_deadline_task(rq, idle); -+ prefetch(next); -+ prefetch_stack(next); -+ clear_cpuidle_map(cpu); -+ } -+ -+ if (likely(prev != next)) { -+ sched_info_switch(prev, next); -+ perf_event_task_sched_out(prev, next); -+ -+ set_rq_task(rq, next); -+ grq.nr_switches++; -+ prev->oncpu = 0; -+ next->oncpu = 1; -+ rq->curr = next; -+ ++*switch_count; -+ -+ context_switch(rq, prev, next); /* unlocks the grq */ -+ /* -+ * The context switch have flipped the stack from under us -+ * and restored the local variables which were saved when -+ * this task called schedule() in the past. prev == current -+ * is still correct, but it can be moved to another cpu/rq. -+ */ -+ cpu = smp_processor_id(); -+ rq = cpu_rq(cpu); -+ idle = rq->idle; -+ } else -+ grq_unlock_irq(); -+ -+rerun_prev_unlocked: -+ if (unlikely(reacquire_kernel_lock(prev))) -+ goto need_resched_nonpreemptible; -+ -+ preempt_enable_no_resched(); -+ if (need_resched()) -+ goto need_resched; -+} -+EXPORT_SYMBOL(schedule); -+ -+#ifdef CONFIG_SMP -+int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) -+{ -+ unsigned int cpu; -+ struct rq *rq; -+ -+#ifdef CONFIG_DEBUG_PAGEALLOC -+ /* -+ * Need to access the cpu field knowing that -+ * DEBUG_PAGEALLOC could have unmapped it if -+ * the mutex owner just released it and exited. -+ */ -+ if (probe_kernel_address(&owner->cpu, cpu)) -+ return 0; -+#else -+ cpu = owner->cpu; -+#endif -+ -+ /* -+ * Even if the access succeeded (likely case), -+ * the cpu field may no longer be valid. -+ */ -+ if (cpu >= nr_cpumask_bits) -+ return 0; -+ -+ /* -+ * We need to validate that we can do a -+ * get_cpu() and that we have the percpu area. -+ */ -+ if (!cpu_online(cpu)) -+ return 0; -+ -+ rq = cpu_rq(cpu); -+ -+ for (;;) { -+ /* -+ * Owner changed, break to re-assess state. -+ */ -+ if (lock->owner != owner) -+ break; -+ -+ /* -+ * Is that owner really running on that cpu? -+ */ -+ if (task_thread_info(rq->curr) != owner || need_resched()) -+ return 0; -+ -+ cpu_relax(); -+ } -+ -+ return 1; -+} -+#endif -+ -+#ifdef CONFIG_PREEMPT -+/* -+ * this is the entry point to schedule() from in-kernel preemption -+ * off of preempt_enable. Kernel preemptions off return from interrupt -+ * occur there and call schedule directly. -+ */ -+asmlinkage void __sched notrace preempt_schedule(void) -+{ -+ struct thread_info *ti = current_thread_info(); -+ -+ /* -+ * If there is a non-zero preempt_count or interrupts are disabled, -+ * we do not want to preempt the current task. Just return.. -+ */ -+ if (likely(ti->preempt_count || irqs_disabled())) -+ return; -+ -+ do { -+ add_preempt_count_notrace(PREEMPT_ACTIVE); -+ schedule(); -+ sub_preempt_count_notrace(PREEMPT_ACTIVE); -+ -+ /* -+ * Check again in case we missed a preemption opportunity -+ * between schedule and now. -+ */ -+ barrier(); -+ } while (need_resched()); -+} -+EXPORT_SYMBOL(preempt_schedule); -+ -+/* -+ * this is the entry point to schedule() from kernel preemption -+ * off of irq context. -+ * Note, that this is called and return with irqs disabled. This will -+ * protect us against recursive calling from irq. -+ */ -+asmlinkage void __sched preempt_schedule_irq(void) -+{ -+ struct thread_info *ti = current_thread_info(); -+ -+ /* Catch callers which need to be fixed */ -+ BUG_ON(ti->preempt_count || !irqs_disabled()); -+ -+ do { -+ add_preempt_count(PREEMPT_ACTIVE); -+ local_irq_enable(); -+ schedule(); -+ local_irq_disable(); -+ sub_preempt_count(PREEMPT_ACTIVE); -+ -+ /* -+ * Check again in case we missed a preemption opportunity -+ * between schedule and now. -+ */ -+ barrier(); -+ } while (need_resched()); -+} -+ -+#endif /* CONFIG_PREEMPT */ -+ -+int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, -+ void *key) -+{ -+ return try_to_wake_up(curr->private, mode, wake_flags); -+} -+EXPORT_SYMBOL(default_wake_function); -+ -+/* -+ * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just -+ * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve -+ * number) then we wake all the non-exclusive tasks and one exclusive task. -+ * -+ * There are circumstances in which we can try to wake a task which has already -+ * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns -+ * zero in this (rare) case, and we handle it by continuing to scan the queue. -+ */ -+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, -+ int nr_exclusive, int wake_flags, void *key) -+{ -+ struct list_head *tmp, *next; -+ -+ list_for_each_safe(tmp, next, &q->task_list) { -+ wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list); -+ unsigned int flags = curr->flags; -+ -+ if (curr->func(curr, mode, wake_flags, key) && -+ (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) -+ break; -+ } -+} -+ -+/** -+ * __wake_up - wake up threads blocked on a waitqueue. -+ * @q: the waitqueue -+ * @mode: which threads -+ * @nr_exclusive: how many wake-one or wake-many threads to wake up -+ * @key: is directly passed to the wakeup function -+ * -+ * It may be assumed that this function implies a write memory barrier before -+ * changing the task state if and only if any tasks are woken up. -+ */ -+void __wake_up(wait_queue_head_t *q, unsigned int mode, -+ int nr_exclusive, void *key) -+{ -+ unsigned long flags; -+ -+ spin_lock_irqsave(&q->lock, flags); -+ __wake_up_common(q, mode, nr_exclusive, 0, key); -+ spin_unlock_irqrestore(&q->lock, flags); -+} -+EXPORT_SYMBOL(__wake_up); -+ -+/* -+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held. -+ */ -+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) -+{ -+ __wake_up_common(q, mode, 1, 0, NULL); -+} -+EXPORT_SYMBOL_GPL(__wake_up_locked); -+ -+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) -+{ -+ __wake_up_common(q, mode, 1, 0, key); -+} -+ -+/** -+ * __wake_up_sync_key - wake up threads blocked on a waitqueue. -+ * @q: the waitqueue -+ * @mode: which threads -+ * @nr_exclusive: how many wake-one or wake-many threads to wake up -+ * @key: opaque value to be passed to wakeup targets -+ * -+ * The sync wakeup differs that the waker knows that it will schedule -+ * away soon, so while the target thread will be woken up, it will not -+ * be migrated to another CPU - ie. the two threads are 'synchronised' -+ * with each other. This can prevent needless bouncing between CPUs. -+ * -+ * On UP it can prevent extra preemption. -+ * -+ * It may be assumed that this function implies a write memory barrier before -+ * changing the task state if and only if any tasks are woken up. -+ */ -+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, -+ int nr_exclusive, void *key) -+{ -+ unsigned long flags; -+ int wake_flags = WF_SYNC; -+ -+ if (unlikely(!q)) -+ return; -+ -+ if (unlikely(!nr_exclusive)) -+ wake_flags = 0; -+ -+ spin_lock_irqsave(&q->lock, flags); -+ __wake_up_common(q, mode, nr_exclusive, wake_flags, key); -+ spin_unlock_irqrestore(&q->lock, flags); -+} -+EXPORT_SYMBOL_GPL(__wake_up_sync_key); -+ -+/** -+ * __wake_up_sync - wake up threads blocked on a waitqueue. -+ * @q: the waitqueue -+ * @mode: which threads -+ * @nr_exclusive: how many wake-one or wake-many threads to wake up -+ * -+ * The sync wakeup differs that the waker knows that it will schedule -+ * away soon, so while the target thread will be woken up, it will not -+ * be migrated to another CPU - ie. the two threads are 'synchronised' -+ * with each other. This can prevent needless bouncing between CPUs. -+ * -+ * On UP it can prevent extra preemption. -+ */ -+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) -+{ -+ unsigned long flags; -+ int sync = 1; -+ -+ if (unlikely(!q)) -+ return; -+ -+ if (unlikely(!nr_exclusive)) -+ sync = 0; -+ -+ spin_lock_irqsave(&q->lock, flags); -+ __wake_up_common(q, mode, nr_exclusive, sync, NULL); -+ spin_unlock_irqrestore(&q->lock, flags); -+} -+EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ -+ -+/** -+ * complete: - signals a single thread waiting on this completion -+ * @x: holds the state of this particular completion -+ * -+ * This will wake up a single thread waiting on this completion. Threads will be -+ * awakened in the same order in which they were queued. -+ * -+ * See also complete_all(), wait_for_completion() and related routines. -+ * -+ * It may be assumed that this function implies a write memory barrier before -+ * changing the task state if and only if any tasks are woken up. -+ */ -+void complete(struct completion *x) -+{ -+ unsigned long flags; -+ -+ spin_lock_irqsave(&x->wait.lock, flags); -+ x->done++; -+ __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); -+ spin_unlock_irqrestore(&x->wait.lock, flags); -+} -+EXPORT_SYMBOL(complete); -+ -+/** -+ * complete_all: - signals all threads waiting on this completion -+ * @x: holds the state of this particular completion -+ * -+ * This will wake up all threads waiting on this particular completion event. -+ * -+ * It may be assumed that this function implies a write memory barrier before -+ * changing the task state if and only if any tasks are woken up. -+ */ -+void complete_all(struct completion *x) -+{ -+ unsigned long flags; -+ -+ spin_lock_irqsave(&x->wait.lock, flags); -+ x->done += UINT_MAX/2; -+ __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); -+ spin_unlock_irqrestore(&x->wait.lock, flags); -+} -+EXPORT_SYMBOL(complete_all); -+ -+static inline long __sched -+do_wait_for_common(struct completion *x, long timeout, int state) -+{ -+ if (!x->done) { -+ DECLARE_WAITQUEUE(wait, current); -+ -+ __add_wait_queue_tail_exclusive(&x->wait, &wait); -+ do { -+ if (signal_pending_state(state, current)) { -+ timeout = -ERESTARTSYS; -+ break; -+ } -+ __set_current_state(state); -+ spin_unlock_irq(&x->wait.lock); -+ timeout = schedule_timeout(timeout); -+ spin_lock_irq(&x->wait.lock); -+ } while (!x->done && timeout); -+ __remove_wait_queue(&x->wait, &wait); -+ if (!x->done) -+ return timeout; -+ } -+ x->done--; -+ return timeout ?: 1; -+} -+ -+static long __sched -+wait_for_common(struct completion *x, long timeout, int state) -+{ -+ might_sleep(); -+ -+ spin_lock_irq(&x->wait.lock); -+ timeout = do_wait_for_common(x, timeout, state); -+ spin_unlock_irq(&x->wait.lock); -+ return timeout; -+} -+ -+/** -+ * wait_for_completion: - waits for completion of a task -+ * @x: holds the state of this particular completion -+ * -+ * This waits to be signaled for completion of a specific task. It is NOT -+ * interruptible and there is no timeout. -+ * -+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout -+ * and interrupt capability. Also see complete(). -+ */ -+void __sched wait_for_completion(struct completion *x) -+{ -+ wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); -+} -+EXPORT_SYMBOL(wait_for_completion); -+ -+/** -+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout) -+ * @x: holds the state of this particular completion -+ * @timeout: timeout value in jiffies -+ * -+ * This waits for either a completion of a specific task to be signaled or for a -+ * specified timeout to expire. The timeout is in jiffies. It is not -+ * interruptible. -+ */ -+unsigned long __sched -+wait_for_completion_timeout(struct completion *x, unsigned long timeout) -+{ -+ return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); -+} -+EXPORT_SYMBOL(wait_for_completion_timeout); -+ -+/** -+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr) -+ * @x: holds the state of this particular completion -+ * -+ * This waits for completion of a specific task to be signaled. It is -+ * interruptible. -+ */ -+int __sched wait_for_completion_interruptible(struct completion *x) -+{ -+ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); -+ if (t == -ERESTARTSYS) -+ return t; -+ return 0; -+} -+EXPORT_SYMBOL(wait_for_completion_interruptible); -+ -+/** -+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) -+ * @x: holds the state of this particular completion -+ * @timeout: timeout value in jiffies -+ * -+ * This waits for either a completion of a specific task to be signaled or for a -+ * specified timeout to expire. It is interruptible. The timeout is in jiffies. -+ */ -+unsigned long __sched -+wait_for_completion_interruptible_timeout(struct completion *x, -+ unsigned long timeout) -+{ -+ return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); -+} -+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); -+ -+/** -+ * wait_for_completion_killable: - waits for completion of a task (killable) -+ * @x: holds the state of this particular completion -+ * -+ * This waits to be signaled for completion of a specific task. It can be -+ * interrupted by a kill signal. -+ */ -+int __sched wait_for_completion_killable(struct completion *x) -+{ -+ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); -+ if (t == -ERESTARTSYS) -+ return t; -+ return 0; -+} -+EXPORT_SYMBOL(wait_for_completion_killable); -+ -+/** -+ * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable)) -+ * @x: holds the state of this particular completion -+ * @timeout: timeout value in jiffies -+ * -+ * This waits for either a completion of a specific task to be -+ * signaled or for a specified timeout to expire. It can be -+ * interrupted by a kill signal. The timeout is in jiffies. -+ */ -+unsigned long __sched -+wait_for_completion_killable_timeout(struct completion *x, -+ unsigned long timeout) -+{ -+ return wait_for_common(x, timeout, TASK_KILLABLE); -+} -+EXPORT_SYMBOL(wait_for_completion_killable_timeout); -+ -+/** -+ * try_wait_for_completion - try to decrement a completion without blocking -+ * @x: completion structure -+ * -+ * Returns: 0 if a decrement cannot be done without blocking -+ * 1 if a decrement succeeded. -+ * -+ * If a completion is being used as a counting completion, -+ * attempt to decrement the counter without blocking. This -+ * enables us to avoid waiting if the resource the completion -+ * is protecting is not available. -+ */ -+bool try_wait_for_completion(struct completion *x) -+{ -+ unsigned long flags; -+ int ret = 1; -+ -+ spin_lock_irqsave(&x->wait.lock, flags); -+ if (!x->done) -+ ret = 0; -+ else -+ x->done--; -+ spin_unlock_irqrestore(&x->wait.lock, flags); -+ return ret; -+} -+EXPORT_SYMBOL(try_wait_for_completion); -+ -+/** -+ * completion_done - Test to see if a completion has any waiters -+ * @x: completion structure -+ * -+ * Returns: 0 if there are waiters (wait_for_completion() in progress) -+ * 1 if there are no waiters. -+ * -+ */ -+bool completion_done(struct completion *x) -+{ -+ unsigned long flags; -+ int ret = 1; -+ -+ spin_lock_irqsave(&x->wait.lock, flags); -+ if (!x->done) -+ ret = 0; -+ spin_unlock_irqrestore(&x->wait.lock, flags); -+ return ret; -+} -+EXPORT_SYMBOL(completion_done); -+ -+static long __sched -+sleep_on_common(wait_queue_head_t *q, int state, long timeout) -+{ -+ unsigned long flags; -+ wait_queue_t wait; -+ -+ init_waitqueue_entry(&wait, current); -+ -+ __set_current_state(state); -+ -+ spin_lock_irqsave(&q->lock, flags); -+ __add_wait_queue(q, &wait); -+ spin_unlock(&q->lock); -+ timeout = schedule_timeout(timeout); -+ spin_lock_irq(&q->lock); -+ __remove_wait_queue(q, &wait); -+ spin_unlock_irqrestore(&q->lock, flags); -+ -+ return timeout; -+} -+ -+void __sched interruptible_sleep_on(wait_queue_head_t *q) -+{ -+ sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -+} -+EXPORT_SYMBOL(interruptible_sleep_on); -+ -+long __sched -+interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) -+{ -+ return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); -+} -+EXPORT_SYMBOL(interruptible_sleep_on_timeout); -+ -+void __sched sleep_on(wait_queue_head_t *q) -+{ -+ sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -+} -+EXPORT_SYMBOL(sleep_on); -+ -+long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) -+{ -+ return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); -+} -+EXPORT_SYMBOL(sleep_on_timeout); -+ -+#ifdef CONFIG_RT_MUTEXES -+ -+/* -+ * rt_mutex_setprio - set the current priority of a task -+ * @p: task -+ * @prio: prio value (kernel-internal form) -+ * -+ * This function changes the 'effective' priority of a task. It does -+ * not touch ->normal_prio like __setscheduler(). -+ * -+ * Used by the rt_mutex code to implement priority inheritance logic. -+ */ -+void rt_mutex_setprio(struct task_struct *p, int prio) -+{ -+ unsigned long flags; -+ int queued, oldprio; -+ struct rq *rq; -+ -+ BUG_ON(prio < 0 || prio > MAX_PRIO); -+ -+ rq = task_grq_lock(p, &flags); -+ -+ trace_sched_pi_setprio(p, prio); -+ oldprio = p->prio; -+ queued = task_queued(p); -+ if (queued) -+ dequeue_task(p); -+ p->prio = prio; -+ if (task_running(p) && prio > oldprio) -+ resched_task(p); -+ if (queued) { -+ enqueue_task(p); -+ try_preempt(p, rq); -+ } -+ -+ task_grq_unlock(&flags); -+} -+ -+#endif -+ -+/* -+ * Adjust the deadline for when the priority is to change, before it's -+ * changed. -+ */ -+static inline void adjust_deadline(struct task_struct *p, int new_prio) -+{ -+ p->deadline += static_deadline_diff(new_prio) - task_deadline_diff(p); -+} -+ -+void set_user_nice(struct task_struct *p, long nice) -+{ -+ int queued, new_static, old_static; -+ unsigned long flags; -+ struct rq *rq; -+ -+ if (TASK_NICE(p) == nice || nice < -20 || nice > 19) -+ return; -+ new_static = NICE_TO_PRIO(nice); -+ /* -+ * We have to be careful, if called from sys_setpriority(), -+ * the task might be in the middle of scheduling on another CPU. -+ */ -+ rq = time_task_grq_lock(p, &flags); -+ /* -+ * The RT priorities are set via sched_setscheduler(), but we still -+ * allow the 'normal' nice value to be set - but as expected -+ * it wont have any effect on scheduling until the task is -+ * not SCHED_NORMAL/SCHED_BATCH: -+ */ -+ if (has_rt_policy(p)) { -+ p->static_prio = new_static; -+ goto out_unlock; -+ } -+ queued = task_queued(p); -+ if (queued) -+ dequeue_task(p); -+ -+ adjust_deadline(p, new_static); -+ old_static = p->static_prio; -+ p->static_prio = new_static; -+ p->prio = effective_prio(p); -+ -+ if (queued) { -+ enqueue_task(p); -+ if (new_static < old_static) -+ try_preempt(p, rq); -+ } else if (task_running(p)) { -+ reset_rq_task(rq, p); -+ if (old_static < new_static) -+ resched_task(p); -+ } -+out_unlock: -+ task_grq_unlock(&flags); -+} -+EXPORT_SYMBOL(set_user_nice); -+ -+/* -+ * can_nice - check if a task can reduce its nice value -+ * @p: task -+ * @nice: nice value -+ */ -+int can_nice(const struct task_struct *p, const int nice) -+{ -+ /* convert nice value [19,-20] to rlimit style value [1,40] */ -+ int nice_rlim = 20 - nice; -+ -+ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || -+ capable(CAP_SYS_NICE)); -+} -+ -+#ifdef __ARCH_WANT_SYS_NICE -+ -+/* -+ * sys_nice - change the priority of the current process. -+ * @increment: priority increment -+ * -+ * sys_setpriority is a more generic, but much slower function that -+ * does similar things. -+ */ -+SYSCALL_DEFINE1(nice, int, increment) -+{ -+ long nice, retval; -+ -+ /* -+ * Setpriority might change our priority at the same moment. -+ * We don't have to worry. Conceptually one call occurs first -+ * and we have a single winner. -+ */ -+ if (increment < -40) -+ increment = -40; -+ if (increment > 40) -+ increment = 40; -+ -+ nice = TASK_NICE(current) + increment; -+ if (nice < -20) -+ nice = -20; -+ if (nice > 19) -+ nice = 19; -+ -+ if (increment < 0 && !can_nice(current, nice)) -+ return -EPERM; -+ -+ retval = security_task_setnice(current, nice); -+ if (retval) -+ return retval; -+ -+ set_user_nice(current, nice); -+ return 0; -+} -+ -+#endif -+ -+/** -+ * task_prio - return the priority value of a given task. -+ * @p: the task in question. -+ * -+ * This is the priority value as seen by users in /proc. -+ * RT tasks are offset by -100. Normal tasks are centered around 1, value goes -+ * from 0 (SCHED_ISO) up to 82 (nice +19 SCHED_IDLEPRIO). -+ */ -+int task_prio(const struct task_struct *p) -+{ -+ int delta, prio = p->prio - MAX_RT_PRIO; -+ -+ /* rt tasks and iso tasks */ -+ if (prio <= 0) -+ goto out; -+ -+ /* Convert to ms to avoid overflows */ -+ delta = NS_TO_MS(p->deadline - grq.niffies); -+ delta = delta * 40 / ms_longest_deadline_diff(); -+ if (delta > 0 && delta <= 80) -+ prio += delta; -+ if (idleprio_task(p)) -+ prio += 40; -+out: -+ return prio; -+} -+ -+/** -+ * task_nice - return the nice value of a given task. -+ * @p: the task in question. -+ */ -+int task_nice(const struct task_struct *p) -+{ -+ return TASK_NICE(p); -+} -+EXPORT_SYMBOL_GPL(task_nice); -+ -+/** -+ * idle_cpu - is a given cpu idle currently? -+ * @cpu: the processor in question. -+ */ -+int idle_cpu(int cpu) -+{ -+ return cpu_curr(cpu) == cpu_rq(cpu)->idle; -+} -+ -+/** -+ * idle_task - return the idle task for a given cpu. -+ * @cpu: the processor in question. -+ */ -+struct task_struct *idle_task(int cpu) -+{ -+ return cpu_rq(cpu)->idle; -+} -+ -+/** -+ * find_process_by_pid - find a process with a matching PID value. -+ * @pid: the pid in question. -+ */ -+static inline struct task_struct *find_process_by_pid(pid_t pid) -+{ -+ return pid ? find_task_by_vpid(pid) : current; -+} -+ -+/* Actually do priority change: must hold grq lock. */ -+static void -+__setscheduler(struct task_struct *p, struct rq *rq, int policy, int prio) -+{ -+ int oldrtprio, oldprio; -+ -+ BUG_ON(task_queued(p)); -+ -+ p->policy = policy; -+ oldrtprio = p->rt_priority; -+ p->rt_priority = prio; -+ p->normal_prio = normal_prio(p); -+ oldprio = p->prio; -+ /* we are holding p->pi_lock already */ -+ p->prio = rt_mutex_getprio(p); -+ if (task_running(p)) { -+ reset_rq_task(rq, p); -+ /* Resched only if we might now be preempted */ -+ if (p->prio > oldprio || p->rt_priority > oldrtprio) -+ resched_task(p); -+ } -+} -+ -+/* -+ * check the target process has a UID that matches the current process's -+ */ -+static bool check_same_owner(struct task_struct *p) -+{ -+ const struct cred *cred = current_cred(), *pcred; -+ bool match; -+ -+ rcu_read_lock(); -+ pcred = __task_cred(p); -+ match = (cred->euid == pcred->euid || -+ cred->euid == pcred->uid); -+ rcu_read_unlock(); -+ return match; -+} -+ -+static int __sched_setscheduler(struct task_struct *p, int policy, -+ struct sched_param *param, bool user) -+{ -+ struct sched_param zero_param = { .sched_priority = 0 }; -+ int queued, retval, oldpolicy = -1; -+ unsigned long flags, rlim_rtprio = 0; -+ int reset_on_fork; -+ struct rq *rq; -+ -+ /* may grab non-irq protected spin_locks */ -+ BUG_ON(in_interrupt()); -+ -+ if (is_rt_policy(policy) && !capable(CAP_SYS_NICE)) { -+ unsigned long lflags; -+ -+ if (!lock_task_sighand(p, &lflags)) -+ return -ESRCH; -+ rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); -+ unlock_task_sighand(p, &lflags); -+ if (rlim_rtprio) -+ goto recheck; -+ /* -+ * If the caller requested an RT policy without having the -+ * necessary rights, we downgrade the policy to SCHED_ISO. -+ * We also set the parameter to zero to pass the checks. -+ */ -+ policy = SCHED_ISO; -+ param = &zero_param; -+ } -+recheck: -+ /* double check policy once rq lock held */ -+ if (policy < 0) { -+ reset_on_fork = p->sched_reset_on_fork; -+ policy = oldpolicy = p->policy; -+ } else { -+ reset_on_fork = !!(policy & SCHED_RESET_ON_FORK); -+ policy &= ~SCHED_RESET_ON_FORK; -+ -+ if (!SCHED_RANGE(policy)) -+ return -EINVAL; -+ } -+ -+ /* -+ * Valid priorities for SCHED_FIFO and SCHED_RR are -+ * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and -+ * SCHED_BATCH is 0. -+ */ -+ if (param->sched_priority < 0 || -+ (p->mm && param->sched_priority > MAX_USER_RT_PRIO - 1) || -+ (!p->mm && param->sched_priority > MAX_RT_PRIO - 1)) -+ return -EINVAL; -+ if (is_rt_policy(policy) != (param->sched_priority != 0)) -+ return -EINVAL; -+ -+ /* -+ * Allow unprivileged RT tasks to decrease priority: -+ */ -+ if (user && !capable(CAP_SYS_NICE)) { -+ if (is_rt_policy(policy)) { -+ unsigned long rlim_rtprio = -+ task_rlimit(p, RLIMIT_RTPRIO); -+ -+ /* can't set/change the rt policy */ -+ if (policy != p->policy && !rlim_rtprio) -+ return -EPERM; -+ -+ /* can't increase priority */ -+ if (param->sched_priority > p->rt_priority && -+ param->sched_priority > rlim_rtprio) -+ return -EPERM; -+ } else { -+ switch (p->policy) { -+ /* -+ * Can only downgrade policies but not back to -+ * SCHED_NORMAL -+ */ -+ case SCHED_ISO: -+ if (policy == SCHED_ISO) -+ goto out; -+ if (policy == SCHED_NORMAL) -+ return -EPERM; -+ break; -+ case SCHED_BATCH: -+ if (policy == SCHED_BATCH) -+ goto out; -+ if (policy != SCHED_IDLEPRIO) -+ return -EPERM; -+ break; -+ case SCHED_IDLEPRIO: -+ if (policy == SCHED_IDLEPRIO) -+ goto out; -+ return -EPERM; -+ default: -+ break; -+ } -+ } -+ -+ /* can't change other user's priorities */ -+ if (!check_same_owner(p)) -+ return -EPERM; -+ -+ /* Normal users shall not reset the sched_reset_on_fork flag */ -+ if (p->sched_reset_on_fork && !reset_on_fork) -+ return -EPERM; -+ } -+ -+ if (user) { -+ retval = security_task_setscheduler(p); -+ if (retval) -+ return retval; -+ } -+ -+ /* -+ * make sure no PI-waiters arrive (or leave) while we are -+ * changing the priority of the task: -+ */ -+ raw_spin_lock_irqsave(&p->pi_lock, flags); -+ /* -+ * To be able to change p->policy safely, the apropriate -+ * runqueue lock must be held. -+ */ -+ rq = __task_grq_lock(p); -+ -+ /* -+ * Changing the policy of the stop threads its a very bad idea -+ */ -+ if (p == rq->stop) { -+ __task_grq_unlock(); -+ raw_spin_unlock_irqrestore(&p->pi_lock, flags); -+ return -EINVAL; -+ } -+ -+ /* recheck policy now with rq lock held */ -+ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { -+ policy = oldpolicy = -1; -+ __task_grq_unlock(); -+ raw_spin_unlock_irqrestore(&p->pi_lock, flags); -+ goto recheck; -+ } -+ update_clocks(rq); -+ p->sched_reset_on_fork = reset_on_fork; -+ -+ queued = task_queued(p); -+ if (queued) -+ dequeue_task(p); -+ __setscheduler(p, rq, policy, param->sched_priority); -+ if (queued) { -+ enqueue_task(p); -+ try_preempt(p, rq); -+ } -+ __task_grq_unlock(); -+ raw_spin_unlock_irqrestore(&p->pi_lock, flags); -+ -+ rt_mutex_adjust_pi(p); -+out: -+ return 0; -+} -+ -+/** -+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. -+ * @p: the task in question. -+ * @policy: new policy. -+ * @param: structure containing the new RT priority. -+ * -+ * NOTE that the task may be already dead. -+ */ -+int sched_setscheduler(struct task_struct *p, int policy, -+ struct sched_param *param) -+{ -+ return __sched_setscheduler(p, policy, param, true); -+} -+ -+EXPORT_SYMBOL_GPL(sched_setscheduler); -+ -+/** -+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. -+ * @p: the task in question. -+ * @policy: new policy. -+ * @param: structure containing the new RT priority. -+ * -+ * Just like sched_setscheduler, only don't bother checking if the -+ * current context has permission. For example, this is needed in -+ * stop_machine(): we create temporary high priority worker threads, -+ * but our caller might not have that capability. -+ */ -+int sched_setscheduler_nocheck(struct task_struct *p, int policy, -+ struct sched_param *param) -+{ -+ return __sched_setscheduler(p, policy, param, false); -+} -+ -+static int -+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) -+{ -+ struct sched_param lparam; -+ struct task_struct *p; -+ int retval; -+ -+ if (!param || pid < 0) -+ return -EINVAL; -+ if (copy_from_user(&lparam, param, sizeof(struct sched_param))) -+ return -EFAULT; -+ -+ rcu_read_lock(); -+ retval = -ESRCH; -+ p = find_process_by_pid(pid); -+ if (p != NULL) -+ retval = sched_setscheduler(p, policy, &lparam); -+ rcu_read_unlock(); -+ -+ return retval; -+} -+ -+/** -+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority -+ * @pid: the pid in question. -+ * @policy: new policy. -+ * @param: structure containing the new RT priority. -+ */ -+asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, -+ struct sched_param __user *param) -+{ -+ /* negative values for policy are not valid */ -+ if (policy < 0) -+ return -EINVAL; -+ -+ return do_sched_setscheduler(pid, policy, param); -+} -+ -+/** -+ * sys_sched_setparam - set/change the RT priority of a thread -+ * @pid: the pid in question. -+ * @param: structure containing the new RT priority. -+ */ -+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) -+{ -+ return do_sched_setscheduler(pid, -1, param); -+} -+ -+/** -+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread -+ * @pid: the pid in question. -+ */ -+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) -+{ -+ struct task_struct *p; -+ int retval = -EINVAL; -+ -+ if (pid < 0) -+ goto out_nounlock; -+ -+ retval = -ESRCH; -+ rcu_read_lock(); -+ p = find_process_by_pid(pid); -+ if (p) { -+ retval = security_task_getscheduler(p); -+ if (!retval) -+ retval = p->policy; -+ } -+ rcu_read_unlock(); -+ -+out_nounlock: -+ return retval; -+} -+ -+/** -+ * sys_sched_getscheduler - get the RT priority of a thread -+ * @pid: the pid in question. -+ * @param: structure containing the RT priority. -+ */ -+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) -+{ -+ struct sched_param lp; -+ struct task_struct *p; -+ int retval = -EINVAL; -+ -+ if (!param || pid < 0) -+ goto out_nounlock; -+ -+ rcu_read_lock(); -+ p = find_process_by_pid(pid); -+ retval = -ESRCH; -+ if (!p) -+ goto out_unlock; -+ -+ retval = security_task_getscheduler(p); -+ if (retval) -+ goto out_unlock; -+ -+ lp.sched_priority = p->rt_priority; -+ rcu_read_unlock(); -+ -+ /* -+ * This one might sleep, we cannot do it with a spinlock held ... -+ */ -+ retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; -+ -+out_nounlock: -+ return retval; -+ -+out_unlock: -+ rcu_read_unlock(); -+ return retval; -+} -+ -+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) -+{ -+ cpumask_var_t cpus_allowed, new_mask; -+ struct task_struct *p; -+ int retval; -+ -+ get_online_cpus(); -+ rcu_read_lock(); -+ -+ p = find_process_by_pid(pid); -+ if (!p) { -+ rcu_read_unlock(); -+ put_online_cpus(); -+ return -ESRCH; -+ } -+ -+ /* Prevent p going away */ -+ get_task_struct(p); -+ rcu_read_unlock(); -+ -+ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { -+ retval = -ENOMEM; -+ goto out_put_task; -+ } -+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { -+ retval = -ENOMEM; -+ goto out_free_cpus_allowed; -+ } -+ retval = -EPERM; -+ if (!check_same_owner(p) && !capable(CAP_SYS_NICE)) -+ goto out_unlock; -+ -+ retval = security_task_setscheduler(p); -+ if (retval) -+ goto out_unlock; -+ -+ cpuset_cpus_allowed(p, cpus_allowed); -+ cpumask_and(new_mask, in_mask, cpus_allowed); -+again: -+ retval = set_cpus_allowed_ptr(p, new_mask); -+ -+ if (!retval) { -+ cpuset_cpus_allowed(p, cpus_allowed); -+ if (!cpumask_subset(new_mask, cpus_allowed)) { -+ /* -+ * We must have raced with a concurrent cpuset -+ * update. Just reset the cpus_allowed to the -+ * cpuset's cpus_allowed -+ */ -+ cpumask_copy(new_mask, cpus_allowed); -+ goto again; -+ } -+ } -+out_unlock: -+ free_cpumask_var(new_mask); -+out_free_cpus_allowed: -+ free_cpumask_var(cpus_allowed); -+out_put_task: -+ put_task_struct(p); -+ put_online_cpus(); -+ return retval; -+} -+ -+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, -+ cpumask_t *new_mask) -+{ -+ if (len < sizeof(cpumask_t)) { -+ memset(new_mask, 0, sizeof(cpumask_t)); -+ } else if (len > sizeof(cpumask_t)) { -+ len = sizeof(cpumask_t); -+ } -+ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; -+} -+ -+ -+/** -+ * sys_sched_setaffinity - set the cpu affinity of a process -+ * @pid: pid of the process -+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr -+ * @user_mask_ptr: user-space pointer to the new cpu mask -+ */ -+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, -+ unsigned long __user *, user_mask_ptr) -+{ -+ cpumask_var_t new_mask; -+ int retval; -+ -+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) -+ return -ENOMEM; -+ -+ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); -+ if (retval == 0) -+ retval = sched_setaffinity(pid, new_mask); -+ free_cpumask_var(new_mask); -+ return retval; -+} -+ -+long sched_getaffinity(pid_t pid, cpumask_t *mask) -+{ -+ struct task_struct *p; -+ unsigned long flags; -+ struct rq *rq; -+ int retval; -+ -+ get_online_cpus(); -+ rcu_read_lock(); -+ -+ retval = -ESRCH; -+ p = find_process_by_pid(pid); -+ if (!p) -+ goto out_unlock; -+ -+ retval = security_task_getscheduler(p); -+ if (retval) -+ goto out_unlock; -+ -+ rq = task_grq_lock(p, &flags); -+ cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); -+ task_grq_unlock(&flags); -+ -+out_unlock: -+ rcu_read_unlock(); -+ put_online_cpus(); -+ -+ return retval; -+} -+ -+/** -+ * sys_sched_getaffinity - get the cpu affinity of a process -+ * @pid: pid of the process -+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr -+ * @user_mask_ptr: user-space pointer to hold the current cpu mask -+ */ -+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, -+ unsigned long __user *, user_mask_ptr) -+{ -+ int ret; -+ cpumask_var_t mask; -+ -+ if ((len * BITS_PER_BYTE) < nr_cpu_ids) -+ return -EINVAL; -+ if (len & (sizeof(unsigned long)-1)) -+ return -EINVAL; -+ -+ if (!alloc_cpumask_var(&mask, GFP_KERNEL)) -+ return -ENOMEM; -+ -+ ret = sched_getaffinity(pid, mask); -+ if (ret == 0) { -+ size_t retlen = min_t(size_t, len, cpumask_size()); -+ -+ if (copy_to_user(user_mask_ptr, mask, retlen)) -+ ret = -EFAULT; -+ else -+ ret = retlen; -+ } -+ free_cpumask_var(mask); -+ -+ return ret; -+} -+ -+/** -+ * sys_sched_yield - yield the current processor to other threads. -+ * -+ * This function yields the current CPU to other tasks. It does this by -+ * scheduling away the current task. If it still has the earliest deadline -+ * it will be scheduled again as the next task. -+ */ -+SYSCALL_DEFINE0(sched_yield) -+{ -+ struct task_struct *p; -+ struct rq *rq; -+ -+ p = current; -+ rq = task_grq_lock_irq(p); -+ schedstat_inc(rq, yld_count); -+ requeue_task(p); -+ -+ /* -+ * Since we are going to call schedule() anyway, there's -+ * no need to preempt or enable interrupts: -+ */ -+ __release(grq.lock); -+ spin_release(&grq.lock.dep_map, 1, _THIS_IP_); -+ do_raw_spin_unlock(&grq.lock); -+ preempt_enable_no_resched(); -+ -+ schedule(); -+ -+ return 0; -+} -+ -+static inline int should_resched(void) -+{ -+ return need_resched() && !(preempt_count() & PREEMPT_ACTIVE); -+} -+ -+static void __cond_resched(void) -+{ -+ /* NOT a real fix but will make voluntary preempt work. 馬鹿な事 */ -+ if (unlikely(system_state != SYSTEM_RUNNING)) -+ return; -+ -+ add_preempt_count(PREEMPT_ACTIVE); -+ schedule(); -+ sub_preempt_count(PREEMPT_ACTIVE); -+} -+ -+int __sched _cond_resched(void) -+{ -+ if (should_resched()) { -+ __cond_resched(); -+ return 1; -+ } -+ return 0; -+} -+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 -+ * operations here to prevent schedule() from being called twice (once via -+ * spin_unlock(), once by hand). -+ */ -+int __cond_resched_lock(spinlock_t *lock) -+{ -+ int resched = should_resched(); -+ int ret = 0; -+ -+ lockdep_assert_held(lock); -+ -+ if (spin_needbreak(lock) || resched) { -+ spin_unlock(lock); -+ if (resched) -+ __cond_resched(); -+ else -+ cpu_relax(); -+ ret = 1; -+ spin_lock(lock); -+ } -+ return ret; -+} -+EXPORT_SYMBOL(__cond_resched_lock); -+ -+int __sched __cond_resched_softirq(void) -+{ -+ BUG_ON(!in_softirq()); -+ -+ if (should_resched()) { -+ local_bh_enable(); -+ __cond_resched(); -+ local_bh_disable(); -+ return 1; -+ } -+ return 0; -+} -+EXPORT_SYMBOL(__cond_resched_softirq); -+ -+/** -+ * yield - yield the current processor to other threads. -+ * -+ * This is a shortcut for kernel-space yielding - it marks the -+ * thread runnable and calls sys_sched_yield(). -+ */ -+void __sched yield(void) -+{ -+ set_current_state(TASK_RUNNING); -+ sys_sched_yield(); -+} -+EXPORT_SYMBOL(yield); -+ -+/* -+ * This task is about to go to sleep on IO. Increment rq->nr_iowait so -+ * that process accounting knows that this is a task in IO wait state. -+ * -+ * But don't do that if it is a deliberate, throttling IO wait (this task -+ * has set its backing_dev_info: the queue against which it should throttle) -+ */ -+void __sched io_schedule(void) -+{ -+ struct rq *rq = raw_rq(); -+ -+ delayacct_blkio_start(); -+ atomic_inc(&rq->nr_iowait); -+ current->in_iowait = 1; -+ schedule(); -+ current->in_iowait = 0; -+ atomic_dec(&rq->nr_iowait); -+ delayacct_blkio_end(); -+} -+EXPORT_SYMBOL(io_schedule); -+ -+long __sched io_schedule_timeout(long timeout) -+{ -+ struct rq *rq = raw_rq(); -+ long ret; -+ -+ delayacct_blkio_start(); -+ atomic_inc(&rq->nr_iowait); -+ current->in_iowait = 1; -+ ret = schedule_timeout(timeout); -+ current->in_iowait = 0; -+ atomic_dec(&rq->nr_iowait); -+ delayacct_blkio_end(); -+ return ret; -+} -+ -+/** -+ * sys_sched_get_priority_max - return maximum RT priority. -+ * @policy: scheduling class. -+ * -+ * this syscall returns the maximum rt_priority that can be used -+ * by a given scheduling class. -+ */ -+SYSCALL_DEFINE1(sched_get_priority_max, int, policy) -+{ -+ int ret = -EINVAL; -+ -+ switch (policy) { -+ case SCHED_FIFO: -+ case SCHED_RR: -+ ret = MAX_USER_RT_PRIO-1; -+ break; -+ case SCHED_NORMAL: -+ case SCHED_BATCH: -+ case SCHED_ISO: -+ case SCHED_IDLEPRIO: -+ ret = 0; -+ break; -+ } -+ return ret; -+} -+ -+/** -+ * sys_sched_get_priority_min - return minimum RT priority. -+ * @policy: scheduling class. -+ * -+ * this syscall returns the minimum rt_priority that can be used -+ * by a given scheduling class. -+ */ -+SYSCALL_DEFINE1(sched_get_priority_min, int, policy) -+{ -+ int ret = -EINVAL; -+ -+ switch (policy) { -+ case SCHED_FIFO: -+ case SCHED_RR: -+ ret = 1; -+ break; -+ case SCHED_NORMAL: -+ case SCHED_BATCH: -+ case SCHED_ISO: -+ case SCHED_IDLEPRIO: -+ ret = 0; -+ break; -+ } -+ return ret; -+} -+ -+/** -+ * sys_sched_rr_get_interval - return the default timeslice of a process. -+ * @pid: pid of the process. -+ * @interval: userspace pointer to the timeslice value. -+ * -+ * this syscall writes the default timeslice value of a given process -+ * into the user-space timespec buffer. A value of '0' means infinity. -+ */ -+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, -+ struct timespec __user *, interval) -+{ -+ struct task_struct *p; -+ unsigned int time_slice; -+ unsigned long flags; -+ struct rq *rq; -+ int retval; -+ struct timespec t; -+ -+ if (pid < 0) -+ return -EINVAL; -+ -+ retval = -ESRCH; -+ rcu_read_lock(); -+ p = find_process_by_pid(pid); -+ if (!p) -+ goto out_unlock; -+ -+ retval = security_task_getscheduler(p); -+ if (retval) -+ goto out_unlock; -+ -+ rq = task_grq_lock(p, &flags); -+ time_slice = p->policy == SCHED_FIFO ? 0 : MS_TO_NS(task_timeslice(p)); -+ task_grq_unlock(&flags); -+ -+ rcu_read_unlock(); -+ t = ns_to_timespec(time_slice); -+ retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; -+ return retval; -+ -+out_unlock: -+ rcu_read_unlock(); -+ return retval; -+} -+ -+static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; -+ -+void sched_show_task(struct task_struct *p) -+{ -+ unsigned long free = 0; -+ unsigned state; -+ -+ state = p->state ? __ffs(p->state) + 1 : 0; -+ printk(KERN_INFO "%-13.13s %c", p->comm, -+ state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); -+#if BITS_PER_LONG == 32 -+ if (state == TASK_RUNNING) -+ printk(KERN_CONT " running "); -+ else -+ printk(KERN_CONT " %08lx ", thread_saved_pc(p)); -+#else -+ if (state == TASK_RUNNING) -+ printk(KERN_CONT " running task "); -+ else -+ printk(KERN_CONT " %016lx ", thread_saved_pc(p)); -+#endif -+#ifdef CONFIG_DEBUG_STACK_USAGE -+ free = stack_not_used(p); -+#endif -+ printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, -+ task_pid_nr(p), task_pid_nr(p->real_parent), -+ (unsigned long)task_thread_info(p)->flags); -+ -+ show_stack(p, NULL); -+} -+ -+void show_state_filter(unsigned long state_filter) -+{ -+ struct task_struct *g, *p; -+ -+#if BITS_PER_LONG == 32 -+ printk(KERN_INFO -+ " task PC stack pid father\n"); -+#else -+ printk(KERN_INFO -+ " task PC stack pid father\n"); -+#endif -+ read_lock(&tasklist_lock); -+ do_each_thread(g, p) { -+ /* -+ * reset the NMI-timeout, listing all files on a slow -+ * console might take alot of time: -+ */ -+ touch_nmi_watchdog(); -+ if (!state_filter || (p->state & state_filter)) -+ sched_show_task(p); -+ } while_each_thread(g, p); -+ -+ touch_all_softlockup_watchdogs(); -+ -+ read_unlock(&tasklist_lock); -+ /* -+ * Only show locks if all tasks are dumped: -+ */ -+ if (!state_filter) -+ debug_show_all_locks(); -+} -+ -+/** -+ * init_idle - set up an idle thread for a given CPU -+ * @idle: task in question -+ * @cpu: cpu the idle task belongs to -+ * -+ * NOTE: this function does not set the idle thread's NEED_RESCHED -+ * flag, to make booting more robust. -+ */ -+void init_idle(struct task_struct *idle, int cpu) -+{ -+ struct rq *rq = cpu_rq(cpu); -+ unsigned long flags; -+ -+ time_grq_lock(rq, &flags); -+ idle->last_ran = rq->clock; -+ idle->state = TASK_RUNNING; -+ /* Setting prio to illegal value shouldn't matter when never queued */ -+ idle->prio = PRIO_LIMIT; -+ set_rq_task(rq, idle); -+ idle->cpus_allowed = cpumask_of_cpu(cpu); -+ /* Silence PROVE_RCU */ -+ rcu_read_lock(); -+ set_task_cpu(idle, cpu); -+ rcu_read_unlock(); -+ rq->curr = rq->idle = idle; -+ idle->oncpu = 1; -+ set_cpuidle_map(cpu); -+ grq_unlock_irqrestore(&flags); -+ -+ /* Set the preempt count _outside_ the spinlocks! */ -+#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL) -+ task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0); -+#else -+ task_thread_info(idle)->preempt_count = 0; -+#endif -+ ftrace_graph_init_task(idle); -+} -+ -+/* -+ * In a system that switches off the HZ timer nohz_cpu_mask -+ * indicates which cpus entered this state. This is used -+ * in the rcu update to wait only for active cpus. For system -+ * which do not switch off the HZ timer nohz_cpu_mask should -+ * always be CPU_BITS_NONE. -+ */ -+cpumask_var_t nohz_cpu_mask; -+ -+#ifdef CONFIG_SMP -+#ifdef CONFIG_NO_HZ -+void select_nohz_load_balancer(int stop_tick) -+{ -+} -+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -+/** -+ * lowest_flag_domain - Return lowest sched_domain containing flag. -+ * @cpu: The cpu whose lowest level of sched domain is to -+ * be returned. -+ * @flag: The flag to check for the lowest sched_domain -+ * for the given cpu. -+ * -+ * Returns the lowest sched_domain of a cpu which contains the given flag. -+ */ -+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) -+{ -+ struct sched_domain *sd; -+ -+ for_each_domain(cpu, sd) -+ if (sd && (sd->flags & flag)) -+ break; -+ -+ return sd; -+} -+ -+/** -+ * for_each_flag_domain - Iterates over sched_domains containing the flag. -+ * @cpu: The cpu whose domains we're iterating over. -+ * @sd: variable holding the value of the power_savings_sd -+ * for cpu. -+ * @flag: The flag to filter the sched_domains to be iterated. -+ * -+ * Iterates over all the scheduler domains for a given cpu that has the 'flag' -+ * set, starting from the lowest sched_domain to the highest. -+ */ -+#define for_each_flag_domain(cpu, sd, flag) \ -+ for (sd = lowest_flag_domain(cpu, flag); \ -+ (sd && (sd->flags & flag)); sd = sd->parent) -+ -+#endif /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ -+ -+static inline void resched_cpu(int cpu) -+{ -+ unsigned long flags; -+ -+ grq_lock_irqsave(&flags); -+ resched_task(cpu_curr(cpu)); -+ grq_unlock_irqrestore(&flags); -+} -+ -+/* -+ * In the semi idle case, use the nearest busy cpu for migrating timers -+ * from an idle cpu. This is good for power-savings. -+ * -+ * We don't do similar optimization for completely idle system, as -+ * selecting an idle cpu will add more delays to the timers than intended -+ * (as that cpu's timer base may not be uptodate wrt jiffies etc). -+ */ -+int get_nohz_timer_target(void) -+{ -+ int cpu = smp_processor_id(); -+ int i; -+ struct sched_domain *sd; -+ -+ for_each_domain(cpu, sd) { -+ for_each_cpu(i, sched_domain_span(sd)) -+ if (!idle_cpu(i)) -+ return i; -+ } -+ return cpu; -+} -+ -+/* -+ * When add_timer_on() enqueues a timer into the timer wheel of an -+ * idle CPU then this timer might expire before the next timer event -+ * which is scheduled to wake up that CPU. In case of a completely -+ * idle system the next event might even be infinite time into the -+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and -+ * leaves the inner idle loop so the newly added timer is taken into -+ * account when the CPU goes back to idle and evaluates the timer -+ * wheel for the next timer event. -+ */ -+void wake_up_idle_cpu(int cpu) -+{ -+ struct task_struct *idle; -+ struct rq *rq; -+ -+ if (cpu == smp_processor_id()) -+ return; -+ -+ rq = cpu_rq(cpu); -+ idle = rq->idle; -+ -+ /* -+ * This is safe, as this function is called with the timer -+ * wheel base lock of (cpu) held. When the CPU is on the way -+ * to idle and has not yet set rq->curr to idle then it will -+ * be serialised on the timer wheel base lock and take the new -+ * timer into account automatically. -+ */ -+ if (unlikely(rq->curr != idle)) -+ return; -+ -+ /* -+ * We can set TIF_RESCHED on the idle task of the other CPU -+ * lockless. The worst case is that the other CPU runs the -+ * idle task through an additional NOOP schedule() -+ */ -+ set_tsk_need_resched(idle); -+ -+ /* NEED_RESCHED must be visible before we test polling */ -+ smp_mb(); -+ if (!tsk_is_polling(idle)) -+ smp_send_reschedule(cpu); -+} -+ -+#endif /* CONFIG_NO_HZ */ -+ -+/* -+ * Change a given task's CPU affinity. Migrate the thread to a -+ * proper CPU and schedule it away if the CPU it's executing on -+ * is removed from the allowed bitmask. -+ * -+ * NOTE: the caller must have a valid reference to the task, the -+ * task must not exit() & deallocate itself prematurely. The -+ * call is not atomic; no spinlocks may be held. -+ */ -+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) -+{ -+ unsigned long flags; -+ int running_wrong = 0; -+ int queued = 0; -+ struct rq *rq; -+ int ret = 0; -+ -+ rq = task_grq_lock(p, &flags); -+ -+ if (!cpumask_intersects(new_mask, cpu_active_mask)) { -+ ret = -EINVAL; -+ goto out; -+ } -+ -+ if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && -+ !cpumask_equal(&p->cpus_allowed, new_mask))) { -+ ret = -EINVAL; -+ goto out; -+ } -+ -+ queued = task_queued(p); -+ -+ cpumask_copy(&p->cpus_allowed, new_mask); -+ -+ /* Can the task run on the task's current CPU? If so, we're done */ -+ if (cpumask_test_cpu(task_cpu(p), new_mask)) -+ goto out; -+ -+ if (task_running(p)) { -+ /* Task is running on the wrong cpu now, reschedule it. */ -+ if (rq == this_rq()) { -+ set_tsk_need_resched(p); -+ running_wrong = 1; -+ } else -+ resched_task(p); -+ } else -+ set_task_cpu(p, cpumask_any_and(cpu_active_mask, new_mask)); -+ -+out: -+ if (queued) -+ try_preempt(p, rq); -+ task_grq_unlock(&flags); -+ -+ if (running_wrong) -+ _cond_resched(); -+ -+ return ret; -+} -+EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); -+ -+#ifdef CONFIG_HOTPLUG_CPU -+/* -+ * Reschedule a task if it's on a dead CPU. -+ */ -+void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) -+{ -+ unsigned long flags; -+ struct rq *rq, *dead_rq; -+ -+ dead_rq = cpu_rq(dead_cpu); -+ rq = task_grq_lock(p, &flags); -+ if (rq == dead_rq && task_running(p)) -+ resched_task(p); -+ task_grq_unlock(&flags); -+ -+} -+ -+/* Run through task list and find tasks affined to just the dead cpu, then -+ * allocate a new affinity */ -+static void break_sole_affinity(int src_cpu) -+{ -+ struct task_struct *p, *t; -+ -+ do_each_thread(t, p) { -+ if (!online_cpus(p)) { -+ cpumask_copy(&p->cpus_allowed, cpu_possible_mask); -+ /* -+ * Don't tell them about moving exiting tasks or -+ * kernel threads (both mm NULL), since they never -+ * leave kernel. -+ */ -+ if (p->mm && printk_ratelimit()) { -+ printk(KERN_INFO "process %d (%s) no " -+ "longer affine to cpu %d\n", -+ task_pid_nr(p), p->comm, src_cpu); -+ } -+ } -+ } while_each_thread(t, p); -+} -+ -+/* -+ * Schedules idle task to be the next runnable task on current CPU. -+ * It does so by boosting its priority to highest possible. -+ * Used by CPU offline code. -+ */ -+void sched_idle_next(void) -+{ -+ int this_cpu = smp_processor_id(); -+ struct rq *rq = cpu_rq(this_cpu); -+ struct task_struct *idle = rq->idle; -+ unsigned long flags; -+ -+ /* cpu has to be offline */ -+ BUG_ON(cpu_online(this_cpu)); -+ -+ /* -+ * Strictly not necessary since rest of the CPUs are stopped by now -+ * and interrupts disabled on the current cpu. -+ */ -+ grq_lock_irqsave(&flags); -+ break_sole_affinity(this_cpu); -+ -+ __setscheduler(idle, rq, SCHED_FIFO, STOP_PRIO); -+ -+ activate_idle_task(idle); -+ set_tsk_need_resched(rq->curr); -+ -+ grq_unlock_irqrestore(&flags); -+} -+ -+void sched_set_stop_task(int cpu, struct task_struct *stop) -+{ -+ struct sched_param stop_param = { .sched_priority = STOP_PRIO }; -+ struct sched_param start_param = { .sched_priority = MAX_USER_RT_PRIO - 1 }; -+ struct task_struct *old_stop = cpu_rq(cpu)->stop; -+ -+ if (stop) { -+ /* -+ * Make it appear like a SCHED_FIFO task, its something -+ * userspace knows about and won't get confused about. -+ * -+ * Also, it will make PI more or less work without too -+ * much confusion -- but then, stop work should not -+ * rely on PI working anyway. -+ */ -+ sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param); -+ } -+ -+ cpu_rq(cpu)->stop = stop; -+ -+ if (old_stop) { -+ /* -+ * Reset it back to a normal rt scheduling prio so that -+ * it can die in pieces. -+ */ -+ sched_setscheduler_nocheck(old_stop, SCHED_FIFO, &start_param); -+ } -+} -+ -+/* -+ * Ensures that the idle task is using init_mm right before its cpu goes -+ * offline. -+ */ -+void idle_task_exit(void) -+{ -+ struct mm_struct *mm = current->active_mm; -+ -+ BUG_ON(cpu_online(smp_processor_id())); -+ -+ if (mm != &init_mm) -+ switch_mm(mm, &init_mm, current); -+ mmdrop(mm); -+} -+ -+#endif /* CONFIG_HOTPLUG_CPU */ -+ -+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) -+ -+static struct ctl_table sd_ctl_dir[] = { -+ { -+ .procname = "sched_domain", -+ .mode = 0555, -+ }, -+ {} -+}; -+ -+static struct ctl_table sd_ctl_root[] = { -+ { -+ .procname = "kernel", -+ .mode = 0555, -+ .child = sd_ctl_dir, -+ }, -+ {} -+}; -+ -+static struct ctl_table *sd_alloc_ctl_entry(int n) -+{ -+ struct ctl_table *entry = -+ kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); -+ -+ return entry; -+} -+ -+static void sd_free_ctl_entry(struct ctl_table **tablep) -+{ -+ struct ctl_table *entry; -+ -+ /* -+ * In the intermediate directories, both the child directory and -+ * procname are dynamically allocated and could fail but the mode -+ * will always be set. In the lowest directory the names are -+ * static strings and all have proc handlers. -+ */ -+ for (entry = *tablep; entry->mode; entry++) { -+ if (entry->child) -+ sd_free_ctl_entry(&entry->child); -+ if (entry->proc_handler == NULL) -+ kfree(entry->procname); -+ } -+ -+ kfree(*tablep); -+ *tablep = NULL; -+} -+ -+static void -+set_table_entry(struct ctl_table *entry, -+ const char *procname, void *data, int maxlen, -+ mode_t mode, proc_handler *proc_handler) -+{ -+ entry->procname = procname; -+ entry->data = data; -+ entry->maxlen = maxlen; -+ entry->mode = mode; -+ entry->proc_handler = proc_handler; -+} -+ -+static struct ctl_table * -+sd_alloc_ctl_domain_table(struct sched_domain *sd) -+{ -+ struct ctl_table *table = sd_alloc_ctl_entry(13); -+ -+ if (table == NULL) -+ return NULL; -+ -+ set_table_entry(&table[0], "min_interval", &sd->min_interval, -+ sizeof(long), 0644, proc_doulongvec_minmax); -+ set_table_entry(&table[1], "max_interval", &sd->max_interval, -+ sizeof(long), 0644, proc_doulongvec_minmax); -+ set_table_entry(&table[2], "busy_idx", &sd->busy_idx, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[3], "idle_idx", &sd->idle_idx, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[5], "wake_idx", &sd->wake_idx, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[7], "busy_factor", &sd->busy_factor, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[9], "cache_nice_tries", -+ &sd->cache_nice_tries, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[10], "flags", &sd->flags, -+ sizeof(int), 0644, proc_dointvec_minmax); -+ set_table_entry(&table[11], "name", sd->name, -+ CORENAME_MAX_SIZE, 0444, proc_dostring); -+ /* &table[12] is terminator */ -+ -+ return table; -+} -+ -+static ctl_table *sd_alloc_ctl_cpu_table(int cpu) -+{ -+ struct ctl_table *entry, *table; -+ struct sched_domain *sd; -+ int domain_num = 0, i; -+ char buf[32]; -+ -+ for_each_domain(cpu, sd) -+ domain_num++; -+ entry = table = sd_alloc_ctl_entry(domain_num + 1); -+ if (table == NULL) -+ return NULL; -+ -+ i = 0; -+ for_each_domain(cpu, sd) { -+ snprintf(buf, 32, "domain%d", i); -+ entry->procname = kstrdup(buf, GFP_KERNEL); -+ entry->mode = 0555; -+ entry->child = sd_alloc_ctl_domain_table(sd); -+ entry++; -+ i++; -+ } -+ return table; -+} -+ -+static struct ctl_table_header *sd_sysctl_header; -+static void register_sched_domain_sysctl(void) -+{ -+ int i, cpu_num = num_possible_cpus(); -+ struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); -+ char buf[32]; -+ -+ WARN_ON(sd_ctl_dir[0].child); -+ sd_ctl_dir[0].child = entry; -+ -+ if (entry == NULL) -+ return; -+ -+ for_each_possible_cpu(i) { -+ snprintf(buf, 32, "cpu%d", i); -+ entry->procname = kstrdup(buf, GFP_KERNEL); -+ entry->mode = 0555; -+ entry->child = sd_alloc_ctl_cpu_table(i); -+ entry++; -+ } -+ -+ WARN_ON(sd_sysctl_header); -+ sd_sysctl_header = register_sysctl_table(sd_ctl_root); -+} -+ -+/* may be called multiple times per register */ -+static void unregister_sched_domain_sysctl(void) -+{ -+ if (sd_sysctl_header) -+ unregister_sysctl_table(sd_sysctl_header); -+ sd_sysctl_header = NULL; -+ if (sd_ctl_dir[0].child) -+ sd_free_ctl_entry(&sd_ctl_dir[0].child); -+} -+#else -+static void register_sched_domain_sysctl(void) -+{ -+} -+static void unregister_sched_domain_sysctl(void) -+{ -+} -+#endif -+ -+static void set_rq_online(struct rq *rq) -+{ -+ if (!rq->online) { -+ cpumask_set_cpu(cpu_of(rq), rq->rd->online); -+ rq->online = 1; -+ } -+} -+ -+static void set_rq_offline(struct rq *rq) -+{ -+ if (rq->online) { -+ cpumask_clear_cpu(cpu_of(rq), rq->rd->online); -+ rq->online = 0; -+ } -+} -+ -+/* -+ * migration_call - callback that gets triggered when a CPU is added. -+ */ -+static int __cpuinit -+migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) -+{ -+#ifdef CONFIG_HOTPLUG_CPU -+ struct task_struct *idle; -+#endif -+ int cpu = (long)hcpu; -+ unsigned long flags; -+ struct rq *rq = cpu_rq(cpu); -+ -+ switch (action) { -+ -+ case CPU_UP_PREPARE: -+ case CPU_UP_PREPARE_FROZEN: -+ break; -+ -+ case CPU_ONLINE: -+ case CPU_ONLINE_FROZEN: -+ /* Update our root-domain */ -+ grq_lock_irqsave(&flags); -+ if (rq->rd) { -+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); -+ -+ set_rq_online(rq); -+ } -+ grq_unlock_irqrestore(&flags); -+ break; -+ -+#ifdef CONFIG_HOTPLUG_CPU -+ case CPU_DEAD: -+ case CPU_DEAD_FROZEN: -+ idle = rq->idle; -+ /* Idle task back to normal (off runqueue, low prio) */ -+ grq_lock_irq(); -+ return_task(idle, 1); -+ idle->static_prio = MAX_PRIO; -+ __setscheduler(idle, rq, SCHED_NORMAL, 0); -+ idle->prio = PRIO_LIMIT; -+ set_rq_task(rq, idle); -+ update_clocks(rq); -+ grq_unlock_irq(); -+ break; -+ -+ case CPU_DYING: -+ case CPU_DYING_FROZEN: -+ /* Update our root-domain */ -+ grq_lock_irqsave(&flags); -+ if (rq->rd) { -+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); -+ set_rq_offline(rq); -+ } -+ grq_unlock_irqrestore(&flags); -+ break; -+#endif -+ } -+ return NOTIFY_OK; -+} -+ -+/* -+ * Register at high priority so that task migration (migrate_all_tasks) -+ * happens before everything else. This has to be lower priority than -+ * the notifier in the perf_counter subsystem, though. -+ */ -+static struct notifier_block __cpuinitdata migration_notifier = { -+ .notifier_call = migration_call, -+ .priority = CPU_PRI_MIGRATION, -+}; -+ -+static int __cpuinit sched_cpu_active(struct notifier_block *nfb, -+ unsigned long action, void *hcpu) -+{ -+ switch (action & ~CPU_TASKS_FROZEN) { -+ case CPU_ONLINE: -+ case CPU_DOWN_FAILED: -+ set_cpu_active((long)hcpu, true); -+ return NOTIFY_OK; -+ default: -+ return NOTIFY_DONE; -+ } -+} -+ -+static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, -+ unsigned long action, void *hcpu) -+{ -+ switch (action & ~CPU_TASKS_FROZEN) { -+ case CPU_DOWN_PREPARE: -+ set_cpu_active((long)hcpu, false); -+ return NOTIFY_OK; -+ default: -+ return NOTIFY_DONE; -+ } -+} -+ -+int __init migration_init(void) -+{ -+ void *cpu = (void *)(long)smp_processor_id(); -+ int err; -+ -+ /* Initialise migration for the boot CPU */ -+ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); -+ BUG_ON(err == NOTIFY_BAD); -+ migration_call(&migration_notifier, CPU_ONLINE, cpu); -+ register_cpu_notifier(&migration_notifier); -+ -+ /* Register cpu active notifiers */ -+ cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); -+ cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); -+ -+ return 0; -+} -+early_initcall(migration_init); -+#endif -+ -+#ifdef CONFIG_SMP -+ -+#ifdef CONFIG_SCHED_DEBUG -+ -+static __read_mostly int sched_domain_debug_enabled; -+ -+static int __init sched_domain_debug_setup(char *str) -+{ -+ sched_domain_debug_enabled = 1; -+ -+ return 0; -+} -+early_param("sched_debug", sched_domain_debug_setup); -+ -+static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, -+ struct cpumask *groupmask) -+{ -+ struct sched_group *group = sd->groups; -+ char str[256]; -+ -+ cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); -+ cpumask_clear(groupmask); -+ -+ printk(KERN_DEBUG "%*s domain %d: ", level, "", level); -+ -+ if (!(sd->flags & SD_LOAD_BALANCE)) { -+ printk("does not load-balance\n"); -+ if (sd->parent) -+ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" -+ " has parent"); -+ return -1; -+ } -+ -+ printk(KERN_CONT "span %s level %s\n", str, sd->name); -+ -+ if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { -+ printk(KERN_ERR "ERROR: domain->span does not contain " -+ "CPU%d\n", cpu); -+ } -+ if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { -+ printk(KERN_ERR "ERROR: domain->groups does not contain" -+ " CPU%d\n", cpu); -+ } -+ -+ printk(KERN_DEBUG "%*s groups:", level + 1, ""); -+ do { -+ if (!group) { -+ printk("\n"); -+ printk(KERN_ERR "ERROR: group is NULL\n"); -+ break; -+ } -+ -+ if (!group->cpu_power) { -+ printk(KERN_CONT "\n"); -+ printk(KERN_ERR "ERROR: domain->cpu_power not " -+ "set\n"); -+ break; -+ } -+ -+ if (!cpumask_weight(sched_group_cpus(group))) { -+ printk(KERN_CONT "\n"); -+ printk(KERN_ERR "ERROR: empty group\n"); -+ break; -+ } -+ -+ if (cpumask_intersects(groupmask, sched_group_cpus(group))) { -+ printk(KERN_CONT "\n"); -+ printk(KERN_ERR "ERROR: repeated CPUs\n"); -+ break; -+ } -+ -+ cpumask_or(groupmask, groupmask, sched_group_cpus(group)); -+ -+ cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); -+ -+ printk(KERN_CONT " %s", str); -+ if (group->cpu_power != SCHED_LOAD_SCALE) { -+ printk(KERN_CONT " (cpu_power = %d)", -+ group->cpu_power); -+ } -+ -+ group = group->next; -+ } while (group != sd->groups); -+ printk(KERN_CONT "\n"); -+ -+ if (!cpumask_equal(sched_domain_span(sd), groupmask)) -+ printk(KERN_ERR "ERROR: groups don't span domain->span\n"); -+ -+ if (sd->parent && -+ !cpumask_subset(groupmask, sched_domain_span(sd->parent))) -+ printk(KERN_ERR "ERROR: parent span is not a superset " -+ "of domain->span\n"); -+ return 0; -+} -+ -+static void sched_domain_debug(struct sched_domain *sd, int cpu) -+{ -+ cpumask_var_t groupmask; -+ int level = 0; -+ -+ if (!sched_domain_debug_enabled) -+ return; -+ -+ if (!sd) { -+ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); -+ return; -+ } -+ -+ printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); -+ -+ if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) { -+ printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); -+ return; -+ } -+ -+ for (;;) { -+ if (sched_domain_debug_one(sd, cpu, level, groupmask)) -+ break; -+ level++; -+ sd = sd->parent; -+ if (!sd) -+ break; -+ } -+ free_cpumask_var(groupmask); -+} -+#else /* !CONFIG_SCHED_DEBUG */ -+# define sched_domain_debug(sd, cpu) do { } while (0) -+#endif /* CONFIG_SCHED_DEBUG */ -+ -+static int sd_degenerate(struct sched_domain *sd) -+{ -+ if (cpumask_weight(sched_domain_span(sd)) == 1) -+ return 1; -+ -+ /* Following flags need at least 2 groups */ -+ if (sd->flags & (SD_LOAD_BALANCE | -+ SD_BALANCE_NEWIDLE | -+ SD_BALANCE_FORK | -+ SD_BALANCE_EXEC | -+ SD_SHARE_CPUPOWER | -+ SD_SHARE_PKG_RESOURCES)) { -+ if (sd->groups != sd->groups->next) -+ return 0; -+ } -+ -+ /* Following flags don't use groups */ -+ if (sd->flags & (SD_WAKE_AFFINE)) -+ return 0; -+ -+ return 1; -+} -+ -+static int -+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) -+{ -+ unsigned long cflags = sd->flags, pflags = parent->flags; -+ -+ if (sd_degenerate(parent)) -+ return 1; -+ -+ if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) -+ return 0; -+ -+ /* Flags needing groups don't count if only 1 group in parent */ -+ if (parent->groups == parent->groups->next) { -+ pflags &= ~(SD_LOAD_BALANCE | -+ SD_BALANCE_NEWIDLE | -+ SD_BALANCE_FORK | -+ SD_BALANCE_EXEC | -+ SD_SHARE_CPUPOWER | -+ SD_SHARE_PKG_RESOURCES); -+ if (nr_node_ids == 1) -+ pflags &= ~SD_SERIALIZE; -+ } -+ if (~cflags & pflags) -+ return 0; -+ -+ return 1; -+} -+ -+static void free_rootdomain(struct root_domain *rd) -+{ -+ synchronize_sched(); -+ -+ free_cpumask_var(rd->rto_mask); -+ free_cpumask_var(rd->online); -+ free_cpumask_var(rd->span); -+ kfree(rd); -+} -+ -+static void rq_attach_root(struct rq *rq, struct root_domain *rd) -+{ -+ struct root_domain *old_rd = NULL; -+ unsigned long flags; -+ -+ grq_lock_irqsave(&flags); -+ -+ if (rq->rd) { -+ old_rd = rq->rd; -+ -+ if (cpumask_test_cpu(cpu_of(rq), old_rd->online)) -+ set_rq_offline(rq); -+ -+ cpumask_clear_cpu(cpu_of(rq), old_rd->span); -+ -+ /* -+ * If we dont want to free the old_rt yet then -+ * set old_rd to NULL to skip the freeing later -+ * in this function: -+ */ -+ if (!atomic_dec_and_test(&old_rd->refcount)) -+ old_rd = NULL; -+ } -+ -+ atomic_inc(&rd->refcount); -+ rq->rd = rd; -+ -+ cpumask_set_cpu(cpu_of(rq), rd->span); -+ if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) -+ set_rq_online(rq); -+ -+ grq_unlock_irqrestore(&flags); -+ -+ if (old_rd) -+ free_rootdomain(old_rd); -+} -+ -+static int init_rootdomain(struct root_domain *rd) -+{ -+ memset(rd, 0, sizeof(*rd)); -+ -+ if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) -+ goto out; -+ if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) -+ goto free_span; -+ if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) -+ goto free_online; -+ -+ if (cpupri_init(&rd->cpupri) != 0) -+ goto free_rto_mask; -+ return 0; -+ -+free_rto_mask: -+ free_cpumask_var(rd->rto_mask); -+free_online: -+ free_cpumask_var(rd->online); -+free_span: -+ free_cpumask_var(rd->span); -+out: -+ return -ENOMEM; -+} -+ -+static void init_defrootdomain(void) -+{ -+ init_rootdomain(&def_root_domain); -+ -+ atomic_set(&def_root_domain.refcount, 1); -+} -+ -+static struct root_domain *alloc_rootdomain(void) -+{ -+ struct root_domain *rd; -+ -+ rd = kmalloc(sizeof(*rd), GFP_KERNEL); -+ if (!rd) -+ return NULL; -+ -+ if (init_rootdomain(rd) != 0) { -+ kfree(rd); -+ return NULL; -+ } -+ -+ return rd; -+} -+ -+/* -+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must -+ * hold the hotplug lock. -+ */ -+static void -+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) -+{ -+ struct rq *rq = cpu_rq(cpu); -+ struct sched_domain *tmp; -+ -+ for (tmp = sd; tmp; tmp = tmp->parent) -+ tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); -+ -+ /* Remove the sched domains which do not contribute to scheduling. */ -+ for (tmp = sd; tmp; ) { -+ struct sched_domain *parent = tmp->parent; -+ if (!parent) -+ break; -+ -+ if (sd_parent_degenerate(tmp, parent)) { -+ tmp->parent = parent->parent; -+ if (parent->parent) -+ parent->parent->child = tmp; -+ } else -+ tmp = tmp->parent; -+ } -+ -+ if (sd && sd_degenerate(sd)) { -+ sd = sd->parent; -+ if (sd) -+ sd->child = NULL; -+ } -+ -+ sched_domain_debug(sd, cpu); -+ -+ rq_attach_root(rq, rd); -+ rcu_assign_pointer(rq->sd, sd); -+} -+ -+/* cpus with isolated domains */ -+static cpumask_var_t cpu_isolated_map; -+ -+/* Setup the mask of cpus configured for isolated domains */ -+static int __init isolated_cpu_setup(char *str) -+{ -+ alloc_bootmem_cpumask_var(&cpu_isolated_map); -+ cpulist_parse(str, cpu_isolated_map); -+ return 1; -+} -+ -+__setup("isolcpus=", isolated_cpu_setup); -+ -+/* -+ * init_sched_build_groups takes the cpumask we wish to span, and a pointer -+ * to a function which identifies what group(along with sched group) a CPU -+ * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids -+ * (due to the fact that we keep track of groups covered with a struct cpumask). -+ * -+ * init_sched_build_groups will build a circular linked list of the groups -+ * covered by the given span, and will set each group's ->cpumask correctly, -+ * and ->cpu_power to 0. -+ */ -+static void -+init_sched_build_groups(const struct cpumask *span, -+ const struct cpumask *cpu_map, -+ int (*group_fn)(int cpu, const struct cpumask *cpu_map, -+ struct sched_group **sg, -+ struct cpumask *tmpmask), -+ struct cpumask *covered, struct cpumask *tmpmask) -+{ -+ struct sched_group *first = NULL, *last = NULL; -+ int i; -+ -+ cpumask_clear(covered); -+ -+ for_each_cpu(i, span) { -+ struct sched_group *sg; -+ int group = group_fn(i, cpu_map, &sg, tmpmask); -+ int j; -+ -+ if (cpumask_test_cpu(i, covered)) -+ continue; -+ -+ cpumask_clear(sched_group_cpus(sg)); -+ sg->cpu_power = 0; -+ -+ for_each_cpu(j, span) { -+ if (group_fn(j, cpu_map, NULL, tmpmask) != group) -+ continue; -+ -+ cpumask_set_cpu(j, covered); -+ cpumask_set_cpu(j, sched_group_cpus(sg)); -+ } -+ if (!first) -+ first = sg; -+ if (last) -+ last->next = sg; -+ last = sg; -+ } -+ last->next = first; -+} -+ -+#define SD_NODES_PER_DOMAIN 16 -+ -+#ifdef CONFIG_NUMA -+ -+/** -+ * find_next_best_node - find the next node to include in a sched_domain -+ * @node: node whose sched_domain we're building -+ * @used_nodes: nodes already in the sched_domain -+ * -+ * Find the next node to include in a given scheduling domain. Simply -+ * finds the closest node not already in the @used_nodes map. -+ * -+ * Should use nodemask_t. -+ */ -+static int find_next_best_node(int node, nodemask_t *used_nodes) -+{ -+ int i, n, val, min_val, best_node = 0; -+ -+ min_val = INT_MAX; -+ -+ for (i = 0; i < nr_node_ids; i++) { -+ /* Start at @node */ -+ n = (node + i) % nr_node_ids; -+ -+ if (!nr_cpus_node(n)) -+ continue; -+ -+ /* Skip already used nodes */ -+ if (node_isset(n, *used_nodes)) -+ continue; -+ -+ /* Simple min distance search */ -+ val = node_distance(node, n); -+ -+ if (val < min_val) { -+ min_val = val; -+ best_node = n; -+ } -+ } -+ -+ node_set(best_node, *used_nodes); -+ return best_node; -+} -+ -+/** -+ * sched_domain_node_span - get a cpumask for a node's sched_domain -+ * @node: node whose cpumask we're constructing -+ * @span: resulting cpumask -+ * -+ * Given a node, construct a good cpumask for its sched_domain to span. It -+ * should be one that prevents unnecessary balancing, but also spreads tasks -+ * out optimally. -+ */ -+static void sched_domain_node_span(int node, struct cpumask *span) -+{ -+ nodemask_t used_nodes; -+ int i; -+ -+ cpumask_clear(span); -+ nodes_clear(used_nodes); -+ -+ cpumask_or(span, span, cpumask_of_node(node)); -+ node_set(node, used_nodes); -+ -+ for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { -+ int next_node = find_next_best_node(node, &used_nodes); -+ -+ cpumask_or(span, span, cpumask_of_node(next_node)); -+ } -+} -+#endif /* CONFIG_NUMA */ -+ -+int sched_smt_power_savings = 0, sched_mc_power_savings = 0; -+ -+/* -+ * The cpus mask in sched_group and sched_domain hangs off the end. -+ * -+ * ( See the the comments in include/linux/sched.h:struct sched_group -+ * and struct sched_domain. ) -+ */ -+struct static_sched_group { -+ struct sched_group sg; -+ DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); -+}; -+ -+struct static_sched_domain { -+ struct sched_domain sd; -+ DECLARE_BITMAP(span, CONFIG_NR_CPUS); -+}; -+ -+struct s_data { -+#ifdef CONFIG_NUMA -+ int sd_allnodes; -+ cpumask_var_t domainspan; -+ cpumask_var_t covered; -+ cpumask_var_t notcovered; -+#endif -+ cpumask_var_t nodemask; -+ cpumask_var_t this_sibling_map; -+ cpumask_var_t this_core_map; -+ cpumask_var_t this_book_map; -+ cpumask_var_t send_covered; -+ cpumask_var_t tmpmask; -+ struct sched_group **sched_group_nodes; -+ struct root_domain *rd; -+}; -+ -+enum s_alloc { -+ sa_sched_groups = 0, -+ sa_rootdomain, -+ sa_tmpmask, -+ sa_send_covered, -+ sa_this_book_map, -+ sa_this_core_map, -+ sa_this_sibling_map, -+ sa_nodemask, -+ sa_sched_group_nodes, -+#ifdef CONFIG_NUMA -+ sa_notcovered, -+ sa_covered, -+ sa_domainspan, -+#endif -+ sa_none, -+}; -+ -+/* -+ * SMT sched-domains: -+ */ -+#ifdef CONFIG_SCHED_SMT -+static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -+static DEFINE_PER_CPU(struct static_sched_group, sched_groups); -+ -+static int -+cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, -+ struct sched_group **sg, struct cpumask *unused) -+{ -+ if (sg) -+ *sg = &per_cpu(sched_groups, cpu).sg; -+ return cpu; -+} -+#endif /* CONFIG_SCHED_SMT */ -+ -+/* -+ * multi-core sched-domains: -+ */ -+#ifdef CONFIG_SCHED_MC -+static DEFINE_PER_CPU(struct static_sched_domain, core_domains); -+static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); -+ -+static int -+cpu_to_core_group(int cpu, const struct cpumask *cpu_map, -+ struct sched_group **sg, struct cpumask *mask) -+{ -+ int group; -+#ifdef CONFIG_SCHED_SMT -+ cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); -+ group = cpumask_first(mask); -+#else -+ group = cpu; -+#endif -+ if (sg) -+ *sg = &per_cpu(sched_group_core, group).sg; -+ return group; -+} -+#endif /* CONFIG_SCHED_MC */ -+ -+/* -+ * book sched-domains: -+ */ -+#ifdef CONFIG_SCHED_BOOK -+static DEFINE_PER_CPU(struct static_sched_domain, book_domains); -+static DEFINE_PER_CPU(struct static_sched_group, sched_group_book); -+ -+static int -+cpu_to_book_group(int cpu, const struct cpumask *cpu_map, -+ struct sched_group **sg, struct cpumask *mask) -+{ -+ int group = cpu; -+#ifdef CONFIG_SCHED_MC -+ cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); -+ group = cpumask_first(mask); -+#elif defined(CONFIG_SCHED_SMT) -+ cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); -+ group = cpumask_first(mask); -+#endif -+ if (sg) -+ *sg = &per_cpu(sched_group_book, group).sg; -+ return group; -+} -+#endif /* CONFIG_SCHED_BOOK */ -+ -+static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); -+static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); -+ -+static int -+cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, -+ struct sched_group **sg, struct cpumask *mask) -+{ -+ int group; -+#ifdef CONFIG_SCHED_BOOK -+ cpumask_and(mask, cpu_book_mask(cpu), cpu_map); -+ group = cpumask_first(mask); -+#elif defined(CONFIG_SCHED_MC) -+ cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); -+ group = cpumask_first(mask); -+#elif defined(CONFIG_SCHED_SMT) -+ cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); -+ group = cpumask_first(mask); -+#else -+ group = cpu; -+#endif -+ if (sg) -+ *sg = &per_cpu(sched_group_phys, group).sg; -+ return group; -+} -+ -+/** -+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. -+ * @group: The group whose first cpu is to be returned. -+ */ -+static inline unsigned int group_first_cpu(struct sched_group *group) -+{ -+ return cpumask_first(sched_group_cpus(group)); -+} -+ -+#ifdef CONFIG_NUMA -+/* -+ * The init_sched_build_groups can't handle what we want to do with node -+ * groups, so roll our own. Now each node has its own list of groups which -+ * gets dynamically allocated. -+ */ -+static DEFINE_PER_CPU(struct static_sched_domain, node_domains); -+static struct sched_group ***sched_group_nodes_bycpu; -+ -+static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); -+static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); -+ -+static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, -+ struct sched_group **sg, -+ struct cpumask *nodemask) -+{ -+ int group; -+ -+ cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); -+ group = cpumask_first(nodemask); -+ -+ if (sg) -+ *sg = &per_cpu(sched_group_allnodes, group).sg; -+ return group; -+} -+ -+static void init_numa_sched_groups_power(struct sched_group *group_head) -+{ -+ struct sched_group *sg = group_head; -+ int j; -+ -+ if (!sg) -+ return; -+ do { -+ for_each_cpu(j, sched_group_cpus(sg)) { -+ struct sched_domain *sd; -+ -+ sd = &per_cpu(phys_domains, j).sd; -+ if (j != group_first_cpu(sd->groups)) { -+ /* -+ * Only add "power" once for each -+ * physical package. -+ */ -+ continue; -+ } -+ -+ sg->cpu_power += sd->groups->cpu_power; -+ } -+ sg = sg->next; -+ } while (sg != group_head); -+} -+ -+static int build_numa_sched_groups(struct s_data *d, -+ const struct cpumask *cpu_map, int num) -+{ -+ struct sched_domain *sd; -+ struct sched_group *sg, *prev; -+ int n, j; -+ -+ cpumask_clear(d->covered); -+ cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map); -+ if (cpumask_empty(d->nodemask)) { -+ d->sched_group_nodes[num] = NULL; -+ goto out; -+ } -+ -+ sched_domain_node_span(num, d->domainspan); -+ cpumask_and(d->domainspan, d->domainspan, cpu_map); -+ -+ sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), -+ GFP_KERNEL, num); -+ if (!sg) { -+ printk(KERN_WARNING "Can not alloc domain group for node %d\n", -+ num); -+ return -ENOMEM; -+ } -+ d->sched_group_nodes[num] = sg; -+ -+ for_each_cpu(j, d->nodemask) { -+ sd = &per_cpu(node_domains, j).sd; -+ sd->groups = sg; -+ } -+ -+ sg->cpu_power = 0; -+ cpumask_copy(sched_group_cpus(sg), d->nodemask); -+ sg->next = sg; -+ cpumask_or(d->covered, d->covered, d->nodemask); -+ -+ prev = sg; -+ for (j = 0; j < nr_node_ids; j++) { -+ n = (num + j) % nr_node_ids; -+ cpumask_complement(d->notcovered, d->covered); -+ cpumask_and(d->tmpmask, d->notcovered, cpu_map); -+ cpumask_and(d->tmpmask, d->tmpmask, d->domainspan); -+ if (cpumask_empty(d->tmpmask)) -+ break; -+ cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n)); -+ if (cpumask_empty(d->tmpmask)) -+ continue; -+ sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), -+ GFP_KERNEL, num); -+ if (!sg) { -+ printk(KERN_WARNING -+ "Can not alloc domain group for node %d\n", j); -+ return -ENOMEM; -+ } -+ sg->cpu_power = 0; -+ cpumask_copy(sched_group_cpus(sg), d->tmpmask); -+ sg->next = prev->next; -+ cpumask_or(d->covered, d->covered, d->tmpmask); -+ prev->next = sg; -+ prev = sg; -+ } -+out: -+ return 0; -+} -+#endif /* CONFIG_NUMA */ -+ -+#ifdef CONFIG_NUMA -+/* Free memory allocated for various sched_group structures */ -+static void free_sched_groups(const struct cpumask *cpu_map, -+ struct cpumask *nodemask) -+{ -+ int cpu, i; -+ -+ for_each_cpu(cpu, cpu_map) { -+ struct sched_group **sched_group_nodes -+ = sched_group_nodes_bycpu[cpu]; -+ -+ if (!sched_group_nodes) -+ continue; -+ -+ for (i = 0; i < nr_node_ids; i++) { -+ struct sched_group *oldsg, *sg = sched_group_nodes[i]; -+ -+ cpumask_and(nodemask, cpumask_of_node(i), cpu_map); -+ if (cpumask_empty(nodemask)) -+ continue; -+ -+ if (sg == NULL) -+ continue; -+ sg = sg->next; -+next_sg: -+ oldsg = sg; -+ sg = sg->next; -+ kfree(oldsg); -+ if (oldsg != sched_group_nodes[i]) -+ goto next_sg; -+ } -+ kfree(sched_group_nodes); -+ sched_group_nodes_bycpu[cpu] = NULL; -+ } -+} -+#else /* !CONFIG_NUMA */ -+static void free_sched_groups(const struct cpumask *cpu_map, -+ struct cpumask *nodemask) -+{ -+} -+#endif /* CONFIG_NUMA */ -+ -+/* -+ * Initialise sched groups cpu_power. -+ * -+ * cpu_power indicates the capacity of sched group, which is used while -+ * distributing the load between different sched groups in a sched domain. -+ * Typically cpu_power for all the groups in a sched domain will be same unless -+ * there are asymmetries in the topology. If there are asymmetries, group -+ * having more cpu_power will pickup more load compared to the group having -+ * less cpu_power. -+ * -+ * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents -+ * the maximum number of tasks a group can handle in the presence of other idle -+ * or lightly loaded groups in the same sched domain. -+ */ -+static void init_sched_groups_power(int cpu, struct sched_domain *sd) -+{ -+ struct sched_domain *child; -+ struct sched_group *group; -+ long power; -+ int weight; -+ -+ WARN_ON(!sd || !sd->groups); -+ -+ if (cpu != group_first_cpu(sd->groups)) -+ return; -+ -+ sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); -+ -+ child = sd->child; -+ -+ sd->groups->cpu_power = 0; -+ -+ if (!child) { -+ power = SCHED_LOAD_SCALE; -+ weight = cpumask_weight(sched_domain_span(sd)); -+ /* -+ * SMT siblings share the power of a single core. -+ * Usually multiple threads get a better yield out of -+ * that one core than a single thread would have, -+ * reflect that in sd->smt_gain. -+ */ -+ if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { -+ power *= sd->smt_gain; -+ power /= weight; -+ power >>= SCHED_LOAD_SHIFT; -+ } -+ sd->groups->cpu_power += power; -+ return; -+ } -+ -+ /* -+ * Add cpu_power of each child group to this groups cpu_power -+ */ -+ group = child->groups; -+ do { -+ sd->groups->cpu_power += group->cpu_power; -+ group = group->next; -+ } while (group != child->groups); -+} -+ -+/* -+ * Initialisers for schedule domains -+ * Non-inlined to reduce accumulated stack pressure in build_sched_domains() -+ */ -+ -+#ifdef CONFIG_SCHED_DEBUG -+# define SD_INIT_NAME(sd, type) sd->name = #type -+#else -+# define SD_INIT_NAME(sd, type) do { } while (0) -+#endif -+ -+#define SD_INIT(sd, type) sd_init_##type(sd) -+ -+#define SD_INIT_FUNC(type) \ -+static noinline void sd_init_##type(struct sched_domain *sd) \ -+{ \ -+ memset(sd, 0, sizeof(*sd)); \ -+ *sd = SD_##type##_INIT; \ -+ sd->level = SD_LV_##type; \ -+ SD_INIT_NAME(sd, type); \ -+} -+ -+SD_INIT_FUNC(CPU) -+#ifdef CONFIG_NUMA -+ SD_INIT_FUNC(ALLNODES) -+ SD_INIT_FUNC(NODE) -+#endif -+#ifdef CONFIG_SCHED_SMT -+ SD_INIT_FUNC(SIBLING) -+#endif -+#ifdef CONFIG_SCHED_MC -+ SD_INIT_FUNC(MC) -+#endif -+#ifdef CONFIG_SCHED_BOOK -+ SD_INIT_FUNC(BOOK) -+#endif -+ -+static int default_relax_domain_level = -1; -+ -+static int __init setup_relax_domain_level(char *str) -+{ -+ unsigned long val; -+ -+ val = simple_strtoul(str, NULL, 0); -+ if (val < SD_LV_MAX) -+ default_relax_domain_level = val; -+ -+ return 1; -+} -+__setup("relax_domain_level=", setup_relax_domain_level); -+ -+static void set_domain_attribute(struct sched_domain *sd, -+ struct sched_domain_attr *attr) -+{ -+ int request; -+ -+ if (!attr || attr->relax_domain_level < 0) { -+ if (default_relax_domain_level < 0) -+ return; -+ else -+ request = default_relax_domain_level; -+ } else -+ request = attr->relax_domain_level; -+ if (request < sd->level) { -+ /* turn off idle balance on this domain */ -+ sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); -+ } else { -+ /* turn on idle balance on this domain */ -+ sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); -+ } -+} -+ -+static void __free_domain_allocs(struct s_data *d, enum s_alloc what, -+ const struct cpumask *cpu_map) -+{ -+ switch (what) { -+ case sa_sched_groups: -+ free_sched_groups(cpu_map, d->tmpmask); /* fall through */ -+ d->sched_group_nodes = NULL; -+ case sa_rootdomain: -+ free_rootdomain(d->rd); /* fall through */ -+ case sa_tmpmask: -+ free_cpumask_var(d->tmpmask); /* fall through */ -+ case sa_send_covered: -+ free_cpumask_var(d->send_covered); /* fall through */ -+ case sa_this_book_map: -+ free_cpumask_var(d->this_book_map); /* fall through */ -+ case sa_this_core_map: -+ free_cpumask_var(d->this_core_map); /* fall through */ -+ case sa_this_sibling_map: -+ free_cpumask_var(d->this_sibling_map); /* fall through */ -+ case sa_nodemask: -+ free_cpumask_var(d->nodemask); /* fall through */ -+ case sa_sched_group_nodes: -+#ifdef CONFIG_NUMA -+ kfree(d->sched_group_nodes); /* fall through */ -+ case sa_notcovered: -+ free_cpumask_var(d->notcovered); /* fall through */ -+ case sa_covered: -+ free_cpumask_var(d->covered); /* fall through */ -+ case sa_domainspan: -+ free_cpumask_var(d->domainspan); /* fall through */ -+#endif -+ case sa_none: -+ break; -+ } -+} -+ -+static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, -+ const struct cpumask *cpu_map) -+{ -+#ifdef CONFIG_NUMA -+ if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL)) -+ return sa_none; -+ if (!alloc_cpumask_var(&d->covered, GFP_KERNEL)) -+ return sa_domainspan; -+ if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL)) -+ return sa_covered; -+ /* Allocate the per-node list of sched groups */ -+ d->sched_group_nodes = kcalloc(nr_node_ids, -+ sizeof(struct sched_group *), GFP_KERNEL); -+ if (!d->sched_group_nodes) { -+ printk(KERN_WARNING "Can not alloc sched group node list\n"); -+ return sa_notcovered; -+ } -+ sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes; -+#endif -+ if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL)) -+ return sa_sched_group_nodes; -+ if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL)) -+ return sa_nodemask; -+ if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL)) -+ return sa_this_sibling_map; -+ if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL)) -+ return sa_this_core_map; -+ if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL)) -+ return sa_this_book_map; -+ if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL)) -+ return sa_send_covered; -+ d->rd = alloc_rootdomain(); -+ if (!d->rd) { -+ printk(KERN_WARNING "Cannot alloc root domain\n"); -+ return sa_tmpmask; -+ } -+ return sa_rootdomain; -+} -+ -+static struct sched_domain *__build_numa_sched_domains(struct s_data *d, -+ const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i) -+{ -+ struct sched_domain *sd = NULL; -+#ifdef CONFIG_NUMA -+ struct sched_domain *parent; -+ -+ d->sd_allnodes = 0; -+ if (cpumask_weight(cpu_map) > -+ SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) { -+ sd = &per_cpu(allnodes_domains, i).sd; -+ SD_INIT(sd, ALLNODES); -+ set_domain_attribute(sd, attr); -+ cpumask_copy(sched_domain_span(sd), cpu_map); -+ cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask); -+ d->sd_allnodes = 1; -+ } -+ parent = sd; -+ -+ sd = &per_cpu(node_domains, i).sd; -+ SD_INIT(sd, NODE); -+ set_domain_attribute(sd, attr); -+ sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); -+ sd->parent = parent; -+ if (parent) -+ parent->child = sd; -+ cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map); -+#endif -+ return sd; -+} -+ -+static struct sched_domain *__build_cpu_sched_domain(struct s_data *d, -+ const struct cpumask *cpu_map, struct sched_domain_attr *attr, -+ struct sched_domain *parent, int i) -+{ -+ struct sched_domain *sd; -+ sd = &per_cpu(phys_domains, i).sd; -+ SD_INIT(sd, CPU); -+ set_domain_attribute(sd, attr); -+ cpumask_copy(sched_domain_span(sd), d->nodemask); -+ sd->parent = parent; -+ if (parent) -+ parent->child = sd; -+ cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask); -+ return sd; -+} -+ -+static struct sched_domain *__build_book_sched_domain(struct s_data *d, -+ const struct cpumask *cpu_map, struct sched_domain_attr *attr, -+ struct sched_domain *parent, int i) -+{ -+ struct sched_domain *sd = parent; -+#ifdef CONFIG_SCHED_BOOK -+ sd = &per_cpu(book_domains, i).sd; -+ SD_INIT(sd, BOOK); -+ set_domain_attribute(sd, attr); -+ cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i)); -+ sd->parent = parent; -+ parent->child = sd; -+ cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask); -+#endif -+ return sd; -+} -+ -+static struct sched_domain *__build_mc_sched_domain(struct s_data *d, -+ const struct cpumask *cpu_map, struct sched_domain_attr *attr, -+ struct sched_domain *parent, int i) -+{ -+ struct sched_domain *sd = parent; -+#ifdef CONFIG_SCHED_MC -+ sd = &per_cpu(core_domains, i).sd; -+ SD_INIT(sd, MC); -+ set_domain_attribute(sd, attr); -+ cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i)); -+ sd->parent = parent; -+ parent->child = sd; -+ cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask); -+#endif -+ return sd; -+} -+ -+static struct sched_domain *__build_smt_sched_domain(struct s_data *d, -+ const struct cpumask *cpu_map, struct sched_domain_attr *attr, -+ struct sched_domain *parent, int i) -+{ -+ struct sched_domain *sd = parent; -+#ifdef CONFIG_SCHED_SMT -+ sd = &per_cpu(cpu_domains, i).sd; -+ SD_INIT(sd, SIBLING); -+ set_domain_attribute(sd, attr); -+ cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i)); -+ sd->parent = parent; -+ parent->child = sd; -+ cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask); -+#endif -+ return sd; -+} -+ -+static void build_sched_groups(struct s_data *d, enum sched_domain_level l, -+ const struct cpumask *cpu_map, int cpu) -+{ -+ switch (l) { -+#ifdef CONFIG_SCHED_SMT -+ case SD_LV_SIBLING: /* set up CPU (sibling) groups */ -+ cpumask_and(d->this_sibling_map, cpu_map, -+ topology_thread_cpumask(cpu)); -+ if (cpu == cpumask_first(d->this_sibling_map)) -+ init_sched_build_groups(d->this_sibling_map, cpu_map, -+ &cpu_to_cpu_group, -+ d->send_covered, d->tmpmask); -+ break; -+#endif -+#ifdef CONFIG_SCHED_MC -+ case SD_LV_MC: /* set up multi-core groups */ -+ cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu)); -+ if (cpu == cpumask_first(d->this_core_map)) -+ init_sched_build_groups(d->this_core_map, cpu_map, -+ &cpu_to_core_group, -+ d->send_covered, d->tmpmask); -+ break; -+#endif -+#ifdef CONFIG_SCHED_BOOK -+ case SD_LV_BOOK: /* set up book groups */ -+ cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu)); -+ if (cpu == cpumask_first(d->this_book_map)) -+ init_sched_build_groups(d->this_book_map, cpu_map, -+ &cpu_to_book_group, -+ d->send_covered, d->tmpmask); -+ break; -+#endif -+ case SD_LV_CPU: /* set up physical groups */ -+ cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map); -+ if (!cpumask_empty(d->nodemask)) -+ init_sched_build_groups(d->nodemask, cpu_map, -+ &cpu_to_phys_group, -+ d->send_covered, d->tmpmask); -+ break; -+#ifdef CONFIG_NUMA -+ case SD_LV_ALLNODES: -+ init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group, -+ d->send_covered, d->tmpmask); -+ break; -+#endif -+ default: -+ break; -+ } -+} -+ -+/* -+ * Build sched domains for a given set of cpus and attach the sched domains -+ * to the individual cpus -+ */ -+static int __build_sched_domains(const struct cpumask *cpu_map, -+ struct sched_domain_attr *attr) -+{ -+ enum s_alloc alloc_state = sa_none; -+ struct s_data d; -+ struct sched_domain *sd; -+ int i; -+#ifdef CONFIG_NUMA -+ d.sd_allnodes = 0; -+#endif -+ -+ alloc_state = __visit_domain_allocation_hell(&d, cpu_map); -+ if (alloc_state != sa_rootdomain) -+ goto error; -+ alloc_state = sa_sched_groups; -+ -+ /* -+ * Set up domains for cpus specified by the cpu_map. -+ */ -+ for_each_cpu(i, cpu_map) { -+ cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)), -+ cpu_map); -+ -+ sd = __build_numa_sched_domains(&d, cpu_map, attr, i); -+ sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i); -+ sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i); -+ sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i); -+ sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i); -+ } -+ -+ for_each_cpu(i, cpu_map) { -+ build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i); -+ build_sched_groups(&d, SD_LV_BOOK, cpu_map, i); -+ build_sched_groups(&d, SD_LV_MC, cpu_map, i); -+ } -+ -+ /* Set up physical groups */ -+ for (i = 0; i < nr_node_ids; i++) -+ build_sched_groups(&d, SD_LV_CPU, cpu_map, i); -+ -+#ifdef CONFIG_NUMA -+ /* Set up node groups */ -+ if (d.sd_allnodes) -+ build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0); -+ -+ for (i = 0; i < nr_node_ids; i++) -+ if (build_numa_sched_groups(&d, cpu_map, i)) -+ goto error; -+#endif -+ -+ /* Calculate CPU power for physical packages and nodes */ -+#ifdef CONFIG_SCHED_SMT -+ for_each_cpu(i, cpu_map) { -+ sd = &per_cpu(cpu_domains, i).sd; -+ init_sched_groups_power(i, sd); -+ } -+#endif -+#ifdef CONFIG_SCHED_MC -+ for_each_cpu(i, cpu_map) { -+ sd = &per_cpu(core_domains, i).sd; -+ init_sched_groups_power(i, sd); -+ } -+#endif -+#ifdef CONFIG_SCHED_BOOK -+ for_each_cpu(i, cpu_map) { -+ sd = &per_cpu(book_domains, i).sd; -+ init_sched_groups_power(i, sd); -+ } -+#endif -+ -+ for_each_cpu(i, cpu_map) { -+ sd = &per_cpu(phys_domains, i).sd; -+ init_sched_groups_power(i, sd); -+ } -+ -+#ifdef CONFIG_NUMA -+ for (i = 0; i < nr_node_ids; i++) -+ init_numa_sched_groups_power(d.sched_group_nodes[i]); -+ -+ if (d.sd_allnodes) { -+ struct sched_group *sg; -+ -+ cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, -+ d.tmpmask); -+ init_numa_sched_groups_power(sg); -+ } -+#endif -+ -+ /* Attach the domains */ -+ for_each_cpu(i, cpu_map) { -+#ifdef CONFIG_SCHED_SMT -+ sd = &per_cpu(cpu_domains, i).sd; -+#elif defined(CONFIG_SCHED_MC) -+ sd = &per_cpu(core_domains, i).sd; -+#elif defined(CONFIG_SCHED_BOOK) -+ sd = &per_cpu(book_domains, i).sd; -+#else -+ sd = &per_cpu(phys_domains, i).sd; -+#endif -+ cpu_attach_domain(sd, d.rd, i); -+ } -+ -+ d.sched_group_nodes = NULL; /* don't free this we still need it */ -+ __free_domain_allocs(&d, sa_tmpmask, cpu_map); -+ return 0; -+ -+error: -+ __free_domain_allocs(&d, alloc_state, cpu_map); -+ return -ENOMEM; -+} -+ -+static int build_sched_domains(const struct cpumask *cpu_map) -+{ -+ return __build_sched_domains(cpu_map, NULL); -+} -+ -+static cpumask_var_t *doms_cur; /* current sched domains */ -+static int ndoms_cur; /* number of sched domains in 'doms_cur' */ -+static struct sched_domain_attr *dattr_cur; -+ /* attribues of custom domains in 'doms_cur' */ -+ -+/* -+ * Special case: If a kmalloc of a doms_cur partition (array of -+ * cpumask) fails, then fallback to a single sched domain, -+ * as determined by the single cpumask fallback_doms. -+ */ -+static cpumask_var_t fallback_doms; -+ -+/* -+ * arch_update_cpu_topology lets virtualised architectures update the -+ * cpu core maps. It is supposed to return 1 if the topology changed -+ * or 0 if it stayed the same. -+ */ -+int __attribute__((weak)) arch_update_cpu_topology(void) -+{ -+ return 0; -+} -+ -+cpumask_var_t *alloc_sched_domains(unsigned int ndoms) -+{ -+ int i; -+ cpumask_var_t *doms; -+ -+ doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); -+ if (!doms) -+ return NULL; -+ for (i = 0; i < ndoms; i++) { -+ if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { -+ free_sched_domains(doms, i); -+ return NULL; -+ } -+ } -+ return doms; -+} -+ -+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) -+{ -+ unsigned int i; -+ for (i = 0; i < ndoms; i++) -+ free_cpumask_var(doms[i]); -+ kfree(doms); -+} -+ -+/* -+ * Set up scheduler domains and groups. Callers must hold the hotplug lock. -+ * For now this just excludes isolated cpus, but could be used to -+ * exclude other special cases in the future. -+ */ -+static int arch_init_sched_domains(const struct cpumask *cpu_map) -+{ -+ int err; -+ -+ arch_update_cpu_topology(); -+ ndoms_cur = 1; -+ doms_cur = alloc_sched_domains(ndoms_cur); -+ if (!doms_cur) -+ doms_cur = &fallback_doms; -+ cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); -+ dattr_cur = NULL; -+ err = build_sched_domains(doms_cur[0]); -+ register_sched_domain_sysctl(); -+ -+ return err; -+} -+ -+static void arch_destroy_sched_domains(const struct cpumask *cpu_map, -+ struct cpumask *tmpmask) -+{ -+ free_sched_groups(cpu_map, tmpmask); -+} -+ -+/* -+ * Detach sched domains from a group of cpus specified in cpu_map -+ * These cpus will now be attached to the NULL domain -+ */ -+static void detach_destroy_domains(const struct cpumask *cpu_map) -+{ -+ /* Save because hotplug lock held. */ -+ static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); -+ int i; -+ -+ for_each_cpu(i, cpu_map) -+ cpu_attach_domain(NULL, &def_root_domain, i); -+ synchronize_sched(); -+ arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); -+} -+ -+/* handle null as "default" */ -+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, -+ struct sched_domain_attr *new, int idx_new) -+{ -+ struct sched_domain_attr tmp; -+ -+ /* fast path */ -+ if (!new && !cur) -+ return 1; -+ -+ tmp = SD_ATTR_INIT; -+ return !memcmp(cur ? (cur + idx_cur) : &tmp, -+ new ? (new + idx_new) : &tmp, -+ sizeof(struct sched_domain_attr)); -+} -+ -+/* -+ * Partition sched domains as specified by the 'ndoms_new' -+ * cpumasks in the array doms_new[] of cpumasks. This compares -+ * doms_new[] to the current sched domain partitioning, doms_cur[]. -+ * It destroys each deleted domain and builds each new domain. -+ * -+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. -+ * The masks don't intersect (don't overlap.) We should setup one -+ * sched domain for each mask. CPUs not in any of the cpumasks will -+ * not be load balanced. If the same cpumask appears both in the -+ * current 'doms_cur' domains and in the new 'doms_new', we can leave -+ * it as it is. -+ * -+ * The passed in 'doms_new' should be allocated using -+ * alloc_sched_domains. This routine takes ownership of it and will -+ * free_sched_domains it when done with it. If the caller failed the -+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, -+ * and partition_sched_domains() will fallback to the single partition -+ * 'fallback_doms', it also forces the domains to be rebuilt. -+ * -+ * If doms_new == NULL it will be replaced with cpu_online_mask. -+ * ndoms_new == 0 is a special case for destroying existing domains, -+ * and it will not create the default domain. -+ * -+ * Call with hotplug lock held -+ */ -+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], -+ struct sched_domain_attr *dattr_new) -+{ -+ int i, j, n; -+ int new_topology; -+ -+ mutex_lock(&sched_domains_mutex); -+ -+ /* always unregister in case we don't destroy any domains */ -+ unregister_sched_domain_sysctl(); -+ -+ /* Let architecture update cpu core mappings. */ -+ new_topology = arch_update_cpu_topology(); -+ -+ n = doms_new ? ndoms_new : 0; -+ -+ /* Destroy deleted domains */ -+ 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)) -+ goto match1; -+ } -+ /* no match - a current sched domain not in new doms_new[] */ -+ detach_destroy_domains(doms_cur[i]); -+match1: -+ ; -+ } -+ -+ if (doms_new == NULL) { -+ ndoms_cur = 0; -+ doms_new = &fallback_doms; -+ cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); -+ WARN_ON_ONCE(dattr_new); -+ } -+ -+ /* Build new domains */ -+ for (i = 0; i < ndoms_new; i++) { -+ for (j = 0; j < ndoms_cur && !new_topology; j++) { -+ if (cpumask_equal(doms_new[i], doms_cur[j]) -+ && dattrs_equal(dattr_new, i, dattr_cur, j)) -+ goto match2; -+ } -+ /* no match - add a new doms_new */ -+ __build_sched_domains(doms_new[i], -+ dattr_new ? dattr_new + i : NULL); -+match2: -+ ; -+ } -+ -+ /* Remember the new sched domains */ -+ if (doms_cur != &fallback_doms) -+ free_sched_domains(doms_cur, ndoms_cur); -+ kfree(dattr_cur); /* kfree(NULL) is safe */ -+ doms_cur = doms_new; -+ dattr_cur = dattr_new; -+ ndoms_cur = ndoms_new; -+ -+ register_sched_domain_sysctl(); -+ -+ mutex_unlock(&sched_domains_mutex); -+} -+ -+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -+static void arch_reinit_sched_domains(void) -+{ -+ get_online_cpus(); -+ -+ /* Destroy domains first to force the rebuild */ -+ partition_sched_domains(0, NULL, NULL); -+ -+ rebuild_sched_domains(); -+ put_online_cpus(); -+} -+ -+static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) -+{ -+ unsigned int level = 0; -+ -+ if (sscanf(buf, "%u", &level) != 1) -+ return -EINVAL; -+ -+ /* -+ * level is always be positive so don't check for -+ * level < POWERSAVINGS_BALANCE_NONE which is 0 -+ * What happens on 0 or 1 byte write, -+ * need to check for count as well? -+ */ -+ -+ if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) -+ return -EINVAL; -+ -+ if (smt) -+ sched_smt_power_savings = level; -+ else -+ sched_mc_power_savings = level; -+ -+ arch_reinit_sched_domains(); -+ -+ return count; -+} -+ -+#ifdef CONFIG_SCHED_MC -+static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, -+ struct sysdev_class_attribute *attr, -+ char *page) -+{ -+ return sprintf(page, "%u\n", sched_mc_power_savings); -+} -+static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, -+ struct sysdev_class_attribute *attr, -+ const char *buf, size_t count) -+{ -+ return sched_power_savings_store(buf, count, 0); -+} -+static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, -+ sched_mc_power_savings_show, -+ sched_mc_power_savings_store); -+#endif -+ -+#ifdef CONFIG_SCHED_SMT -+static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, -+ struct sysdev_class_attribute *attr, -+ char *page) -+{ -+ return sprintf(page, "%u\n", sched_smt_power_savings); -+} -+static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, -+ struct sysdev_class_attribute *attr, -+ const char *buf, size_t count) -+{ -+ return sched_power_savings_store(buf, count, 1); -+} -+static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, -+ sched_smt_power_savings_show, -+ sched_smt_power_savings_store); -+#endif -+ -+int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) -+{ -+ int err = 0; -+ -+#ifdef CONFIG_SCHED_SMT -+ if (smt_capable()) -+ err = sysfs_create_file(&cls->kset.kobj, -+ &attr_sched_smt_power_savings.attr); -+#endif -+#ifdef CONFIG_SCHED_MC -+ if (!err && mc_capable()) -+ err = sysfs_create_file(&cls->kset.kobj, -+ &attr_sched_mc_power_savings.attr); -+#endif -+ return err; -+} -+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -+ -+/* -+ * Update cpusets according to cpu_active mask. If cpusets are -+ * disabled, cpuset_update_active_cpus() becomes a simple wrapper -+ * around partition_sched_domains(). -+ */ -+static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, -+ void *hcpu) -+{ -+ switch (action & ~CPU_TASKS_FROZEN) { -+ case CPU_ONLINE: -+ case CPU_DOWN_FAILED: -+ cpuset_update_active_cpus(); -+ return NOTIFY_OK; -+ default: -+ return NOTIFY_DONE; -+ } -+} -+ -+static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, -+ void *hcpu) -+{ -+ switch (action & ~CPU_TASKS_FROZEN) { -+ case CPU_DOWN_PREPARE: -+ cpuset_update_active_cpus(); -+ return NOTIFY_OK; -+ default: -+ return NOTIFY_DONE; -+ } -+} -+ -+static int update_runtime(struct notifier_block *nfb, -+ unsigned long action, void *hcpu) -+{ -+ switch (action) { -+ case CPU_DOWN_PREPARE: -+ case CPU_DOWN_PREPARE_FROZEN: -+ return NOTIFY_OK; -+ -+ case CPU_DOWN_FAILED: -+ case CPU_DOWN_FAILED_FROZEN: -+ case CPU_ONLINE: -+ case CPU_ONLINE_FROZEN: -+ return NOTIFY_OK; -+ -+ default: -+ return NOTIFY_DONE; -+ } -+} -+ -+#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC) -+/* -+ * Cheaper version of the below functions in case support for SMT and MC is -+ * compiled in but CPUs have no siblings. -+ */ -+static int sole_cpu_idle(unsigned long cpu) -+{ -+ return rq_idle(cpu_rq(cpu)); -+} -+#endif -+#ifdef CONFIG_SCHED_SMT -+/* All this CPU's SMT siblings are idle */ -+static int siblings_cpu_idle(unsigned long cpu) -+{ -+ return cpumask_subset(&(cpu_rq(cpu)->smt_siblings), -+ &grq.cpu_idle_map); -+} -+#endif -+#ifdef CONFIG_SCHED_MC -+/* All this CPU's shared cache siblings are idle */ -+static int cache_cpu_idle(unsigned long cpu) -+{ -+ return cpumask_subset(&(cpu_rq(cpu)->cache_siblings), -+ &grq.cpu_idle_map); -+} -+#endif -+ -+void __init sched_init_smp(void) -+{ -+ struct sched_domain *sd; -+ int cpu, cpus; -+ -+ cpumask_var_t non_isolated_cpus; -+ -+ alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); -+ alloc_cpumask_var(&fallback_doms, GFP_KERNEL); -+ -+#if defined(CONFIG_NUMA) -+ sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), -+ GFP_KERNEL); -+ BUG_ON(sched_group_nodes_bycpu == NULL); -+#endif -+ get_online_cpus(); -+ mutex_lock(&sched_domains_mutex); -+ arch_init_sched_domains(cpu_active_mask); -+ cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); -+ if (cpumask_empty(non_isolated_cpus)) -+ cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); -+ mutex_unlock(&sched_domains_mutex); -+ put_online_cpus(); -+ -+ hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); -+ hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); -+ -+ /* RT runtime code needs to handle some hotplug events */ -+ hotcpu_notifier(update_runtime, 0); -+ -+ /* Move init over to a non-isolated CPU */ -+ if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) -+ BUG(); -+ free_cpumask_var(non_isolated_cpus); -+ -+ /* -+ * Assume that every added cpu gives us slightly less overall latency -+ * allowing us to increase the base rr_interval, non-linearly and with -+ * an upper bound. -+ */ -+ cpus = num_online_cpus(); -+ rr_interval = rr_interval * (4 * cpus + 4) / (cpus + 6); -+ -+ grq_lock_irq(); -+ /* -+ * Set up the relative cache distance of each online cpu from each -+ * other in a simple array for quick lookup. Locality is determined -+ * by the closest sched_domain that CPUs are separated by. CPUs with -+ * shared cache in SMT and MC are treated as local. Separate CPUs -+ * (within the same package or physically) within the same node are -+ * treated as not local. CPUs not even in the same domain (different -+ * nodes) are treated as very distant. -+ */ -+ for_each_online_cpu(cpu) { -+ struct rq *rq = cpu_rq(cpu); -+ for_each_domain(cpu, sd) { -+ unsigned long locality; -+ int other_cpu; -+ -+#ifdef CONFIG_SCHED_SMT -+ if (sd->level == SD_LV_SIBLING) { -+ for_each_cpu_mask(other_cpu, *sched_domain_span(sd)) -+ cpumask_set_cpu(other_cpu, &rq->smt_siblings); -+ } -+#endif -+#ifdef CONFIG_SCHED_MC -+ if (sd->level == SD_LV_MC) { -+ for_each_cpu_mask(other_cpu, *sched_domain_span(sd)) -+ cpumask_set_cpu(other_cpu, &rq->cache_siblings); -+ } -+#endif -+ if (sd->level <= SD_LV_SIBLING) -+ locality = 1; -+ else if (sd->level <= SD_LV_MC) -+ locality = 2; -+ else if (sd->level <= SD_LV_NODE) -+ locality = 3; -+ else -+ continue; -+ -+ for_each_cpu_mask(other_cpu, *sched_domain_span(sd)) { -+ if (locality < rq->cpu_locality[other_cpu]) -+ rq->cpu_locality[other_cpu] = locality; -+ } -+ } -+ -+/* -+ * Each runqueue has its own function in case it doesn't have -+ * siblings of its own allowing mixed topologies. -+ */ -+#ifdef CONFIG_SCHED_SMT -+ if (cpus_weight(rq->smt_siblings) > 1) -+ rq->siblings_idle = siblings_cpu_idle; -+#endif -+#ifdef CONFIG_SCHED_MC -+ if (cpus_weight(rq->cache_siblings) > 1) -+ rq->cache_idle = cache_cpu_idle; -+#endif -+ } -+ grq_unlock_irq(); -+} -+#else -+void __init sched_init_smp(void) -+{ -+} -+#endif /* CONFIG_SMP */ -+ -+unsigned int sysctl_timer_migration = 1; -+ -+int in_sched_functions(unsigned long addr) -+{ -+ return in_lock_functions(addr) || -+ (addr >= (unsigned long)__sched_text_start -+ && addr < (unsigned long)__sched_text_end); -+} -+ -+void __init sched_init(void) -+{ -+ int i; -+ struct rq *rq; -+ -+ prio_ratios[0] = 128; -+ for (i = 1 ; i < PRIO_RANGE ; i++) -+ prio_ratios[i] = prio_ratios[i - 1] * 11 / 10; -+ -+ raw_spin_lock_init(&grq.lock); -+ grq.nr_running = grq.nr_uninterruptible = grq.nr_switches = 0; -+ grq.niffies = 0; -+ grq.last_jiffy = jiffies; -+ raw_spin_lock_init(&grq.iso_lock); -+ grq.iso_ticks = grq.iso_refractory = 0; -+#ifdef CONFIG_SMP -+ init_defrootdomain(); -+ grq.qnr = grq.idle_cpus = 0; -+ cpumask_clear(&grq.cpu_idle_map); -+#else -+ uprq = &per_cpu(runqueues, 0); -+#endif -+ for_each_possible_cpu(i) { -+ rq = cpu_rq(i); -+ rq->user_pc = rq->nice_pc = rq->softirq_pc = rq->system_pc = -+ rq->iowait_pc = rq->idle_pc = 0; -+ rq->dither = 0; -+#ifdef CONFIG_SMP -+ rq->last_niffy = 0; -+ rq->sd = NULL; -+ rq->rd = NULL; -+ rq->online = 0; -+ rq->cpu = i; -+ rq_attach_root(rq, &def_root_domain); -+#endif -+ atomic_set(&rq->nr_iowait, 0); -+ } -+ -+#ifdef CONFIG_SMP -+ nr_cpu_ids = i; -+ /* -+ * Set the base locality for cpu cache distance calculation to -+ * "distant" (3). Make sure the distance from a CPU to itself is 0. -+ */ -+ for_each_possible_cpu(i) { -+ int j; -+ -+ rq = cpu_rq(i); -+#ifdef CONFIG_SCHED_SMT -+ cpumask_clear(&rq->smt_siblings); -+ cpumask_set_cpu(i, &rq->smt_siblings); -+ rq->siblings_idle = sole_cpu_idle; -+ cpumask_set_cpu(i, &rq->smt_siblings); -+#endif -+#ifdef CONFIG_SCHED_MC -+ cpumask_clear(&rq->cache_siblings); -+ cpumask_set_cpu(i, &rq->cache_siblings); -+ rq->cache_idle = sole_cpu_idle; -+ cpumask_set_cpu(i, &rq->cache_siblings); -+#endif -+ rq->cpu_locality = kmalloc(nr_cpu_ids * sizeof(unsigned long), -+ GFP_NOWAIT); -+ for_each_possible_cpu(j) { -+ if (i == j) -+ rq->cpu_locality[j] = 0; -+ else -+ rq->cpu_locality[j] = 4; -+ } -+ } -+#endif -+ -+ for (i = 0; i < PRIO_LIMIT; i++) -+ INIT_LIST_HEAD(grq.queue + i); -+ /* delimiter for bitsearch */ -+ __set_bit(PRIO_LIMIT, grq.prio_bitmap); -+ -+#ifdef CONFIG_PREEMPT_NOTIFIERS -+ INIT_HLIST_HEAD(&init_task.preempt_notifiers); -+#endif -+ -+#ifdef CONFIG_RT_MUTEXES -+ plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock); -+#endif -+ -+ /* -+ * The boot idle thread does lazy MMU switching as well: -+ */ -+ atomic_inc(&init_mm.mm_count); -+ enter_lazy_tlb(&init_mm, current); -+ -+ /* -+ * Make us the idle thread. Technically, schedule() should not be -+ * called from this thread, however somewhere below it might be, -+ * but because we are the idle thread, we just pick up running again -+ * when this runqueue becomes "idle". -+ */ -+ init_idle(current, smp_processor_id()); -+ -+ /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ -+ zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); -+#ifdef CONFIG_SMP -+ /* May be allocated at isolcpus cmdline parse time */ -+ if (cpu_isolated_map == NULL) -+ zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); -+#endif /* SMP */ -+ perf_event_init(); -+} -+ -+#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP -+static inline int preempt_count_equals(int preempt_offset) -+{ -+ int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); -+ -+ return (nested == PREEMPT_INATOMIC_BASE + preempt_offset); -+} -+ -+void __might_sleep(const char *file, int line, int preempt_offset) -+{ -+#ifdef in_atomic -+ static unsigned long prev_jiffy; /* ratelimiting */ -+ -+ if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || -+ system_state != SYSTEM_RUNNING || oops_in_progress) -+ return; -+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) -+ return; -+ prev_jiffy = jiffies; -+ -+ printk(KERN_ERR -+ "BUG: sleeping function called from invalid context at %s:%d\n", -+ file, line); -+ printk(KERN_ERR -+ "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", -+ in_atomic(), irqs_disabled(), -+ current->pid, current->comm); -+ -+ debug_show_held_locks(current); -+ if (irqs_disabled()) -+ print_irqtrace_events(current); -+ dump_stack(); -+#endif -+} -+EXPORT_SYMBOL(__might_sleep); -+#endif -+ -+#ifdef CONFIG_MAGIC_SYSRQ -+void normalize_rt_tasks(void) -+{ -+ struct task_struct *g, *p; -+ unsigned long flags; -+ struct rq *rq; -+ int queued; -+ -+ read_lock_irq(&tasklist_lock); -+ -+ do_each_thread(g, p) { -+ if (!rt_task(p) && !iso_task(p)) -+ continue; -+ -+ raw_spin_lock_irqsave(&p->pi_lock, flags); -+ rq = __task_grq_lock(p); -+ -+ queued = task_queued(p); -+ if (queued) -+ dequeue_task(p); -+ __setscheduler(p, rq, SCHED_NORMAL, 0); -+ if (queued) { -+ enqueue_task(p); -+ try_preempt(p, rq); -+ } -+ -+ __task_grq_unlock(); -+ raw_spin_unlock_irqrestore(&p->pi_lock, flags); -+ } while_each_thread(g, p); -+ -+ read_unlock_irq(&tasklist_lock); -+} -+#endif /* CONFIG_MAGIC_SYSRQ */ -+ -+#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) -+/* -+ * These functions are only useful for the IA64 MCA handling, or kdb. -+ * -+ * They can only be called when the whole system has been -+ * stopped - every CPU needs to be quiescent, and no scheduling -+ * activity can take place. Using them for anything else would -+ * be a serious bug, and as a result, they aren't even visible -+ * under any other configuration. -+ */ -+ -+/** -+ * curr_task - return the current task for a given cpu. -+ * @cpu: the processor in question. -+ * -+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! -+ */ -+struct task_struct *curr_task(int cpu) -+{ -+ return cpu_curr(cpu); -+} -+ -+#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ -+ -+#ifdef CONFIG_IA64 -+/** -+ * set_curr_task - set the current task for a given cpu. -+ * @cpu: the processor in question. -+ * @p: the task pointer to set. -+ * -+ * Description: This function must only be used when non-maskable interrupts -+ * are serviced on a separate stack. It allows the architecture to switch the -+ * notion of the current task on a cpu in a non-blocking manner. This function -+ * must be called with all CPU's synchronised, and interrupts disabled, the -+ * and caller must save the original value of the current task (see -+ * curr_task() above) and restore that value before reenabling interrupts and -+ * re-starting the system. -+ * -+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! -+ */ -+void set_curr_task(int cpu, struct task_struct *p) -+{ -+ cpu_curr(cpu) = p; -+} -+ -+#endif -+ -+/* -+ * Use precise platform statistics if available: -+ */ -+#ifdef CONFIG_VIRT_CPU_ACCOUNTING -+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -+{ -+ *ut = p->utime; -+ *st = p->stime; -+} -+ -+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -+{ -+ struct task_cputime cputime; -+ -+ thread_group_cputime(p, &cputime); -+ -+ *ut = cputime.utime; -+ *st = cputime.stime; -+} -+#else -+ -+#ifndef nsecs_to_cputime -+# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) -+#endif -+ -+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -+{ -+ cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); -+ -+ rtime = nsecs_to_cputime(p->sched_time); -+ -+ if (total) { -+ u64 temp; -+ -+ temp = (u64)(rtime * utime); -+ do_div(temp, total); -+ utime = (cputime_t)temp; -+ } else -+ utime = rtime; -+ -+ /* -+ * Compare with previous values, to keep monotonicity: -+ */ -+ p->prev_utime = max(p->prev_utime, utime); -+ p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); -+ -+ *ut = p->prev_utime; -+ *st = p->prev_stime; -+} -+ -+/* -+ * Must be called with siglock held. -+ */ -+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -+{ -+ struct signal_struct *sig = p->signal; -+ struct task_cputime cputime; -+ cputime_t rtime, utime, total; -+ -+ thread_group_cputime(p, &cputime); -+ -+ total = cputime_add(cputime.utime, cputime.stime); -+ rtime = nsecs_to_cputime(cputime.sum_exec_runtime); -+ -+ if (total) { -+ u64 temp; -+ -+ temp = (u64)(rtime * cputime.utime); -+ do_div(temp, total); -+ utime = (cputime_t)temp; -+ } else -+ utime = rtime; -+ -+ sig->prev_utime = max(sig->prev_utime, utime); -+ sig->prev_stime = max(sig->prev_stime, -+ cputime_sub(rtime, sig->prev_utime)); -+ -+ *ut = sig->prev_utime; -+ *st = sig->prev_stime; -+} -+#endif -+ -+inline cputime_t task_gtime(struct task_struct *p) -+{ -+ return p->gtime; -+} -+ -+void __cpuinit init_idle_bootup_task(struct task_struct *idle) -+{} -+ -+#ifdef CONFIG_SCHED_DEBUG -+void proc_sched_show_task(struct task_struct *p, struct seq_file *m) -+{} -+ -+void proc_sched_set_task(struct task_struct *p) -+{} -+#endif -+ -+/* No RCU torture test support */ -+void synchronize_sched_expedited(void) -+{ -+ barrier(); -+} -+EXPORT_SYMBOL_GPL(synchronize_sched_expedited); -+ -+#ifdef CONFIG_SMP -+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) -+{ -+ return SCHED_LOAD_SCALE; -+} -+ -+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) -+{ -+ unsigned long weight = cpumask_weight(sched_domain_span(sd)); -+ unsigned long smt_gain = sd->smt_gain; -+ -+ smt_gain /= weight; -+ -+ return smt_gain; -+} -+#endif -Index: linux-2.6.37-ck2/kernel/sched.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/sched.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/kernel/sched.c 2011-02-14 09:47:50.994252001 +1100 -@@ -1,3 +1,6 @@ -+#ifdef CONFIG_SCHED_BFS -+#include "sched_bfs.c" -+#else - /* - * kernel/sched.c - * -@@ -9603,3 +9606,4 @@ - EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - - #endif /* #else #ifndef CONFIG_SMP */ -+#endif /* CONFIG_SCHED_BFS */ -Index: linux-2.6.37-ck2/kernel/sysctl.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/sysctl.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/kernel/sysctl.c 2011-02-14 09:47:50.995252001 +1100 -@@ -117,7 +117,12 @@ - static int __maybe_unused one = 1; - static int __maybe_unused two = 2; - static unsigned long one_ul = 1; --static int one_hundred = 100; -+static int __maybe_unused one_hundred = 100; -+#ifdef CONFIG_SCHED_BFS -+extern int rr_interval; -+extern int sched_iso_cpu; -+static int __read_mostly one_thousand = 1000; -+#endif - #ifdef CONFIG_PRINTK - static int ten_thousand = 10000; - #endif -@@ -252,7 +257,7 @@ - { } - }; - --#ifdef CONFIG_SCHED_DEBUG -+#if defined(CONFIG_SCHED_DEBUG) && !defined(CONFIG_SCHED_BFS) - static int min_sched_granularity_ns = 100000; /* 100 usecs */ - static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ - static int min_wakeup_granularity_ns; /* 0 usecs */ -@@ -269,6 +274,7 @@ - #endif - - static struct ctl_table kern_table[] = { -+#ifndef CONFIG_SCHED_BFS - { - .procname = "sched_child_runs_first", - .data = &sysctl_sched_child_runs_first, -@@ -382,6 +388,7 @@ - .mode = 0644, - .proc_handler = proc_dointvec, - }, -+#endif /* !CONFIG_SCHED_BFS */ - #ifdef CONFIG_PROVE_LOCKING - { - .procname = "prove_locking", -@@ -815,6 +822,26 @@ - .proc_handler = proc_dointvec, - }, - #endif -+#ifdef CONFIG_SCHED_BFS -+ { -+ .procname = "rr_interval", -+ .data = &rr_interval, -+ .maxlen = sizeof (int), -+ .mode = 0644, -+ .proc_handler = &proc_dointvec_minmax, -+ .extra1 = &one, -+ .extra2 = &one_thousand, -+ }, -+ { -+ .procname = "iso_cpu", -+ .data = &sched_iso_cpu, -+ .maxlen = sizeof (int), -+ .mode = 0644, -+ .proc_handler = &proc_dointvec_minmax, -+ .extra1 = &zero, -+ .extra2 = &one_hundred, -+ }, -+#endif - #if defined(CONFIG_S390) && defined(CONFIG_SMP) - { - .procname = "spin_retry", -Index: linux-2.6.37-ck2/lib/Kconfig.debug -=================================================================== ---- linux-2.6.37-ck2.orig/lib/Kconfig.debug 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/lib/Kconfig.debug 2011-02-14 09:47:50.995252001 +1100 -@@ -833,7 +833,7 @@ - - config RCU_TORTURE_TEST - tristate "torture tests for RCU" -- depends on DEBUG_KERNEL -+ depends on DEBUG_KERNEL && !SCHED_BFS - default n - help - This option provides a kernel module that runs torture tests -Index: linux-2.6.37-ck2/include/linux/jiffies.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/jiffies.h 2010-02-25 21:51:52.000000000 +1100 -+++ linux-2.6.37-ck2/include/linux/jiffies.h 2011-02-14 09:47:50.995252001 +1100 -@@ -164,7 +164,7 @@ - * Have the 32 bit jiffies value wrap 5 minutes after boot - * so jiffies wrap bugs show up earlier. - */ --#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) -+#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-10*HZ)) - - /* - * Change timeval to jiffies, trying to avoid the diff --git a/packages/linux/patches/linux-2.6.38-rc8-702_2637-bfs363-nonhotplug_fix.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-702_2637-bfs363-nonhotplug_fix.patch.disabled deleted file mode 100644 index 59b401dea6..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-702_2637-bfs363-nonhotplug_fix.patch.disabled +++ /dev/null @@ -1,60 +0,0 @@ -Fix a failure to build if CPU hotplug is disabled with BFS. - --ck - ---- - kernel/sched_bfs.c | 34 +++++++++++++++++----------------- - 1 file changed, 17 insertions(+), 17 deletions(-) - -Index: linux-2.6.37-ck2/kernel/sched_bfs.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/sched_bfs.c 2011-02-14 09:50:24.351252002 +1100 -+++ linux-2.6.37-ck2/kernel/sched_bfs.c 2011-02-14 09:53:53.820252000 +1100 -@@ -4812,6 +4812,23 @@ - grq_unlock_irqrestore(&flags); - } - -+/* -+ * Ensures that the idle task is using init_mm right before its cpu goes -+ * offline. -+ */ -+void idle_task_exit(void) -+{ -+ struct mm_struct *mm = current->active_mm; -+ -+ BUG_ON(cpu_online(smp_processor_id())); -+ -+ if (mm != &init_mm) -+ switch_mm(mm, &init_mm, current); -+ mmdrop(mm); -+} -+ -+#endif /* CONFIG_HOTPLUG_CPU */ -+ - void sched_set_stop_task(int cpu, struct task_struct *stop) - { - struct sched_param stop_param = { .sched_priority = STOP_PRIO }; -@@ -4841,23 +4858,6 @@ - } - } - --/* -- * Ensures that the idle task is using init_mm right before its cpu goes -- * offline. -- */ --void idle_task_exit(void) --{ -- struct mm_struct *mm = current->active_mm; -- -- BUG_ON(cpu_online(smp_processor_id())); -- -- if (mm != &init_mm) -- switch_mm(mm, &init_mm, current); -- mmdrop(mm); --} -- --#endif /* CONFIG_HOTPLUG_CPU */ -- - #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) - - static struct ctl_table sd_ctl_dir[] = { diff --git a/packages/linux/patches/linux-2.6.38-rc8-702_ck2-version.patch b/packages/linux/patches/linux-2.6.38-rc8-702_ck2-version.patch deleted file mode 100644 index 4f34a3ebed..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-702_ck2-version.patch +++ /dev/null @@ -1,19 +0,0 @@ ---- - Makefile | 4 ++++ - 1 file changed, 4 insertions(+) - -Index: linux-2.6.37-ck2/Makefile -=================================================================== ---- linux-2.6.37-ck2.orig/Makefile 2011-01-06 14:04:07.000000000 +1100 -+++ linux-2.6.37-ck2/Makefile 2011-02-14 10:11:20.469252000 +1100 -@@ -10,6 +10,10 @@ - # Comments in this file are targeted only to the developer, do not - # expect to learn how to build the kernel reading this file. - -+CKVERSION = -ck2 -+CKNAME = BFS Powered -+EXTRAVERSION := $(EXTRAVERSION)$(CKVERSION) -+ - # Do not: - # o use make's built-in rules and variables - # (this increases performance and avoids hard-to-debug behaviour); diff --git a/packages/linux/patches/linux-2.6.38-rc8-703_cpufreq-bfs_tweaks.patch b/packages/linux/patches/linux-2.6.38-rc8-703_cpufreq-bfs_tweaks.patch deleted file mode 100644 index fc0122e323..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-703_cpufreq-bfs_tweaks.patch +++ /dev/null @@ -1,37 +0,0 @@ ---- - drivers/cpufreq/cpufreq_ondemand.c | 10 +++++----- - 1 file changed, 5 insertions(+), 5 deletions(-) - -Index: linux-2.6.37-ck2/drivers/cpufreq/cpufreq_ondemand.c -=================================================================== ---- linux-2.6.37-ck2.orig/drivers/cpufreq/cpufreq_ondemand.c 2011-01-06 14:04:08.000000000 +1100 -+++ linux-2.6.37-ck2/drivers/cpufreq/cpufreq_ondemand.c 2011-02-14 10:11:11.438252001 +1100 -@@ -28,12 +28,12 @@ - * It helps to keep variable names smaller, simpler - */ - --#define DEF_FREQUENCY_DOWN_DIFFERENTIAL (10) --#define DEF_FREQUENCY_UP_THRESHOLD (80) -+#define DEF_FREQUENCY_DOWN_DIFFERENTIAL (17) -+#define DEF_FREQUENCY_UP_THRESHOLD (63) - #define DEF_SAMPLING_DOWN_FACTOR (1) - #define MAX_SAMPLING_DOWN_FACTOR (100000) - #define MICRO_FREQUENCY_DOWN_DIFFERENTIAL (3) --#define MICRO_FREQUENCY_UP_THRESHOLD (95) -+#define MICRO_FREQUENCY_UP_THRESHOLD (80) - #define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000) - #define MIN_FREQUENCY_UP_THRESHOLD (11) - #define MAX_FREQUENCY_UP_THRESHOLD (100) -@@ -513,10 +513,10 @@ - - /* - * Every sampling_rate, we check, if current idle time is less -- * than 20% (default), then we try to increase frequency -+ * than 37% (default), then we try to increase frequency - * Every sampling_rate, we look for a the lowest - * frequency which can sustain the load while keeping idle time over -- * 30%. If such a frequency exist, we try to decrease to this frequency. -+ * 50%. If such a frequency exist, we try to decrease to this frequency. - * - * Any frequency increase takes it to the maximum frequency. - * Frequency reduction happens at minimum steps of diff --git a/packages/linux/patches/linux-2.6.38-rc8-704_hz-default_1000.patch b/packages/linux/patches/linux-2.6.38-rc8-704_hz-default_1000.patch deleted file mode 100644 index 5af5138068..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-704_hz-default_1000.patch +++ /dev/null @@ -1,17 +0,0 @@ ---- - kernel/Kconfig.hz | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - -Index: linux-2.6.37-ck2/kernel/Kconfig.hz -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/Kconfig.hz 2009-06-10 13:05:27.000000000 +1000 -+++ linux-2.6.37-ck2/kernel/Kconfig.hz 2011-02-14 10:11:10.474252000 +1100 -@@ -4,7 +4,7 @@ - - choice - prompt "Timer frequency" -- default HZ_250 -+ default HZ_1000 - help - Allows the configuration of the timer frequency. It is customary - to have the timer interrupt run at 1000 Hz but 100 Hz may be more diff --git a/packages/linux/patches/linux-2.6.38-rc8-705_hz-no_default_250.patch b/packages/linux/patches/linux-2.6.38-rc8-705_hz-no_default_250.patch deleted file mode 100644 index 051075471a..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-705_hz-no_default_250.patch +++ /dev/null @@ -1,47 +0,0 @@ ---- - kernel/Kconfig.hz | 17 ++++++++++------- - 1 file changed, 10 insertions(+), 7 deletions(-) - -Index: linux-2.6.37-ck2/kernel/Kconfig.hz -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/Kconfig.hz 2011-02-14 10:11:10.474252000 +1100 -+++ linux-2.6.37-ck2/kernel/Kconfig.hz 2011-02-14 10:11:10.702252000 +1100 -@@ -23,13 +23,14 @@ - with lots of processors that may show reduced performance if - too many timer interrupts are occurring. - -- config HZ_250 -+ config HZ_250_NODEFAULT - bool "250 HZ" - help -- 250 Hz is a good compromise choice allowing server performance -- while also showing good interactive responsiveness even -- on SMP and NUMA systems. If you are going to be using NTSC video -- or multimedia, selected 300Hz instead. -+ 250 HZ is a lousy compromise choice allowing server interactivity -+ while also showing desktop throughput and no extra power saving on -+ laptops. No good for anything. -+ -+ Recommend 100 or 1000 instead. - - config HZ_300 - bool "300 HZ" -@@ -43,14 +44,16 @@ - bool "1000 HZ" - help - 1000 Hz is the preferred choice for desktop systems and other -- systems requiring fast interactive responses to events. -+ systems requiring fast interactive responses to events. Laptops -+ can also benefit from this choice without sacrificing battery life -+ if dynticks is also enabled. - - endchoice - - config HZ - int - default 100 if HZ_100 -- default 250 if HZ_250 -+ default 250 if HZ_250_NODEFAULT - default 300 if HZ_300 - default 1000 if HZ_1000 - diff --git a/packages/linux/patches/linux-2.6.38-rc8-706_hz-raise_max.patch b/packages/linux/patches/linux-2.6.38-rc8-706_hz-raise_max.patch deleted file mode 100644 index bf70f54392..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-706_hz-raise_max.patch +++ /dev/null @@ -1,174 +0,0 @@ ---- - arch/x86/kernel/cpu/proc.c | 2 - - arch/x86/kernel/smpboot.c | 2 - - include/linux/nfsd/stats.h | 4 +- - include/net/inet_timewait_sock.h | 10 ++++-- - init/calibrate.c | 2 - - kernel/Kconfig.hz | 64 +++++++++++++++++++++++++++++++++++++++ - 6 files changed, 76 insertions(+), 8 deletions(-) - -Index: linux-2.6.37-ck2/arch/x86/kernel/cpu/proc.c -=================================================================== ---- linux-2.6.37-ck2.orig/arch/x86/kernel/cpu/proc.c 2009-12-03 21:39:58.000000000 +1100 -+++ linux-2.6.37-ck2/arch/x86/kernel/cpu/proc.c 2011-02-14 10:11:10.919252001 +1100 -@@ -109,7 +109,7 @@ - - seq_printf(m, "\nbogomips\t: %lu.%02lu\n", - c->loops_per_jiffy/(500000/HZ), -- (c->loops_per_jiffy/(5000/HZ)) % 100); -+ (c->loops_per_jiffy * 10 /(50000/HZ)) % 100); - - #ifdef CONFIG_X86_64 - if (c->x86_tlbsize > 0) -Index: linux-2.6.37-ck2/arch/x86/kernel/smpboot.c -=================================================================== ---- linux-2.6.37-ck2.orig/arch/x86/kernel/smpboot.c 2011-01-06 14:04:08.000000000 +1100 -+++ linux-2.6.37-ck2/arch/x86/kernel/smpboot.c 2011-02-14 10:11:10.920252001 +1100 -@@ -497,7 +497,7 @@ - "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", - num_online_cpus(), - bogosum/(500000/HZ), -- (bogosum/(5000/HZ))%100); -+ (bogosum * 10/(50000/HZ))%100); - - pr_debug("Before bogocount - setting activated=1.\n"); - } -Index: linux-2.6.37-ck2/include/linux/nfsd/stats.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/nfsd/stats.h 2009-06-10 13:05:27.000000000 +1000 -+++ linux-2.6.37-ck2/include/linux/nfsd/stats.h 2011-02-14 10:11:10.920252001 +1100 -@@ -11,8 +11,8 @@ - - #include - --/* thread usage wraps very million seconds (approx one fortnight) */ --#define NFSD_USAGE_WRAP (HZ*1000000) -+/* thread usage wraps every one hundred thousand seconds (approx one day) */ -+#define NFSD_USAGE_WRAP (HZ*100000) - - #ifdef __KERNEL__ - -Index: linux-2.6.37-ck2/include/net/inet_timewait_sock.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/net/inet_timewait_sock.h 2010-08-02 11:12:25.000000000 +1000 -+++ linux-2.6.37-ck2/include/net/inet_timewait_sock.h 2011-02-14 10:11:10.920252001 +1100 -@@ -39,8 +39,8 @@ - * If time > 4sec, it is "slow" path, no recycling is required, - * so that we select tick to get range about 4 seconds. - */ --#if HZ <= 16 || HZ > 4096 --# error Unsupported: HZ <= 16 or HZ > 4096 -+#if HZ <= 16 || HZ > 16384 -+# error Unsupported: HZ <= 16 or HZ > 16384 - #elif HZ <= 32 - # define INET_TWDR_RECYCLE_TICK (5 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) - #elif HZ <= 64 -@@ -55,8 +55,12 @@ - # define INET_TWDR_RECYCLE_TICK (10 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) - #elif HZ <= 2048 - # define INET_TWDR_RECYCLE_TICK (11 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) --#else -+#elif HZ <= 4096 - # define INET_TWDR_RECYCLE_TICK (12 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -+#elif HZ <= 8192 -+# define INET_TWDR_RECYCLE_TICK (13 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -+#else -+# define INET_TWDR_RECYCLE_TICK (14 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) - #endif - - /* TIME_WAIT reaping mechanism. */ -Index: linux-2.6.37-ck2/init/calibrate.c -=================================================================== ---- linux-2.6.37-ck2.orig/init/calibrate.c 2010-02-25 21:51:52.000000000 +1100 -+++ linux-2.6.37-ck2/init/calibrate.c 2011-02-14 10:11:10.921252001 +1100 -@@ -176,7 +176,7 @@ - if (!printed) - pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n", - loops_per_jiffy/(500000/HZ), -- (loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy); -+ (loops_per_jiffy * 10 /(50000/HZ)) % 100, loops_per_jiffy); - - printed = true; - } -Index: linux-2.6.37-ck2/kernel/Kconfig.hz -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/Kconfig.hz 2011-02-14 10:11:10.702252000 +1100 -+++ linux-2.6.37-ck2/kernel/Kconfig.hz 2011-02-14 10:11:10.921252001 +1100 -@@ -48,6 +48,63 @@ - can also benefit from this choice without sacrificing battery life - if dynticks is also enabled. - -+ config HZ_1500 -+ bool "1500 HZ" -+ help -+ 1500 Hz is an insane value to use to run broken software that is Hz -+ limited. -+ -+ Being over 1000, driver breakage is likely. -+ -+ config HZ_2000 -+ bool "2000 HZ" -+ help -+ 2000 Hz is an insane value to use to run broken software that is Hz -+ limited. -+ -+ Being over 1000, driver breakage is likely. -+ -+ config HZ_3000 -+ bool "3000 HZ" -+ help -+ 3000 Hz is an insane value to use to run broken software that is Hz -+ limited. -+ -+ Being over 1000, driver breakage is likely. -+ -+ config HZ_4000 -+ bool "4000 HZ" -+ help -+ 4000 Hz is an insane value to use to run broken software that is Hz -+ limited. -+ -+ Being over 1000, driver breakage is likely. -+ -+ config HZ_5000 -+ bool "5000 HZ" -+ help -+ 5000 Hz is an obscene value to use to run broken software that is Hz -+ limited. -+ -+ Being over 1000, driver breakage is likely. -+ -+ config HZ_7500 -+ bool "7500 HZ" -+ help -+ 7500 Hz is an obscene value to use to run broken software that is Hz -+ limited. -+ -+ Being over 1000, driver breakage is likely. -+ -+ config HZ_10000 -+ bool "10000 HZ" -+ help -+ 10000 Hz is an obscene value to use to run broken software that is Hz -+ limited. -+ -+ Being over 1000, driver breakage is likely. -+ -+ - endchoice - - config HZ -@@ -56,6 +113,13 @@ - default 250 if HZ_250_NODEFAULT - default 300 if HZ_300 - default 1000 if HZ_1000 -+ default 1500 if HZ_1500 -+ default 2000 if HZ_2000 -+ default 3000 if HZ_3000 -+ default 4000 if HZ_4000 -+ default 5000 if HZ_5000 -+ default 7500 if HZ_7500 -+ default 10000 if HZ_10000 - - config SCHED_HRTICK - def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS) diff --git a/packages/linux/patches/linux-2.6.38-rc8-707_kconfig-expose_vmsplit_option.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-707_kconfig-expose_vmsplit_option.patch.disabled deleted file mode 100644 index 937cf72f31..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-707_kconfig-expose_vmsplit_option.patch.disabled +++ /dev/null @@ -1,40 +0,0 @@ ---- - arch/x86/Kconfig | 12 ++++++------ - 1 file changed, 6 insertions(+), 6 deletions(-) - -Index: linux-2.6.37-ck2/arch/x86/Kconfig -=================================================================== ---- linux-2.6.37-ck2.orig/arch/x86/Kconfig 2011-01-06 14:04:08.000000000 +1100 -+++ linux-2.6.37-ck2/arch/x86/Kconfig 2011-02-14 10:11:10.260252001 +1100 -@@ -1046,7 +1046,7 @@ - - choice - depends on EXPERIMENTAL -- prompt "Memory split" if EMBEDDED -+ prompt "Memory split" - default VMSPLIT_3G - depends on X86_32 - ---help--- -@@ -1066,17 +1066,17 @@ - option alone! - - config VMSPLIT_3G -- bool "3G/1G user/kernel split" -+ bool "Default 896MB lowmem (3G/1G user/kernel split)" - config VMSPLIT_3G_OPT - depends on !X86_PAE -- bool "3G/1G user/kernel split (for full 1G low memory)" -+ bool "1GB lowmem (3G/1G user/kernel split)" - config VMSPLIT_2G -- bool "2G/2G user/kernel split" -+ bool "2GB lowmem (2G/2G user/kernel split)" - config VMSPLIT_2G_OPT - depends on !X86_PAE -- bool "2G/2G user/kernel split (for full 2G low memory)" -+ bool "2GB lowmem (2G/2G user/kernel split)" - config VMSPLIT_1G -- bool "1G/3G user/kernel split" -+ bool "3GB lowmem (1G/3G user/kernel split)" - endchoice - - config PAGE_OFFSET diff --git a/packages/linux/patches/linux-2.6.38-rc8-708_mm-kswapd_inherit_prio-1.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-708_mm-kswapd_inherit_prio-1.patch.disabled deleted file mode 100644 index 04d3712fe7..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-708_mm-kswapd_inherit_prio-1.patch.disabled +++ /dev/null @@ -1,69 +0,0 @@ ---- - mm/vmscan.c | 33 ++++++++++++++++++++++++++++++++- - 1 file changed, 32 insertions(+), 1 deletion(-) - -Index: linux-2.6.37-ck2/mm/vmscan.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/vmscan.c 2011-02-14 10:11:00.986252001 +1100 -+++ linux-2.6.37-ck2/mm/vmscan.c 2011-02-14 10:11:01.254252001 +1100 -@@ -1855,6 +1855,33 @@ - } - - /* -+ * Helper functions to adjust nice level of kswapd, based on the priority of -+ * the task (p) that called it. If it is already higher priority we do not -+ * demote its nice level since it is still working on behalf of a higher -+ * priority task. With kernel threads we leave it at nice 0. -+ * -+ * We don't ever run kswapd real time, so if a real time task calls kswapd we -+ * set it to highest SCHED_NORMAL priority. -+ */ -+static inline int effective_sc_prio(struct task_struct *p) -+{ -+ if (likely(p->mm)) { -+ if (rt_task(p)) -+ return -20; -+ return task_nice(p); -+ } -+ return 0; -+} -+ -+static void set_kswapd_nice(struct task_struct *kswapd, int active) -+{ -+ long nice = effective_sc_prio(current); -+ -+ if (task_nice(kswapd) > nice || !active) -+ set_user_nice(kswapd, nice); -+} -+ -+/* - * This is the direct reclaim path, for page-allocating processes. We only - * try to reclaim pages from zones which will satisfy the caller's allocation - * request. -@@ -2457,6 +2484,7 @@ - } - } - -+ set_user_nice(tsk, 0); - order = pgdat->kswapd_max_order; - } - finish_wait(&pgdat->kswapd_wait, &wait); -@@ -2483,6 +2511,7 @@ - void wakeup_kswapd(struct zone *zone, int order) - { - pg_data_t *pgdat; -+ int active; - - if (!populated_zone(zone)) - return; -@@ -2495,7 +2524,9 @@ - trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - return; -- if (!waitqueue_active(&pgdat->kswapd_wait)) -+ active = waitqueue_active(&pgdat->kswapd_wait); -+ set_kswapd_nice(pgdat->kswapd, active); -+ if (!active) - return; - wake_up_interruptible(&pgdat->kswapd_wait); - } diff --git a/packages/linux/patches/linux-2.6.38-rc8-709_mm-decrease_default_dirty_ratio.patch b/packages/linux/patches/linux-2.6.38-rc8-709_mm-decrease_default_dirty_ratio.patch deleted file mode 100644 index 804bccfcd4..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-709_mm-decrease_default_dirty_ratio.patch +++ /dev/null @@ -1,34 +0,0 @@ -The default dirty ratio is chosen to be a compromise between throughput and -overall system latency. On a desktop, if an application writes to disk a lot, -that application should be the one to slow down rather than the desktop as a -whole. At higher dirty ratio settings, an application could write a lot to -disk and then happily use lots of CPU time after that while the rest of the -system is busy waiting on that naughty applications disk writes to complete -before anything else happening. - -Lower ratios mean that the application that do a lot of disk writes end up -being responsible for their own actions and they're the ones that slow down -rather than the system in general. - -This does decrease overall write throughput slightly, but to the benefit of -the latency of the system as a whole. - --ck - ---- - mm/page-writeback.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - -Index: linux-2.6.37-ck2/mm/page-writeback.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/page-writeback.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/mm/page-writeback.c 2011-02-14 10:11:10.037252000 +1100 -@@ -78,7 +78,7 @@ - /* - * The generator of dirty data starts writeback at this percentage - */ --int vm_dirty_ratio = 20; -+int vm_dirty_ratio = 5; - - /* - * vm_dirty_bytes starts at 0 (disabled) so that it is a function of diff --git a/packages/linux/patches/linux-2.6.38-rc8-710_mm-drop_swap_cache_aggressively.patch b/packages/linux/patches/linux-2.6.38-rc8-710_mm-drop_swap_cache_aggressively.patch deleted file mode 100644 index 2cd9f63b62..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-710_mm-drop_swap_cache_aggressively.patch +++ /dev/null @@ -1,87 +0,0 @@ ---- - include/linux/swap.h | 2 +- - mm/memory.c | 2 +- - mm/swapfile.c | 9 ++++----- - mm/vmscan.c | 2 +- - 4 files changed, 7 insertions(+), 8 deletions(-) - -Index: linux-2.6.37-ck2/include/linux/swap.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/swap.h 2011-02-14 10:11:00.763252001 +1100 -+++ linux-2.6.37-ck2/include/linux/swap.h 2011-02-14 10:11:00.982252001 +1100 -@@ -192,7 +192,7 @@ - int next; /* swapfile to be used next */ - }; - --/* Swap 50% full? Release swapcache more aggressively.. */ -+/* Swap 50% full? */ - #define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) - - /* linux/mm/page_alloc.c */ -Index: linux-2.6.37-ck2/mm/memory.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/memory.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/mm/memory.c 2011-02-14 10:11:00.984252001 +1100 -@@ -2754,7 +2754,7 @@ - mem_cgroup_commit_charge_swapin(page, ptr); - - swap_free(entry); -- if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) -+ if ((vma->vm_flags & VM_LOCKED) || PageMlocked(page)) - try_to_free_swap(page); - unlock_page(page); - if (swapcache) { -Index: linux-2.6.37-ck2/mm/swapfile.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/swapfile.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/mm/swapfile.c 2011-02-14 10:11:00.985252001 +1100 -@@ -321,7 +321,7 @@ - scan_base = offset = si->lowest_bit; - - /* reuse swap entry of cache-only swap if not busy. */ -- if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { -+ if (si->swap_map[offset] == SWAP_HAS_CACHE) { - int swap_was_freed; - spin_unlock(&swap_lock); - swap_was_freed = __try_to_reclaim_swap(si, offset); -@@ -410,7 +410,7 @@ - spin_lock(&swap_lock); - goto checks; - } -- if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { -+ if (si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&swap_lock); - goto checks; - } -@@ -425,7 +425,7 @@ - spin_lock(&swap_lock); - goto checks; - } -- if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { -+ if (si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&swap_lock); - goto checks; - } -@@ -739,8 +739,7 @@ - * Not mapped elsewhere, or swap space full? Free it! - * Also recheck PageSwapCache now page is locked (above). - */ -- if (PageSwapCache(page) && !PageWriteback(page) && -- (!page_mapped(page) || vm_swap_full())) { -+ if (PageSwapCache(page) && !PageWriteback(page)) { - delete_from_swap_cache(page); - SetPageDirty(page); - } -Index: linux-2.6.37-ck2/mm/vmscan.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/vmscan.c 2011-02-14 10:11:00.536252000 +1100 -+++ linux-2.6.37-ck2/mm/vmscan.c 2011-02-14 10:11:00.986252001 +1100 -@@ -900,7 +900,7 @@ - - activate_locked: - /* Not a candidate for swapping, so reclaim swap space. */ -- if (PageSwapCache(page) && vm_swap_full()) -+ if (PageSwapCache(page)) - try_to_free_swap(page); - VM_BUG_ON(PageActive(page)); - SetPageActive(page); diff --git a/packages/linux/patches/linux-2.6.38-rc8-711_mm-enable_swaptoken_only_when_swap_full.patch b/packages/linux/patches/linux-2.6.38-rc8-711_mm-enable_swaptoken_only_when_swap_full.patch deleted file mode 100644 index f7f76ea318..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-711_mm-enable_swaptoken_only_when_swap_full.patch +++ /dev/null @@ -1,20 +0,0 @@ ---- - include/linux/swap.h | 3 ++- - 1 file changed, 2 insertions(+), 1 deletion(-) - -Index: linux-2.6.37-ck2/include/linux/swap.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/swap.h 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/include/linux/swap.h 2011-02-14 10:11:00.763252001 +1100 -@@ -348,9 +348,10 @@ - extern void grab_swap_token(struct mm_struct *); - extern void __put_swap_token(struct mm_struct *); - -+/* Only allow swap token to have effect if swap is full */ - static inline int has_swap_token(struct mm_struct *mm) - { -- return (mm == swap_token_mm); -+ return (mm == swap_token_mm && vm_swap_full()); - } - - static inline void put_swap_token(struct mm_struct *mm) diff --git a/packages/linux/patches/linux-2.6.38-rc8-712_mm-background_scan.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-712_mm-background_scan.patch.disabled deleted file mode 100644 index c84d37d1af..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-712_mm-background_scan.patch.disabled +++ /dev/null @@ -1,137 +0,0 @@ ---- - include/linux/mmzone.h | 6 +++++- - mm/vmscan.c | 42 ++++++++++++++++++++++++++++++++++++++++++ - 2 files changed, 47 insertions(+), 1 deletion(-) - -Index: linux-2.6.37-ck2/include/linux/mmzone.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/mmzone.h 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/include/linux/mmzone.h 2011-02-14 10:11:01.470252001 +1100 -@@ -15,6 +15,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -161,12 +162,14 @@ - WMARK_MIN, - WMARK_LOW, - WMARK_HIGH, -+ WMARK_LOTS, - NR_WMARK - }; - - #define min_wmark_pages(z) (z->watermark[WMARK_MIN]) - #define low_wmark_pages(z) (z->watermark[WMARK_LOW]) - #define high_wmark_pages(z) (z->watermark[WMARK_HIGH]) -+#define lots_wmark_pages(z) (z->watermark[WMARK_LOTS]) - - struct per_cpu_pages { - int count; /* number of pages in the list */ -@@ -343,7 +346,7 @@ - ZONE_PADDING(_pad1_) - - /* Fields commonly accessed by the page reclaim scanner */ -- spinlock_t lru_lock; -+ spinlock_t lru_lock; - struct zone_lru { - struct list_head list; - } lru[NR_LRU_LISTS]; -@@ -645,6 +648,7 @@ - wait_queue_head_t kswapd_wait; - struct task_struct *kswapd; - int kswapd_max_order; -+ struct timer_list watermark_timer; - } pg_data_t; - - #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) -Index: linux-2.6.37-ck2/mm/vmscan.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/vmscan.c 2011-02-14 10:11:01.254252001 +1100 -+++ linux-2.6.37-ck2/mm/vmscan.c 2011-02-14 10:11:01.471252001 +1100 -@@ -36,6 +36,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -2398,6 +2399,8 @@ - return sc.nr_reclaimed; - } - -+#define WT_EXPIRY (HZ * 5) /* Time to wakeup watermark_timer */ -+ - /* - * The background pageout daemon, started as a kernel thread - * from the init process. -@@ -2448,6 +2451,8 @@ - unsigned long new_order; - int ret; - -+ /* kswapd has been busy so delay watermark_timer */ -+ mod_timer(&pgdat->watermark_timer, jiffies + WT_EXPIRY); - prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); - new_order = pgdat->kswapd_max_order; - pgdat->kswapd_max_order = 0; -@@ -2632,20 +2637,57 @@ - } - - /* -+ * We wake up kswapd every WT_EXPIRY till free ram is above pages_lots -+ */ -+static void watermark_wakeup(unsigned long data) -+{ -+ pg_data_t *pgdat = (pg_data_t *)data; -+ struct timer_list *wt = &pgdat->watermark_timer; -+ int i; -+ -+ if (!waitqueue_active(&pgdat->kswapd_wait) || above_background_load()) -+ goto out; -+ for (i = pgdat->nr_zones - 1; i >= 0; i--) { -+ struct zone *z = pgdat->node_zones + i; -+ -+ if (!populated_zone(z) || is_highmem(z)) { -+ /* We are better off leaving highmem full */ -+ continue; -+ } -+ if (!zone_watermark_ok(z, 0, lots_wmark_pages(z), 0, 0)) { -+ wake_up_interruptible(&pgdat->kswapd_wait); -+ goto out; -+ } -+ } -+out: -+ mod_timer(wt, jiffies + WT_EXPIRY); -+ return; -+} -+ -+/* - * This kswapd start function will be called by init and node-hot-add. - * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. - */ - int kswapd_run(int nid) - { - pg_data_t *pgdat = NODE_DATA(nid); -+ struct timer_list *wt; - int ret = 0; - - if (pgdat->kswapd) - return 0; - -+ wt = &pgdat->watermark_timer; -+ init_timer(wt); -+ wt->data = (unsigned long)pgdat; -+ wt->function = watermark_wakeup; -+ wt->expires = jiffies + WT_EXPIRY; -+ add_timer(wt); -+ - pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); - if (IS_ERR(pgdat->kswapd)) { - /* failure at boot is fatal */ -+ del_timer(wt); - BUG_ON(system_state == SYSTEM_BOOTING); - printk("Failed to start kswapd on node %d\n",nid); - ret = -1; diff --git a/packages/linux/patches/linux-2.6.38-rc8-713_mm-idleprio_prio-1.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-713_mm-idleprio_prio-1.patch.disabled deleted file mode 100644 index f0ca19b956..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-713_mm-idleprio_prio-1.patch.disabled +++ /dev/null @@ -1,33 +0,0 @@ ---- - include/linux/sched.h | 2 +- - mm/vmscan.c | 2 ++ - 2 files changed, 3 insertions(+), 1 deletion(-) - -Index: linux-2.6.37-ck1/include/linux/sched.h -=================================================================== ---- linux-2.6.37-ck1.orig/include/linux/sched.h 2011-01-06 14:07:19.971048973 +1100 -+++ linux-2.6.37-ck1/include/linux/sched.h 2011-01-06 14:07:58.442334300 +1100 -@@ -38,9 +38,9 @@ - #define SCHED_BATCH 3 - /* SCHED_ISO: Implemented on BFS only */ - #define SCHED_IDLE 5 -+#define SCHED_IDLEPRIO SCHED_IDLE - #ifdef CONFIG_SCHED_BFS - #define SCHED_ISO 4 --#define SCHED_IDLEPRIO SCHED_IDLE - #define SCHED_MAX (SCHED_IDLEPRIO) - #define SCHED_RANGE(policy) ((policy) <= SCHED_MAX) - #endif -Index: linux-2.6.37-ck1/mm/vmscan.c -=================================================================== ---- linux-2.6.37-ck1.orig/mm/vmscan.c 2011-01-06 14:07:58.305326159 +1100 -+++ linux-2.6.37-ck1/mm/vmscan.c 2011-01-06 14:07:58.443334359 +1100 -@@ -1874,6 +1874,8 @@ static inline int effective_sc_prio(stru - if (likely(p->mm)) { - if (rt_task(p)) - return -20; -+ if (p->policy == SCHED_IDLEPRIO) -+ return 19; - return task_nice(p); - } - return 0; diff --git a/packages/linux/patches/linux-2.6.38-rc8-714_mm-lru_cache_add_lru_tail.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-714_mm-lru_cache_add_lru_tail.patch.disabled deleted file mode 100644 index 98cf2994f4..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-714_mm-lru_cache_add_lru_tail.patch.disabled +++ /dev/null @@ -1,250 +0,0 @@ ---- - include/linux/mm_inline.h | 14 +++++++++++- - include/linux/swap.h | 8 ++++++- - mm/filemap.c | 50 +++++++++++++++++++++++++++++++++++++++------- - mm/swap.c | 30 ++++++++++++++++++++++----- - 4 files changed, 86 insertions(+), 16 deletions(-) - -Index: linux-2.6.37-ck2/include/linux/mm_inline.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/mm_inline.h 2009-12-03 21:40:09.000000000 +1100 -+++ linux-2.6.37-ck2/include/linux/mm_inline.h 2011-02-14 10:11:09.770252000 +1100 -@@ -20,14 +20,24 @@ - } - - static inline void --add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l) -+__add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l, int tail) - { -- list_add(&page->lru, &zone->lru[l].list); -+ /* See if this should be added to the tail of this lru list */ -+ if (tail) -+ list_add_tail(&page->lru, &zone->lru[l].list); -+ else -+ list_add(&page->lru, &zone->lru[l].list); - __inc_zone_state(zone, NR_LRU_BASE + l); - mem_cgroup_add_lru_list(page, l); - } - - static inline void -+add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l) -+{ -+ __add_page_to_lru_list(zone, page, l, 0); -+} -+ -+static inline void - del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l) - { - list_del(&page->lru); -Index: linux-2.6.37-ck2/include/linux/swap.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/swap.h 2011-02-14 10:11:00.982252001 +1100 -+++ linux-2.6.37-ck2/include/linux/swap.h 2011-02-14 10:11:09.770252000 +1100 -@@ -206,6 +206,7 @@ - - - /* linux/mm/swap.c */ -+extern void ____lru_cache_add(struct page *, enum lru_list lru, int tail); - extern void __lru_cache_add(struct page *, enum lru_list lru); - extern void lru_cache_add_lru(struct page *, enum lru_list lru); - extern void activate_page(struct page *); -@@ -226,9 +227,14 @@ - __lru_cache_add(page, LRU_INACTIVE_ANON); - } - -+static inline void lru_cache_add_file_tail(struct page *page, int tail) -+{ -+ ____lru_cache_add(page, LRU_INACTIVE_FILE, tail); -+} -+ - static inline void lru_cache_add_file(struct page *page) - { -- __lru_cache_add(page, LRU_INACTIVE_FILE); -+ ____lru_cache_add(page, LRU_INACTIVE_FILE, 0); - } - - /* LRU Isolation modes. */ -Index: linux-2.6.37-ck2/mm/filemap.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/filemap.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/mm/filemap.c 2011-02-14 10:11:09.772252000 +1100 -@@ -439,8 +439,8 @@ - } - EXPORT_SYMBOL(add_to_page_cache_locked); - --int add_to_page_cache_lru(struct page *page, struct address_space *mapping, -- pgoff_t offset, gfp_t gfp_mask) -+int __add_to_page_cache_lru(struct page *page, struct address_space *mapping, -+ pgoff_t offset, gfp_t gfp_mask, int tail) - { - int ret; - -@@ -456,12 +456,18 @@ - ret = add_to_page_cache(page, mapping, offset, gfp_mask); - if (ret == 0) { - if (page_is_file_cache(page)) -- lru_cache_add_file(page); -+ lru_cache_add_file_tail(page, tail); - else - lru_cache_add_anon(page); - } - return ret; - } -+ -+int add_to_page_cache_lru(struct page *page, struct address_space *mapping, -+ pgoff_t offset, gfp_t gfp_mask) -+{ -+ return __add_to_page_cache_lru(page, mapping, offset, gfp_mask, 0); -+} - EXPORT_SYMBOL_GPL(add_to_page_cache_lru); - - #ifdef CONFIG_NUMA -@@ -968,6 +974,28 @@ - ra->ra_pages /= 4; - } - -+static inline int nr_mapped(void) -+{ -+ return global_page_state(NR_FILE_MAPPED) + -+ global_page_state(NR_ANON_PAGES); -+} -+ -+/* -+ * This examines how large in pages a file size is and returns 1 if it is -+ * more than half the unmapped ram. Avoid doing read_page_state which is -+ * expensive unless we already know it is likely to be large enough. -+ */ -+static int large_isize(unsigned long nr_pages) -+{ -+ if (nr_pages * 6 > vm_total_pages) { -+ unsigned long unmapped_ram = vm_total_pages - nr_mapped(); -+ -+ if (nr_pages * 2 > unmapped_ram) -+ return 1; -+ } -+ return 0; -+} -+ - /** - * do_generic_file_read - generic file read routine - * @filp: the file to read -@@ -992,7 +1020,7 @@ - pgoff_t prev_index; - unsigned long offset; /* offset into pagecache page */ - unsigned int prev_offset; -- int error; -+ int error, tail = 0; - - index = *ppos >> PAGE_CACHE_SHIFT; - prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; -@@ -1003,7 +1031,7 @@ - for (;;) { - struct page *page; - pgoff_t end_index; -- loff_t isize; -+ loff_t isize = 0; - unsigned long nr, ret; - - cond_resched(); -@@ -1177,8 +1205,16 @@ - desc->error = -ENOMEM; - goto out; - } -- error = add_to_page_cache_lru(page, mapping, -- index, GFP_KERNEL); -+ /* -+ * If we know the file is large we add the pages read to the -+ * end of the lru as we're unlikely to be able to cache the -+ * whole file in ram so make those pages the first to be -+ * dropped if not referenced soon. -+ */ -+ if (large_isize(end_index)) -+ tail = 1; -+ error = __add_to_page_cache_lru(page, mapping, -+ index, GFP_KERNEL, tail); - if (error) { - page_cache_release(page); - if (error == -EEXIST) -Index: linux-2.6.37-ck2/mm/swap.c -=================================================================== ---- linux-2.6.37-ck2.orig/mm/swap.c 2011-01-06 14:04:10.000000000 +1100 -+++ linux-2.6.37-ck2/mm/swap.c 2011-02-14 10:11:09.772252000 +1100 -@@ -215,15 +215,23 @@ - - EXPORT_SYMBOL(mark_page_accessed); - --void __lru_cache_add(struct page *page, enum lru_list lru) -+void ______pagevec_lru_add(struct pagevec *pvec, enum lru_list lru, int tail); -+ -+void ____lru_cache_add(struct page *page, enum lru_list lru, int tail) - { - struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru]; - - page_cache_get(page); - if (!pagevec_add(pvec, page)) -- ____pagevec_lru_add(pvec, lru); -+ ______pagevec_lru_add(pvec, lru, tail); - put_cpu_var(lru_add_pvecs); - } -+EXPORT_SYMBOL(____lru_cache_add); -+ -+void __lru_cache_add(struct page *page, enum lru_list lru) -+{ -+ ____lru_cache_add(page, lru, 0); -+} - EXPORT_SYMBOL(__lru_cache_add); - - /** -@@ -231,7 +239,7 @@ - * @page: the page to be added to the LRU. - * @lru: the LRU list to which the page is added. - */ --void lru_cache_add_lru(struct page *page, enum lru_list lru) -+void __lru_cache_add_lru(struct page *page, enum lru_list lru, int tail) - { - if (PageActive(page)) { - VM_BUG_ON(PageUnevictable(page)); -@@ -242,7 +250,12 @@ - } - - VM_BUG_ON(PageLRU(page) || PageActive(page) || PageUnevictable(page)); -- __lru_cache_add(page, lru); -+ ____lru_cache_add(page, lru, tail); -+} -+ -+void lru_cache_add_lru(struct page *page, enum lru_list lru) -+{ -+ __lru_cache_add_lru(page, lru, 0); - } - - /** -@@ -403,7 +416,7 @@ - * Add the passed pages to the LRU, then drop the caller's refcount - * on them. Reinitialises the caller's pagevec. - */ --void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru) -+void ______pagevec_lru_add(struct pagevec *pvec, enum lru_list lru, int tail) - { - int i; - struct zone *zone = NULL; -@@ -431,7 +444,7 @@ - if (active) - SetPageActive(page); - update_page_reclaim_stat(zone, page, file, active); -- add_page_to_lru_list(zone, page, lru); -+ __add_page_to_lru_list(zone, page, lru, tail); - } - if (zone) - spin_unlock_irq(&zone->lru_lock); -@@ -439,6 +452,11 @@ - pagevec_reinit(pvec); - } - -+void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru) -+{ -+ ______pagevec_lru_add(pvec, lru, 0); -+} -+ - EXPORT_SYMBOL(____pagevec_lru_add); - - /* diff --git a/packages/linux/patches/linux-2.6.38-rc8-717_preempt-desktop-tune.patch b/packages/linux/patches/linux-2.6.38-rc8-717_preempt-desktop-tune.patch deleted file mode 100644 index 89d3f3aead..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-717_preempt-desktop-tune.patch +++ /dev/null @@ -1,36 +0,0 @@ ---- - kernel/Kconfig.preempt | 7 ++++--- - 1 file changed, 4 insertions(+), 3 deletions(-) - -Index: linux-2.6.37-ck2/kernel/Kconfig.preempt -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/Kconfig.preempt 2009-06-10 13:05:27.000000000 +1000 -+++ linux-2.6.37-ck2/kernel/Kconfig.preempt 2011-02-14 10:11:11.217252001 +1100 -@@ -1,7 +1,7 @@ - - choice - prompt "Preemption Model" -- default PREEMPT_NONE -+ default PREEMPT - - config PREEMPT_NONE - bool "No Forced Preemption (Server)" -@@ -17,7 +17,7 @@ - latencies. - - config PREEMPT_VOLUNTARY -- bool "Voluntary Kernel Preemption (Desktop)" -+ bool "Voluntary Kernel Preemption (Nothing)" - help - This option reduces the latency of the kernel by adding more - "explicit preemption points" to the kernel code. These new -@@ -31,7 +31,8 @@ - applications to run more 'smoothly' even when the system is - under load. - -- Select this if you are building a kernel for a desktop system. -+ Select this for no system in particular (choose Preemptible -+ instead on a desktop if you know what's good for you). - - config PREEMPT - bool "Preemptible Kernel (Low-Latency Desktop)" diff --git a/packages/linux/patches/linux-2.6.38-rc8-718_sched-add-above-background-load-function.patch.disabled b/packages/linux/patches/linux-2.6.38-rc8-718_sched-add-above-background-load-function.patch.disabled deleted file mode 100644 index ea1c1fa5b1..0000000000 --- a/packages/linux/patches/linux-2.6.38-rc8-718_sched-add-above-background-load-function.patch.disabled +++ /dev/null @@ -1,61 +0,0 @@ ---- - include/linux/sched.h | 7 +++++++ - kernel/sched_bfs.c | 20 ++++++++++++++++++++ - 2 files changed, 27 insertions(+) - -Index: linux-2.6.37-ck2/include/linux/sched.h -=================================================================== ---- linux-2.6.37-ck2.orig/include/linux/sched.h 2011-02-14 09:47:50.988252000 +1100 -+++ linux-2.6.37-ck2/include/linux/sched.h 2011-02-14 10:11:00.292251999 +1100 -@@ -1558,6 +1558,7 @@ - return (p->policy == SCHED_ISO); - } - extern void remove_cpu(unsigned long cpu); -+extern int above_background_load(void); - #else /* CFS */ - extern int runqueue_is_locked(int cpu); - #define tsk_seruntime(t) ((t)->se.sum_exec_runtime) -@@ -1581,6 +1582,12 @@ - static inline void remove_cpu(unsigned long cpu) - { - } -+ -+/* Anyone feel like implementing this? */ -+static inline int above_background_load(void) -+{ -+ return 1; -+} - #endif /* CONFIG_SCHED_BFS */ - - /* Future-safe accessor for struct task_struct's cpus_allowed. */ -Index: linux-2.6.37-ck2/kernel/sched_bfs.c -=================================================================== ---- linux-2.6.37-ck2.orig/kernel/sched_bfs.c 2011-02-14 09:53:53.820252000 +1100 -+++ linux-2.6.37-ck2/kernel/sched_bfs.c 2011-02-14 10:11:00.294252001 +1100 -@@ -559,6 +559,26 @@ - grq_unlock(); - } - -+/* -+ * Look for any tasks *anywhere* that are running nice 0 or better. We do -+ * this lockless for overhead reasons since the occasional wrong result -+ * is harmless. -+ */ -+int above_background_load(void) -+{ -+ struct task_struct *cpu_curr; -+ unsigned long cpu; -+ -+ for_each_online_cpu(cpu) { -+ cpu_curr = cpu_rq(cpu)->curr; -+ if (unlikely(!cpu_curr)) -+ continue; -+ if (PRIO_TO_NICE(cpu_curr->static_prio) < 1) -+ return 1; -+ } -+ return 0; -+} -+ - #ifndef __ARCH_WANT_UNLOCKED_CTXSW - static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) - { diff --git a/projects/ATV/linux/linux.i386.conf b/projects/ATV/linux/linux.i386.conf index d544fe3f7c..ac3bf46591 100644 --- a/projects/ATV/linux/linux.i386.conf +++ b/projects/ATV/linux/linux.i386.conf @@ -1,6 +1,6 @@ # # Automatically generated make config: don't edit -# Linux/i386 2.6.38-rc6-ck2 Kernel Configuration +# Linux/i386 2.6.38-rc8 Kernel Configuration # # CONFIG_64BIT is not set CONFIG_X86_32=y @@ -402,17 +402,10 @@ CONFIG_EFI=y CONFIG_SECCOMP=y # CONFIG_CC_STACKPROTECTOR is not set # CONFIG_HZ_100 is not set -# CONFIG_HZ_250_NODEFAULT is not set -# CONFIG_HZ_300 is not set -CONFIG_HZ_1000=y -# CONFIG_HZ_1500 is not set -# CONFIG_HZ_2000 is not set -# CONFIG_HZ_3000 is not set -# CONFIG_HZ_4000 is not set -# CONFIG_HZ_5000 is not set -# CONFIG_HZ_7500 is not set -# CONFIG_HZ_10000 is not set -CONFIG_HZ=1000 +# CONFIG_HZ_250 is not set +CONFIG_HZ_300=y +# CONFIG_HZ_1000 is not set +CONFIG_HZ=300 CONFIG_SCHED_HRTICK=y # CONFIG_KEXEC is not set CONFIG_PHYSICAL_START=0x1000000 diff --git a/projects/Generic/linux/linux.i386.conf b/projects/Generic/linux/linux.i386.conf index 72b28f82db..fc039a3fe0 100644 --- a/projects/Generic/linux/linux.i386.conf +++ b/projects/Generic/linux/linux.i386.conf @@ -1,6 +1,6 @@ # # Automatically generated make config: don't edit -# Linux/i386 2.6.38-rc6-ck2 Kernel Configuration +# Linux/i386 2.6.38-rc8 Kernel Configuration # # CONFIG_64BIT is not set CONFIG_X86_32=y @@ -389,17 +389,10 @@ CONFIG_ARCH_USES_PG_UNCACHED=y CONFIG_SECCOMP=y CONFIG_CC_STACKPROTECTOR=y # CONFIG_HZ_100 is not set -# CONFIG_HZ_250_NODEFAULT is not set -# CONFIG_HZ_300 is not set -CONFIG_HZ_1000=y -# CONFIG_HZ_1500 is not set -# CONFIG_HZ_2000 is not set -# CONFIG_HZ_3000 is not set -# CONFIG_HZ_4000 is not set -# CONFIG_HZ_5000 is not set -# CONFIG_HZ_7500 is not set -# CONFIG_HZ_10000 is not set -CONFIG_HZ=1000 +# CONFIG_HZ_250 is not set +CONFIG_HZ_300=y +# CONFIG_HZ_1000 is not set +CONFIG_HZ=300 CONFIG_SCHED_HRTICK=y # CONFIG_KEXEC is not set # CONFIG_CRASH_DUMP is not set diff --git a/projects/ION/linux/linux.i386.conf b/projects/ION/linux/linux.i386.conf index 75fcba4968..67ceb089a8 100644 --- a/projects/ION/linux/linux.i386.conf +++ b/projects/ION/linux/linux.i386.conf @@ -1,6 +1,6 @@ # # Automatically generated make config: don't edit -# Linux/i386 2.6.38-rc6-ck2 Kernel Configuration +# Linux/i386 2.6.38-rc8 Kernel Configuration # # CONFIG_64BIT is not set CONFIG_X86_32=y @@ -388,17 +388,10 @@ CONFIG_ARCH_USES_PG_UNCACHED=y CONFIG_SECCOMP=y CONFIG_CC_STACKPROTECTOR=y # CONFIG_HZ_100 is not set -# CONFIG_HZ_250_NODEFAULT is not set -# CONFIG_HZ_300 is not set -CONFIG_HZ_1000=y -# CONFIG_HZ_1500 is not set -# CONFIG_HZ_2000 is not set -# CONFIG_HZ_3000 is not set -# CONFIG_HZ_4000 is not set -# CONFIG_HZ_5000 is not set -# CONFIG_HZ_7500 is not set -# CONFIG_HZ_10000 is not set -CONFIG_HZ=1000 +# CONFIG_HZ_250 is not set +CONFIG_HZ_300=y +# CONFIG_HZ_1000 is not set +CONFIG_HZ=300 CONFIG_SCHED_HRTICK=y # CONFIG_KEXEC is not set # CONFIG_CRASH_DUMP is not set diff --git a/projects/ION/linux/linux.x86_64.conf b/projects/ION/linux/linux.x86_64.conf index 5c59fe3b07..fcb756edd6 100644 --- a/projects/ION/linux/linux.x86_64.conf +++ b/projects/ION/linux/linux.x86_64.conf @@ -1,6 +1,6 @@ # # Automatically generated make config: don't edit -# Linux/x86_64 2.6.38-rc6-ck2 Kernel Configuration +# Linux/x86_64 2.6.38-rc8 Kernel Configuration # CONFIG_64BIT=y # CONFIG_X86_32 is not set @@ -352,17 +352,10 @@ CONFIG_ARCH_USES_PG_UNCACHED=y CONFIG_SECCOMP=y CONFIG_CC_STACKPROTECTOR=y # CONFIG_HZ_100 is not set -# CONFIG_HZ_250_NODEFAULT is not set -# CONFIG_HZ_300 is not set -CONFIG_HZ_1000=y -# CONFIG_HZ_1500 is not set -# CONFIG_HZ_2000 is not set -# CONFIG_HZ_3000 is not set -# CONFIG_HZ_4000 is not set -# CONFIG_HZ_5000 is not set -# CONFIG_HZ_7500 is not set -# CONFIG_HZ_10000 is not set -CONFIG_HZ=1000 +# CONFIG_HZ_250 is not set +CONFIG_HZ_300=y +# CONFIG_HZ_1000 is not set +CONFIG_HZ=300 CONFIG_SCHED_HRTICK=y # CONFIG_KEXEC is not set # CONFIG_CRASH_DUMP is not set diff --git a/projects/Intel/linux/linux.i386.conf b/projects/Intel/linux/linux.i386.conf index d3365d98d1..ffad6b90a7 100644 --- a/projects/Intel/linux/linux.i386.conf +++ b/projects/Intel/linux/linux.i386.conf @@ -1,6 +1,6 @@ # # Automatically generated make config: don't edit -# Linux/i386 2.6.38-rc6-ck2 Kernel Configuration +# Linux/i386 2.6.38-rc8 Kernel Configuration # # CONFIG_64BIT is not set CONFIG_X86_32=y @@ -389,17 +389,10 @@ CONFIG_ARCH_USES_PG_UNCACHED=y CONFIG_SECCOMP=y CONFIG_CC_STACKPROTECTOR=y # CONFIG_HZ_100 is not set -# CONFIG_HZ_250_NODEFAULT is not set -# CONFIG_HZ_300 is not set -CONFIG_HZ_1000=y -# CONFIG_HZ_1500 is not set -# CONFIG_HZ_2000 is not set -# CONFIG_HZ_3000 is not set -# CONFIG_HZ_4000 is not set -# CONFIG_HZ_5000 is not set -# CONFIG_HZ_7500 is not set -# CONFIG_HZ_10000 is not set -CONFIG_HZ=1000 +# CONFIG_HZ_250 is not set +CONFIG_HZ_300=y +# CONFIG_HZ_1000 is not set +CONFIG_HZ=300 CONFIG_SCHED_HRTICK=y # CONFIG_KEXEC is not set # CONFIG_CRASH_DUMP is not set diff --git a/projects/Intel/linux/linux.x86_64.conf b/projects/Intel/linux/linux.x86_64.conf index 2e6c5e8e02..765f384e3c 100644 --- a/projects/Intel/linux/linux.x86_64.conf +++ b/projects/Intel/linux/linux.x86_64.conf @@ -1,6 +1,6 @@ # # Automatically generated make config: don't edit -# Linux/x86_64 2.6.38-rc6-ck2 Kernel Configuration +# Linux/x86_64 2.6.38-rc8 Kernel Configuration # CONFIG_64BIT=y # CONFIG_X86_32 is not set @@ -354,17 +354,10 @@ CONFIG_ARCH_USES_PG_UNCACHED=y CONFIG_SECCOMP=y CONFIG_CC_STACKPROTECTOR=y # CONFIG_HZ_100 is not set -# CONFIG_HZ_250_NODEFAULT is not set -# CONFIG_HZ_300 is not set -CONFIG_HZ_1000=y -# CONFIG_HZ_1500 is not set -# CONFIG_HZ_2000 is not set -# CONFIG_HZ_3000 is not set -# CONFIG_HZ_4000 is not set -# CONFIG_HZ_5000 is not set -# CONFIG_HZ_7500 is not set -# CONFIG_HZ_10000 is not set -CONFIG_HZ=1000 +# CONFIG_HZ_250 is not set +CONFIG_HZ_300=y +# CONFIG_HZ_1000 is not set +CONFIG_HZ=300 CONFIG_SCHED_HRTICK=y # CONFIG_KEXEC is not set # CONFIG_CRASH_DUMP is not set