From d50ba256b5f1478e15accfcfda9b72fd7a661364 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 23 Sep 2009 14:44:08 +1000 Subject: drm/kms: start adding command line interface using fb. [note this requires an fb patch posted to linux-fbdev-devel already] This uses the normal video= command line option to control the kms output setup at boot time. It is used to override the autodetection done by kms. video= normally takes a framebuffer as the first parameter, in kms it will take a connector name, DVI-I-1, or LVDS-1 etc. If no output connector is specified the mode string will apply to all connectors. The mode specification used will match down the probed modes, and if no mode is found it will add a CVT mode that matches. video=1024x768 - all connectors match a 1024x768 mode or add a CVT on video=VGA-1:1024x768, VGA-1 connector gets mode only. The same strings as used in current fb modedb.c are used, except I've added three more letters, e, D, d, e = enable, D = enable Digital, d = disable, which allow a connector to be forced into a certain state. Signed-off-by: Dave Airlie --- include/drm/drm_crtc.h | 14 +++++++++++++- include/drm/drm_fb_helper.h | 24 ++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index ae1e9e166959..b69347b8904f 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -387,6 +387,7 @@ struct drm_crtc { * @get_modes: get mode list for this connector * @set_property: property for this connector may need update * @destroy: make object go away + * @force: notify the driver the connector is forced on * * Each CRTC may have one or more connectors attached to it. The functions * below allow the core DRM code to control connectors, enumerate available modes, @@ -401,6 +402,7 @@ struct drm_connector_funcs { int (*set_property)(struct drm_connector *connector, struct drm_property *property, uint64_t val); void (*destroy)(struct drm_connector *connector); + void (*force)(struct drm_connector *connector); }; struct drm_encoder_funcs { @@ -429,6 +431,13 @@ struct drm_encoder { void *helper_private; }; +enum drm_connector_force { + DRM_FORCE_UNSPECIFIED, + DRM_FORCE_OFF, + DRM_FORCE_ON, /* force on analog part normally */ + DRM_FORCE_ON_DIGITAL, /* for DVI-I use digital connector */ +}; + /** * drm_connector - central DRM connector control structure * @crtc: CRTC this connector is currently connected to, NULL if none @@ -478,9 +487,12 @@ struct drm_connector { void *helper_private; + /* forced on connector */ + enum drm_connector_force force; uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER]; uint32_t force_encoder_id; struct drm_encoder *encoder; /* currently active encoder */ + void *fb_helper_private; }; /** @@ -746,7 +758,7 @@ extern int drm_mode_gamma_set_ioctl(struct drm_device *dev, extern bool drm_detect_hdmi_monitor(struct edid *edid); extern struct drm_display_mode *drm_cvt_mode(struct drm_device *dev, int hdisplay, int vdisplay, int vrefresh, - bool reduced, bool interlaced); + bool reduced, bool interlaced, bool margins); extern struct drm_display_mode *drm_gtf_mode(struct drm_device *dev, int hdisplay, int vdisplay, int vrefresh, bool interlaced, int margins); diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index 88fffbdfa26f..4aa5740ce59f 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -35,11 +35,30 @@ struct drm_fb_helper_crtc { struct drm_mode_set mode_set; }; + struct drm_fb_helper_funcs { void (*gamma_set)(struct drm_crtc *crtc, u16 red, u16 green, u16 blue, int regno); }; +/* mode specified on the command line */ +struct drm_fb_helper_cmdline_mode { + bool specified; + bool refresh_specified; + bool bpp_specified; + int xres, yres; + int bpp; + int refresh; + bool rb; + bool interlace; + bool cvt; + bool margins; +}; + +struct drm_fb_helper_connector { + struct drm_fb_helper_cmdline_mode cmdline_mode; +}; + struct drm_fb_helper { struct drm_framebuffer *fb; struct drm_device *dev; @@ -57,6 +76,8 @@ int drm_fb_helper_single_fb_probe(struct drm_device *dev, uint32_t fb_height, uint32_t surface_width, uint32_t surface_height, + uint32_t surface_depth, + uint32_t surface_bpp, struct drm_framebuffer **fb_ptr)); int drm_fb_helper_init_crtc_count(struct drm_fb_helper *helper, int crtc_count, int max_conn); @@ -79,4 +100,7 @@ void drm_fb_helper_fill_var(struct fb_info *info, struct drm_framebuffer *fb, uint32_t fb_width, uint32_t fb_height); void drm_fb_helper_fill_fix(struct fb_info *info, uint32_t pitch); +int drm_fb_helper_add_connector(struct drm_connector *connector); +int drm_fb_helper_parse_command_line(struct drm_device *dev); + #endif -- cgit v1.2.3 From d1f8297a96b0d70f17704296a6666468f2087ce6 Mon Sep 17 00:00:00 2001 From: Sascha Hlusiak Date: Sat, 26 Sep 2009 20:28:07 -0700 Subject: Revert "sit: stateless autoconf for isatap" This reverts commit 645069299a1c7358cf7330afe293f07552f11a5d. While the code does not actually break anything, it does not completely follow RFC5214 yet. After talking back with Fred L. Templin, I agree that completing the ISATAP specific RS/RA code, would pollute the kernel a lot with code that is better implemented in userspace. The kernel should not send RS packages for ISATAP at all. Signed-off-by: Sascha Hlusiak Acked-by: Fred L. Templin Signed-off-by: David S. Miller --- include/linux/if_tunnel.h | 2 +- include/net/ipip.h | 7 ------ net/ipv6/ndisc.c | 1 - net/ipv6/sit.c | 58 ----------------------------------------------- 4 files changed, 1 insertion(+), 67 deletions(-) (limited to 'include') diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 5eb9b0f857e0..5a9aae4adb44 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -44,7 +44,7 @@ struct ip_tunnel_prl { __u16 flags; __u16 __reserved; __u32 datalen; - __u32 rs_delay; + __u32 __reserved2; /* data follows */ }; diff --git a/include/net/ipip.h b/include/net/ipip.h index 76e3ea6e2fe5..87acf8f3a155 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -27,18 +27,11 @@ struct ip_tunnel unsigned int prl_count; /* # of entries in PRL */ }; -/* ISATAP: default interval between RS in secondy */ -#define IPTUNNEL_RS_DEFAULT_DELAY (900) - struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry *next; __be32 addr; u16 flags; - unsigned long rs_delay; - struct timer_list rs_timer; - struct ip_tunnel *tunnel; - spinlock_t lock; }; #define IPTUNNEL_XMIT() do { \ diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 498b9b0b0fad..f74e4e2cdd06 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -658,7 +658,6 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, &icmp6h, NULL, send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0); } -EXPORT_SYMBOL(ndisc_send_rs); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fcb539628847..d65e0c496cc0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -15,7 +15,6 @@ * Roger Venning : 6to4 support * Nate Thompson : 6to4 support * Fred Templin : isatap support - * Sascha Hlusiak : stateless autoconf for isatap */ #include @@ -223,44 +222,6 @@ failed: return NULL; } -static void ipip6_tunnel_rs_timer(unsigned long data) -{ - struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *) data; - struct inet6_dev *ifp; - struct inet6_ifaddr *addr; - - spin_lock(&p->lock); - ifp = __in6_dev_get(p->tunnel->dev); - - read_lock_bh(&ifp->lock); - for (addr = ifp->addr_list; addr; addr = addr->if_next) { - struct in6_addr rtr; - - if (!(ipv6_addr_type(&addr->addr) & IPV6_ADDR_LINKLOCAL)) - continue; - - /* Send RS to guessed linklocal address of router - * - * Better: send to ff02::2 encapsuled in unicast directly - * to router-v4 instead of guessing the v6 address. - * - * Cisco/Windows seem to not set the u/l bit correctly, - * so we won't guess right. - */ - ipv6_addr_set(&rtr, htonl(0xFE800000), 0, 0, 0); - if (!__ipv6_isatap_ifid(rtr.s6_addr + 8, - p->addr)) { - ndisc_send_rs(p->tunnel->dev, &addr->addr, &rtr); - } - } - read_unlock_bh(&ifp->lock); - - mod_timer(&p->rs_timer, jiffies + HZ * p->rs_delay); - spin_unlock(&p->lock); - - return; -} - static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { @@ -319,7 +280,6 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; - kp[c].rs_delay = prl->rs_delay; c++; if (kprl.addr != htonl(INADDR_ANY)) break; @@ -369,23 +329,11 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) } p->next = t->prl; - p->tunnel = t; t->prl = p; t->prl_count++; - - spin_lock_init(&p->lock); - setup_timer(&p->rs_timer, ipip6_tunnel_rs_timer, (unsigned long) p); update: p->addr = a->addr; p->flags = a->flags; - p->rs_delay = a->rs_delay; - if (p->rs_delay == 0) - p->rs_delay = IPTUNNEL_RS_DEFAULT_DELAY; - spin_lock(&p->lock); - del_timer(&p->rs_timer); - if (p->flags & PRL_DEFAULT) - mod_timer(&p->rs_timer, jiffies + 1); - spin_unlock(&p->lock); out: write_unlock(&ipip6_lock); return err; @@ -404,9 +352,6 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) if ((*p)->addr == a->addr) { x = *p; *p = x->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); kfree(x); t->prl_count--; goto out; @@ -417,9 +362,6 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) while (t->prl) { x = t->prl; t->prl = t->prl->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); kfree(x); t->prl_count--; } -- cgit v1.2.3 From 74bf2ad508efa93db4254c9da9c7238da44e2c58 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 28 Sep 2009 15:31:10 +1000 Subject: drm/kms: make fb helper work for all drivers. This initialises the fb helper with the connector helper, so that the fb cmdline code works for intel as well. Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_fb_helper.c | 1 - drivers/gpu/drm/radeon/radeon_connectors.c | 64 +++++++++++++++++++----------- include/drm/drm_crtc_helper.h | 4 +- 3 files changed, 43 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 10d810ef8faa..83d7b7d03863 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -47,7 +47,6 @@ int drm_fb_helper_add_connector(struct drm_connector *connector) return -ENOMEM; return 0; - } EXPORT_SYMBOL(drm_fb_helper_add_connector); diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index db155d5e60ce..e376be47a4a0 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -808,7 +808,9 @@ radeon_add_atom_connector(struct drm_device *dev, switch (connector_type) { case DRM_MODE_CONNECTOR_VGA: drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "VGA"); if (!radeon_connector->ddc_bus) @@ -821,7 +823,9 @@ radeon_add_atom_connector(struct drm_device *dev, break; case DRM_MODE_CONNECTOR_DVIA: drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "DVI"); if (!radeon_connector->ddc_bus) @@ -841,7 +845,9 @@ radeon_add_atom_connector(struct drm_device *dev, radeon_dig_connector->igp_lane_info = igp_lane_info; radeon_connector->con_priv = radeon_dig_connector; drm_connector_init(dev, &radeon_connector->base, &radeon_dvi_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "DVI"); if (!radeon_connector->ddc_bus) @@ -865,7 +871,9 @@ radeon_add_atom_connector(struct drm_device *dev, radeon_dig_connector->igp_lane_info = igp_lane_info; radeon_connector->con_priv = radeon_dig_connector; drm_connector_init(dev, &radeon_connector->base, &radeon_dvi_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "HDMI"); if (!radeon_connector->ddc_bus) @@ -884,7 +892,9 @@ radeon_add_atom_connector(struct drm_device *dev, radeon_dig_connector->igp_lane_info = igp_lane_info; radeon_connector->con_priv = radeon_dig_connector; drm_connector_init(dev, &radeon_connector->base, &radeon_dvi_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "DP"); if (!radeon_connector->ddc_bus) @@ -897,12 +907,14 @@ radeon_add_atom_connector(struct drm_device *dev, case DRM_MODE_CONNECTOR_9PinDIN: if (radeon_tv == 1) { drm_connector_init(dev, &radeon_connector->base, &radeon_tv_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_tv_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_tv_connector_helper_funcs); + if (ret) + goto failed; + radeon_connector->dac_load_detect = true; + drm_connector_attach_property(&radeon_connector->base, + rdev->mode_info.load_detect_property, + 1); } - radeon_connector->dac_load_detect = true; - drm_connector_attach_property(&radeon_connector->base, - rdev->mode_info.load_detect_property, - 1); break; case DRM_MODE_CONNECTOR_LVDS: radeon_dig_connector = kzalloc(sizeof(struct radeon_connector_atom_dig), GFP_KERNEL); @@ -912,7 +924,9 @@ radeon_add_atom_connector(struct drm_device *dev, radeon_dig_connector->igp_lane_info = igp_lane_info; radeon_connector->con_priv = radeon_dig_connector; drm_connector_init(dev, &radeon_connector->base, &radeon_lvds_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "LVDS"); if (!radeon_connector->ddc_bus) @@ -926,10 +940,6 @@ radeon_add_atom_connector(struct drm_device *dev, break; } - ret = drm_fb_helper_add_connector(connector); - if (ret) - goto failed; - connector->display_info.subpixel_order = subpixel_order; drm_sysfs_connector_add(connector); return; @@ -978,7 +988,9 @@ radeon_add_legacy_connector(struct drm_device *dev, switch (connector_type) { case DRM_MODE_CONNECTOR_VGA: drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "VGA"); if (!radeon_connector->ddc_bus) @@ -991,7 +1003,9 @@ radeon_add_legacy_connector(struct drm_device *dev, break; case DRM_MODE_CONNECTOR_DVIA: drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "DVI"); if (!radeon_connector->ddc_bus) @@ -1005,7 +1019,9 @@ radeon_add_legacy_connector(struct drm_device *dev, case DRM_MODE_CONNECTOR_DVII: case DRM_MODE_CONNECTOR_DVID: drm_connector_init(dev, &radeon_connector->base, &radeon_dvi_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "DVI"); if (!radeon_connector->ddc_bus) @@ -1022,7 +1038,9 @@ radeon_add_legacy_connector(struct drm_device *dev, case DRM_MODE_CONNECTOR_9PinDIN: if (radeon_tv == 1) { drm_connector_init(dev, &radeon_connector->base, &radeon_tv_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_tv_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_tv_connector_helper_funcs); + if (ret) + goto failed; radeon_connector->dac_load_detect = true; drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.load_detect_property, @@ -1031,7 +1049,9 @@ radeon_add_legacy_connector(struct drm_device *dev, break; case DRM_MODE_CONNECTOR_LVDS: drm_connector_init(dev, &radeon_connector->base, &radeon_lvds_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs); + ret = drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs); + if (ret) + goto failed; if (i2c_bus->valid) { radeon_connector->ddc_bus = radeon_i2c_create(dev, i2c_bus, "LVDS"); if (!radeon_connector->ddc_bus) @@ -1044,10 +1064,6 @@ radeon_add_legacy_connector(struct drm_device *dev, break; } - ret = drm_fb_helper_add_connector(connector); - if (ret) - goto failed; - connector->display_info.subpixel_order = subpixel_order; drm_sysfs_connector_add(connector); return; diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h index 4c8dacaf4f58..ef47dfd8e5e9 100644 --- a/include/drm/drm_crtc_helper.h +++ b/include/drm/drm_crtc_helper.h @@ -39,6 +39,7 @@ #include +#include "drm_fb_helper.h" struct drm_crtc_helper_funcs { /* * Control power levels on the CRTC. If the mode passed in is @@ -119,10 +120,11 @@ static inline void drm_encoder_helper_add(struct drm_encoder *encoder, encoder->helper_private = (void *)funcs; } -static inline void drm_connector_helper_add(struct drm_connector *connector, +static inline int drm_connector_helper_add(struct drm_connector *connector, const struct drm_connector_helper_funcs *funcs) { connector->helper_private = (void *)funcs; + return drm_fb_helper_add_connector(connector); } extern int drm_helper_resume_force_mode(struct drm_device *dev); -- cgit v1.2.3 From 55138e0bc29c0751e2152df9ad35deea542f29b3 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 29 Sep 2009 13:31:31 -0400 Subject: ext4: Adjust ext4_da_writepages() to write out larger contiguous chunks Work around problems in the writeback code to force out writebacks in larger chunks than just 4mb, which is just too small. This also works around limitations in the ext4 block allocator, which can't allocate more than 2048 blocks at a time. So we need to defeat the round-robin characteristics of the writeback code and try to write out as many blocks in one inode before allowing the writeback code to move on to another inode. We add a a new per-filesystem tunable, max_writeback_mb_bump, which caps this to a default of 128mb per inode. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + fs/ext4/inode.c | 105 +++++++++++++++++++++++++++++++++++++++----- fs/ext4/super.c | 3 ++ include/trace/events/ext4.h | 14 ++++-- 4 files changed, 107 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e227eea23f05..a58438e18d0b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -942,6 +942,7 @@ struct ext4_sb_info { unsigned int s_mb_stats; unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; + unsigned int s_max_writeback_mb_bump; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5fb72a98ccbe..20e2d704dc2e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1144,6 +1144,64 @@ static int check_block_validity(struct inode *inode, const char *msg, return 0; } +/* + * Return the number of dirty pages in the given inode starting at + * page frame idx. + */ +static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, + unsigned int max_pages) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t index; + struct pagevec pvec; + pgoff_t num = 0; + int i, nr_pages, done = 0; + + if (max_pages == 0) + return 0; + pagevec_init(&pvec, 0); + while (!done) { + index = idx; + nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY, + (pgoff_t)PAGEVEC_SIZE); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + struct buffer_head *bh, *head; + + lock_page(page); + if (unlikely(page->mapping != mapping) || + !PageDirty(page) || + PageWriteback(page) || + page->index != idx) { + done = 1; + unlock_page(page); + break; + } + head = page_buffers(page); + bh = head; + do { + if (!buffer_delay(bh) && + !buffer_unwritten(bh)) { + done = 1; + break; + } + } while ((bh = bh->b_this_page) != head); + unlock_page(page); + if (done) + break; + idx++; + num++; + if (num >= max_pages) + break; + } + pagevec_release(&pvec); + } + return num; +} + /* * The ext4_get_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -2743,8 +2801,10 @@ static int ext4_da_writepages(struct address_space *mapping, int no_nrwrite_index_update; int pages_written = 0; long pages_skipped; + unsigned int max_pages; int range_cyclic, cycled = 1, io_done = 0; - int needed_blocks, ret = 0, nr_to_writebump = 0; + int needed_blocks, ret = 0; + long desired_nr_to_write, nr_to_writebump = 0; loff_t range_start = wbc->range_start; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); @@ -2771,16 +2831,6 @@ static int ext4_da_writepages(struct address_space *mapping, if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) return -EROFS; - /* - * Make sure nr_to_write is >= sbi->s_mb_stream_request - * This make sure small files blocks are allocated in - * single attempt. This ensure that small files - * get less fragmented. - */ - if (wbc->nr_to_write < sbi->s_mb_stream_request) { - nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write; - wbc->nr_to_write = sbi->s_mb_stream_request; - } if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; @@ -2795,6 +2845,36 @@ static int ext4_da_writepages(struct address_space *mapping, } else index = wbc->range_start >> PAGE_CACHE_SHIFT; + /* + * This works around two forms of stupidity. The first is in + * the writeback code, which caps the maximum number of pages + * written to be 1024 pages. This is wrong on multiple + * levels; different architectues have a different page size, + * which changes the maximum amount of data which gets + * written. Secondly, 4 megabytes is way too small. XFS + * forces this value to be 16 megabytes by multiplying + * nr_to_write parameter by four, and then relies on its + * allocator to allocate larger extents to make them + * contiguous. Unfortunately this brings us to the second + * stupidity, which is that ext4's mballoc code only allocates + * at most 2048 blocks. So we force contiguous writes up to + * the number of dirty blocks in the inode, or + * sbi->max_writeback_mb_bump whichever is smaller. + */ + max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT); + if (!range_cyclic && range_whole) + desired_nr_to_write = wbc->nr_to_write * 8; + else + desired_nr_to_write = ext4_num_dirty_pages(inode, index, + max_pages); + if (desired_nr_to_write > max_pages) + desired_nr_to_write = max_pages; + + if (wbc->nr_to_write < desired_nr_to_write) { + nr_to_writebump = desired_nr_to_write - wbc->nr_to_write; + wbc->nr_to_write = desired_nr_to_write; + } + mpd.wbc = wbc; mpd.inode = mapping->host; @@ -2914,7 +2994,8 @@ retry: out_writepages: if (!no_nrwrite_index_update) wbc->no_nrwrite_index_update = 0; - wbc->nr_to_write -= nr_to_writebump; + if (wbc->nr_to_write > nr_to_writebump) + wbc->nr_to_write -= nr_to_writebump; wbc->range_start = range_start; trace_ext4_da_writepages_result(inode, wbc, ret, pages_written); return ret; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index df539ba27779..16817737ba52 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2197,6 +2197,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); +EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump); static struct attribute *ext4_attrs[] = { ATTR_LIST(delayed_allocation_blocks), @@ -2210,6 +2211,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_order2_req), ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), + ATTR_LIST(max_writeback_mb_bump), NULL, }; @@ -2679,6 +2681,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sbi->s_stripe = ext4_get_stripe_size(sbi); + sbi->s_max_writeback_mb_bump = 128; /* * set up enough so that it can read an inode diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index c1bd8f1e8b94..7c6bbb7198a3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -236,6 +236,7 @@ TRACE_EVENT(ext4_da_writepages, __field( char, for_kupdate ) __field( char, for_reclaim ) __field( char, range_cyclic ) + __field( pgoff_t, writeback_index ) ), TP_fast_assign( @@ -249,15 +250,17 @@ TRACE_EVENT(ext4_da_writepages, __entry->for_kupdate = wbc->for_kupdate; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; + __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d", + TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d writeback_index %lu", jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->nonblocking, __entry->for_kupdate, __entry->for_reclaim, - __entry->range_cyclic) + __entry->range_cyclic, + (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_pages, @@ -309,6 +312,7 @@ TRACE_EVENT(ext4_da_writepages_result, __field( char, encountered_congestion ) __field( char, more_io ) __field( char, no_nrwrite_index_update ) + __field( pgoff_t, writeback_index ) ), TP_fast_assign( @@ -320,14 +324,16 @@ TRACE_EVENT(ext4_da_writepages_result, __entry->encountered_congestion = wbc->encountered_congestion; __entry->more_io = wbc->more_io; __entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update; + __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d", + TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d writeback_index %lu", jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->encountered_congestion, __entry->more_io, - __entry->no_nrwrite_index_update) + __entry->no_nrwrite_index_update, + (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_begin, -- cgit v1.2.3 From 8f1546cadf7ac5e9a40d54089a1c7302264ec49b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 28 Sep 2009 15:26:43 +0200 Subject: wext: add back wireless/ dir in sysfs for cfg80211 interfaces The move away from having drivers assign wireless handlers, in favour of making cfg80211 assign them, broke the sysfs registration (the wireless/ dir went missing) because the handlers are now assigned only after registration, which is too late. Fix this by special-casing cfg80211-based devices, all of which are required to have an ieee80211_ptr, in the sysfs code, and also using get_wireless_stats() to have the same values reported as in procfs. Signed-off-by: Johannes Berg Reported-by: Hugh Dickins Tested-by: Hugh Dickins Signed-off-by: John W. Linville --- include/net/wext.h | 1 + net/core/net-sysfs.c | 12 +++++------- net/wireless/wext.c | 2 +- 3 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/wext.h b/include/net/wext.h index 6d76a39a9c5b..3f2b94de2cfa 100644 --- a/include/net/wext.h +++ b/include/net/wext.h @@ -14,6 +14,7 @@ extern int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cm void __user *arg); extern int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, unsigned long arg); +extern struct iw_statistics *get_wireless_stats(struct net_device *dev); #else static inline int wext_proc_init(struct net *net) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 7d4c57523b09..821d30918cfc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include "net-sysfs.h" @@ -363,15 +363,13 @@ static ssize_t wireless_show(struct device *d, char *buf, char *)) { struct net_device *dev = to_net_dev(d); - const struct iw_statistics *iw = NULL; + const struct iw_statistics *iw; ssize_t ret = -EINVAL; read_lock(&dev_base_lock); if (dev_isalive(dev)) { - if (dev->wireless_handlers && - dev->wireless_handlers->get_wireless_stats) - iw = dev->wireless_handlers->get_wireless_stats(dev); - if (iw != NULL) + iw = get_wireless_stats(dev); + if (iw) ret = (*format)(iw, buf); } read_unlock(&dev_base_lock); @@ -505,7 +503,7 @@ int netdev_register_kobject(struct net_device *net) *groups++ = &netstat_group; #ifdef CONFIG_WIRELESS_EXT_SYSFS - if (net->wireless_handlers && net->wireless_handlers->get_wireless_stats) + if (net->wireless_handlers || net->ieee80211_ptr) *groups++ = &wireless_group; #endif #endif /* CONFIG_SYSFS */ diff --git a/net/wireless/wext.c b/net/wireless/wext.c index ac4ac26b53ce..60fe57761ca9 100644 --- a/net/wireless/wext.c +++ b/net/wireless/wext.c @@ -470,7 +470,7 @@ static iw_handler get_handler(struct net_device *dev, unsigned int cmd) /* * Get statistics out of the driver */ -static struct iw_statistics *get_wireless_stats(struct net_device *dev) +struct iw_statistics *get_wireless_stats(struct net_device *dev) { /* New location */ if ((dev->wireless_handlers != NULL) && -- cgit v1.2.3 From 827b4649d4626bf97b203b4bcd69476bb9b4e760 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 29 Sep 2009 00:10:41 +0200 Subject: PM / PCMCIA: Drop second argument of pcmcia_socket_dev_suspend() pcmcia_socket_dev_suspend() doesn't use its second argument, so it may be dropped safely. This change is necessary for the subsequent yenta suspend/resume fix. Signed-off-by: Rafael J. Wysocki Cc: stable@kernel.org --- drivers/pcmcia/at91_cf.c | 2 +- drivers/pcmcia/au1000_generic.c | 2 +- drivers/pcmcia/bfin_cf_pcmcia.c | 2 +- drivers/pcmcia/cs.c | 2 +- drivers/pcmcia/i82092.c | 2 +- drivers/pcmcia/i82365.c | 2 +- drivers/pcmcia/m32r_cfc.c | 2 +- drivers/pcmcia/m32r_pcc.c | 2 +- drivers/pcmcia/m8xx_pcmcia.c | 2 +- drivers/pcmcia/omap_cf.c | 2 +- drivers/pcmcia/pd6729.c | 2 +- drivers/pcmcia/pxa2xx_base.c | 2 +- drivers/pcmcia/sa1100_generic.c | 2 +- drivers/pcmcia/sa1111_generic.c | 2 +- drivers/pcmcia/tcic.c | 2 +- drivers/pcmcia/vrc4171_card.c | 2 +- drivers/pcmcia/yenta_socket.c | 2 +- include/pcmcia/ss.h | 2 +- 18 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c index 9e1140f085fd..e1dccedc5960 100644 --- a/drivers/pcmcia/at91_cf.c +++ b/drivers/pcmcia/at91_cf.c @@ -363,7 +363,7 @@ static int at91_cf_suspend(struct platform_device *pdev, pm_message_t mesg) struct at91_cf_socket *cf = platform_get_drvdata(pdev); struct at91_cf_data *board = cf->board; - pcmcia_socket_dev_suspend(&pdev->dev, mesg); + pcmcia_socket_dev_suspend(&pdev->dev); if (device_may_wakeup(&pdev->dev)) { enable_irq_wake(board->det_pin); if (board->irq_pin) diff --git a/drivers/pcmcia/au1000_generic.c b/drivers/pcmcia/au1000_generic.c index 90013341cd5f..02088704ac2c 100644 --- a/drivers/pcmcia/au1000_generic.c +++ b/drivers/pcmcia/au1000_generic.c @@ -515,7 +515,7 @@ static int au1x00_drv_pcmcia_probe(struct platform_device *dev) static int au1x00_drv_pcmcia_suspend(struct platform_device *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int au1x00_drv_pcmcia_resume(struct platform_device *dev) diff --git a/drivers/pcmcia/bfin_cf_pcmcia.c b/drivers/pcmcia/bfin_cf_pcmcia.c index b59d4115d20f..300b368605c9 100644 --- a/drivers/pcmcia/bfin_cf_pcmcia.c +++ b/drivers/pcmcia/bfin_cf_pcmcia.c @@ -302,7 +302,7 @@ static int __devexit bfin_cf_remove(struct platform_device *pdev) static int bfin_cf_suspend(struct platform_device *pdev, pm_message_t mesg) { - return pcmcia_socket_dev_suspend(&pdev->dev, mesg); + return pcmcia_socket_dev_suspend(&pdev->dev); } static int bfin_cf_resume(struct platform_device *pdev) diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c index 0660ad182589..934d4bee39a0 100644 --- a/drivers/pcmcia/cs.c +++ b/drivers/pcmcia/cs.c @@ -101,7 +101,7 @@ EXPORT_SYMBOL(pcmcia_socket_list_rwsem); static int socket_resume(struct pcmcia_socket *skt); static int socket_suspend(struct pcmcia_socket *skt); -int pcmcia_socket_dev_suspend(struct device *dev, pm_message_t state) +int pcmcia_socket_dev_suspend(struct device *dev) { struct pcmcia_socket *socket; diff --git a/drivers/pcmcia/i82092.c b/drivers/pcmcia/i82092.c index 46561face128..a04f21c8170f 100644 --- a/drivers/pcmcia/i82092.c +++ b/drivers/pcmcia/i82092.c @@ -42,7 +42,7 @@ MODULE_DEVICE_TABLE(pci, i82092aa_pci_ids); #ifdef CONFIG_PM static int i82092aa_socket_suspend (struct pci_dev *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int i82092aa_socket_resume (struct pci_dev *dev) diff --git a/drivers/pcmcia/i82365.c b/drivers/pcmcia/i82365.c index 40d4953e4b12..b906abe26ad0 100644 --- a/drivers/pcmcia/i82365.c +++ b/drivers/pcmcia/i82365.c @@ -1241,7 +1241,7 @@ static int pcic_init(struct pcmcia_socket *s) static int i82365_drv_pcmcia_suspend(struct platform_device *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int i82365_drv_pcmcia_resume(struct platform_device *dev) diff --git a/drivers/pcmcia/m32r_cfc.c b/drivers/pcmcia/m32r_cfc.c index 62b4ecc97c46..d1d89c4491ad 100644 --- a/drivers/pcmcia/m32r_cfc.c +++ b/drivers/pcmcia/m32r_cfc.c @@ -699,7 +699,7 @@ static struct pccard_operations pcc_operations = { static int cfc_drv_pcmcia_suspend(struct platform_device *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int cfc_drv_pcmcia_resume(struct platform_device *dev) diff --git a/drivers/pcmcia/m32r_pcc.c b/drivers/pcmcia/m32r_pcc.c index 12034b41d196..a0655839c8d3 100644 --- a/drivers/pcmcia/m32r_pcc.c +++ b/drivers/pcmcia/m32r_pcc.c @@ -675,7 +675,7 @@ static struct pccard_operations pcc_operations = { static int pcc_drv_pcmcia_suspend(struct platform_device *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int pcc_drv_pcmcia_resume(struct platform_device *dev) diff --git a/drivers/pcmcia/m8xx_pcmcia.c b/drivers/pcmcia/m8xx_pcmcia.c index d1ad0966392d..c69f2c4fe520 100644 --- a/drivers/pcmcia/m8xx_pcmcia.c +++ b/drivers/pcmcia/m8xx_pcmcia.c @@ -1296,7 +1296,7 @@ static int m8xx_remove(struct of_device *ofdev) #ifdef CONFIG_PM static int m8xx_suspend(struct platform_device *pdev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&pdev->dev, state); + return pcmcia_socket_dev_suspend(&pdev->dev); } static int m8xx_resume(struct platform_device *pdev) diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c index f3736398900e..68570bc3ac86 100644 --- a/drivers/pcmcia/omap_cf.c +++ b/drivers/pcmcia/omap_cf.c @@ -334,7 +334,7 @@ static int __exit omap_cf_remove(struct platform_device *pdev) static int omap_cf_suspend(struct platform_device *pdev, pm_message_t mesg) { - return pcmcia_socket_dev_suspend(&pdev->dev, mesg); + return pcmcia_socket_dev_suspend(&pdev->dev); } static int omap_cf_resume(struct platform_device *pdev) diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c index 8bed1dab9039..1c39d3438f20 100644 --- a/drivers/pcmcia/pd6729.c +++ b/drivers/pcmcia/pd6729.c @@ -758,7 +758,7 @@ static void __devexit pd6729_pci_remove(struct pci_dev *dev) #ifdef CONFIG_PM static int pd6729_socket_suspend(struct pci_dev *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int pd6729_socket_resume(struct pci_dev *dev) diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c index 87e22ef8eb02..0e35acb1366b 100644 --- a/drivers/pcmcia/pxa2xx_base.c +++ b/drivers/pcmcia/pxa2xx_base.c @@ -302,7 +302,7 @@ static int pxa2xx_drv_pcmcia_remove(struct platform_device *dev) static int pxa2xx_drv_pcmcia_suspend(struct device *dev) { - return pcmcia_socket_dev_suspend(dev, PMSG_SUSPEND); + return pcmcia_socket_dev_suspend(dev); } static int pxa2xx_drv_pcmcia_resume(struct device *dev) diff --git a/drivers/pcmcia/sa1100_generic.c b/drivers/pcmcia/sa1100_generic.c index d8da5ac844e9..2d0e99751530 100644 --- a/drivers/pcmcia/sa1100_generic.c +++ b/drivers/pcmcia/sa1100_generic.c @@ -89,7 +89,7 @@ static int sa11x0_drv_pcmcia_remove(struct platform_device *dev) static int sa11x0_drv_pcmcia_suspend(struct platform_device *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int sa11x0_drv_pcmcia_resume(struct platform_device *dev) diff --git a/drivers/pcmcia/sa1111_generic.c b/drivers/pcmcia/sa1111_generic.c index 401052a21ce8..4be4e172ffa1 100644 --- a/drivers/pcmcia/sa1111_generic.c +++ b/drivers/pcmcia/sa1111_generic.c @@ -159,7 +159,7 @@ static int __devexit pcmcia_remove(struct sa1111_dev *dev) static int pcmcia_suspend(struct sa1111_dev *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int pcmcia_resume(struct sa1111_dev *dev) diff --git a/drivers/pcmcia/tcic.c b/drivers/pcmcia/tcic.c index 8eb04230fec7..582413fcb62f 100644 --- a/drivers/pcmcia/tcic.c +++ b/drivers/pcmcia/tcic.c @@ -366,7 +366,7 @@ static int __init get_tcic_id(void) static int tcic_drv_pcmcia_suspend(struct platform_device *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int tcic_drv_pcmcia_resume(struct platform_device *dev) diff --git a/drivers/pcmcia/vrc4171_card.c b/drivers/pcmcia/vrc4171_card.c index d4ad50d737b0..c9fcbdc164ea 100644 --- a/drivers/pcmcia/vrc4171_card.c +++ b/drivers/pcmcia/vrc4171_card.c @@ -707,7 +707,7 @@ __setup("vrc4171_card=", vrc4171_card_setup); static int vrc4171_card_suspend(struct platform_device *dev, pm_message_t state) { - return pcmcia_socket_dev_suspend(&dev->dev, state); + return pcmcia_socket_dev_suspend(&dev->dev); } static int vrc4171_card_resume(struct platform_device *dev) diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c index b459e87a30ac..6fa1ed8f2b2f 100644 --- a/drivers/pcmcia/yenta_socket.c +++ b/drivers/pcmcia/yenta_socket.c @@ -1230,7 +1230,7 @@ static int yenta_dev_suspend (struct pci_dev *dev, pm_message_t state) struct yenta_socket *socket = pci_get_drvdata(dev); int ret; - ret = pcmcia_socket_dev_suspend(&dev->dev, state); + ret = pcmcia_socket_dev_suspend(&dev->dev); if (socket) { if (socket->type && socket->type->save_state) diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h index 9a3b49865173..d696a692d94a 100644 --- a/include/pcmcia/ss.h +++ b/include/pcmcia/ss.h @@ -279,7 +279,7 @@ extern struct pccard_resource_ops pccard_iodyn_ops; extern struct pccard_resource_ops pccard_nonstatic_ops; /* socket drivers are expected to use these callbacks in their .drv struct */ -extern int pcmcia_socket_dev_suspend(struct device *dev, pm_message_t state); +extern int pcmcia_socket_dev_suspend(struct device *dev); extern int pcmcia_socket_dev_resume(struct device *dev); /* socket drivers use this callback in their IRQ handler */ -- cgit v1.2.3 From 296c355cd6443d89fa251885a8d78778fe111dc4 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 30 Sep 2009 00:32:42 -0400 Subject: ext4: Use tracepoints for mb_history trace file The /proc/fs/ext4//mb_history was maintained manually, and had a number of problems: it required a largish amount of memory to be allocated for each ext4 filesystem, and the s_mb_history_lock introduced a CPU contention problem. By ripping out the mb_history code and replacing it with ftrace tracepoints, and we get more functionality: timestamps, event filtering, the ability to correlate mballoc history with other ext4 tracepoints, etc. Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/proc.txt | 1 - fs/ext4/ext4.h | 14 +- fs/ext4/mballoc.c | 301 ++----------------------------------- fs/ext4/mballoc.h | 33 ---- fs/ext4/super.c | 18 +-- include/trace/events/ext4.h | 163 ++++++++++++++++++++ 6 files changed, 182 insertions(+), 348 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index b5aee7838a00..2c48f945546b 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1113,7 +1113,6 @@ Table 1-12: Files in /proc/fs/ext4/ .............................................................................. File Content mb_groups details of multiblock allocator buddy cache of free blocks - mb_history multiblock allocation history .............................................................................. diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b491576e11c3..c508cf7be75c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -65,6 +65,12 @@ typedef __u32 ext4_lblk_t; /* data type for block group number */ typedef unsigned int ext4_group_t; +/* + * Flags used in mballoc's allocation_context flags field. + * + * Also used to show what's going on for debugging purposes when the + * flag field is exported via the traceport interface + */ /* prefer goal again. length */ #define EXT4_MB_HINT_MERGE 0x0001 @@ -971,14 +977,6 @@ struct ext4_sb_info { unsigned long s_mb_last_group; unsigned long s_mb_last_start; - /* history to debug policy */ - struct ext4_mb_history *s_mb_history; - int s_mb_history_cur; - int s_mb_history_max; - int s_mb_history_num; - spinlock_t s_mb_history_lock; - int s_mb_history_filter; - /* stats for buddy allocator */ spinlock_t s_mb_pa_lock; atomic_t s_bal_reqs; /* number of reqs with len > 1 */ diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3e2320e66721..bba12824defa 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2096,207 +2096,6 @@ out: return err; } -#ifdef EXT4_MB_HISTORY -struct ext4_mb_proc_session { - struct ext4_mb_history *history; - struct super_block *sb; - int start; - int max; -}; - -static void *ext4_mb_history_skip_empty(struct ext4_mb_proc_session *s, - struct ext4_mb_history *hs, - int first) -{ - if (hs == s->history + s->max) - hs = s->history; - if (!first && hs == s->history + s->start) - return NULL; - while (hs->orig.fe_len == 0) { - hs++; - if (hs == s->history + s->max) - hs = s->history; - if (hs == s->history + s->start) - return NULL; - } - return hs; -} - -static void *ext4_mb_seq_history_start(struct seq_file *seq, loff_t *pos) -{ - struct ext4_mb_proc_session *s = seq->private; - struct ext4_mb_history *hs; - int l = *pos; - - if (l == 0) - return SEQ_START_TOKEN; - hs = ext4_mb_history_skip_empty(s, s->history + s->start, 1); - if (!hs) - return NULL; - while (--l && (hs = ext4_mb_history_skip_empty(s, ++hs, 0)) != NULL); - return hs; -} - -static void *ext4_mb_seq_history_next(struct seq_file *seq, void *v, - loff_t *pos) -{ - struct ext4_mb_proc_session *s = seq->private; - struct ext4_mb_history *hs = v; - - ++*pos; - if (v == SEQ_START_TOKEN) - return ext4_mb_history_skip_empty(s, s->history + s->start, 1); - else - return ext4_mb_history_skip_empty(s, ++hs, 0); -} - -static int ext4_mb_seq_history_show(struct seq_file *seq, void *v) -{ - char buf[25], buf2[25], buf3[25], *fmt; - struct ext4_mb_history *hs = v; - - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%-5s %-8s %-23s %-23s %-23s %-5s " - "%-5s %-2s %-6s %-5s %-5s %-6s\n", - "pid", "inode", "original", "goal", "result", "found", - "grps", "cr", "flags", "merge", "tail", "broken"); - return 0; - } - - if (hs->op == EXT4_MB_HISTORY_ALLOC) { - fmt = "%-5u %-8u %-23s %-23s %-23s %-5u %-5u %-2u " - "0x%04x %-5s %-5u %-6u\n"; - sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len, - hs->result.fe_logical); - sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group, - hs->orig.fe_start, hs->orig.fe_len, - hs->orig.fe_logical); - sprintf(buf3, "%u/%d/%u@%u", hs->goal.fe_group, - hs->goal.fe_start, hs->goal.fe_len, - hs->goal.fe_logical); - seq_printf(seq, fmt, hs->pid, hs->ino, buf, buf3, buf2, - hs->found, hs->groups, hs->cr, hs->flags, - hs->merged ? "M" : "", hs->tail, - hs->buddy ? 1 << hs->buddy : 0); - } else if (hs->op == EXT4_MB_HISTORY_PREALLOC) { - fmt = "%-5u %-8u %-23s %-23s %-23s\n"; - sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len, - hs->result.fe_logical); - sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group, - hs->orig.fe_start, hs->orig.fe_len, - hs->orig.fe_logical); - seq_printf(seq, fmt, hs->pid, hs->ino, buf, "", buf2); - } else if (hs->op == EXT4_MB_HISTORY_DISCARD) { - sprintf(buf2, "%u/%d/%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len); - seq_printf(seq, "%-5u %-8u %-23s discard\n", - hs->pid, hs->ino, buf2); - } else if (hs->op == EXT4_MB_HISTORY_FREE) { - sprintf(buf2, "%u/%d/%u", hs->result.fe_group, - hs->result.fe_start, hs->result.fe_len); - seq_printf(seq, "%-5u %-8u %-23s free\n", - hs->pid, hs->ino, buf2); - } - return 0; -} - -static void ext4_mb_seq_history_stop(struct seq_file *seq, void *v) -{ -} - -static const struct seq_operations ext4_mb_seq_history_ops = { - .start = ext4_mb_seq_history_start, - .next = ext4_mb_seq_history_next, - .stop = ext4_mb_seq_history_stop, - .show = ext4_mb_seq_history_show, -}; - -static int ext4_mb_seq_history_open(struct inode *inode, struct file *file) -{ - struct super_block *sb = PDE(inode)->data; - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_mb_proc_session *s; - int rc; - int size; - - if (unlikely(sbi->s_mb_history == NULL)) - return -ENOMEM; - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (s == NULL) - return -ENOMEM; - s->sb = sb; - size = sizeof(struct ext4_mb_history) * sbi->s_mb_history_max; - s->history = kmalloc(size, GFP_KERNEL); - if (s->history == NULL) { - kfree(s); - return -ENOMEM; - } - - spin_lock(&sbi->s_mb_history_lock); - memcpy(s->history, sbi->s_mb_history, size); - s->max = sbi->s_mb_history_max; - s->start = sbi->s_mb_history_cur % s->max; - spin_unlock(&sbi->s_mb_history_lock); - - rc = seq_open(file, &ext4_mb_seq_history_ops); - if (rc == 0) { - struct seq_file *m = (struct seq_file *)file->private_data; - m->private = s; - } else { - kfree(s->history); - kfree(s); - } - return rc; - -} - -static int ext4_mb_seq_history_release(struct inode *inode, struct file *file) -{ - struct seq_file *seq = (struct seq_file *)file->private_data; - struct ext4_mb_proc_session *s = seq->private; - kfree(s->history); - kfree(s); - return seq_release(inode, file); -} - -static ssize_t ext4_mb_seq_history_write(struct file *file, - const char __user *buffer, - size_t count, loff_t *ppos) -{ - struct seq_file *seq = (struct seq_file *)file->private_data; - struct ext4_mb_proc_session *s = seq->private; - struct super_block *sb = s->sb; - char str[32]; - int value; - - if (count >= sizeof(str)) { - printk(KERN_ERR "EXT4-fs: %s string too long, max %u bytes\n", - "mb_history", (int)sizeof(str)); - return -EOVERFLOW; - } - - if (copy_from_user(str, buffer, count)) - return -EFAULT; - - value = simple_strtol(str, NULL, 0); - if (value < 0) - return -ERANGE; - EXT4_SB(sb)->s_mb_history_filter = value; - - return count; -} - -static const struct file_operations ext4_mb_seq_history_fops = { - .owner = THIS_MODULE, - .open = ext4_mb_seq_history_open, - .read = seq_read, - .write = ext4_mb_seq_history_write, - .llseek = seq_lseek, - .release = ext4_mb_seq_history_release, -}; - static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = seq->private; @@ -2396,82 +2195,6 @@ static const struct file_operations ext4_mb_seq_groups_fops = { .release = seq_release, }; -static void ext4_mb_history_release(struct super_block *sb) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - - if (sbi->s_proc != NULL) { - remove_proc_entry("mb_groups", sbi->s_proc); - if (sbi->s_mb_history_max) - remove_proc_entry("mb_history", sbi->s_proc); - } - kfree(sbi->s_mb_history); -} - -static void ext4_mb_history_init(struct super_block *sb) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - int i; - - if (sbi->s_proc != NULL) { - if (sbi->s_mb_history_max) - proc_create_data("mb_history", S_IRUGO, sbi->s_proc, - &ext4_mb_seq_history_fops, sb); - proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, - &ext4_mb_seq_groups_fops, sb); - } - - sbi->s_mb_history_cur = 0; - spin_lock_init(&sbi->s_mb_history_lock); - i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history); - sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL; - /* if we can't allocate history, then we simple won't use it */ -} - -static noinline_for_stack void -ext4_mb_store_history(struct ext4_allocation_context *ac) -{ - struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - struct ext4_mb_history h; - - if (sbi->s_mb_history == NULL) - return; - - if (!(ac->ac_op & sbi->s_mb_history_filter)) - return; - - h.op = ac->ac_op; - h.pid = current->pid; - h.ino = ac->ac_inode ? ac->ac_inode->i_ino : 0; - h.orig = ac->ac_o_ex; - h.result = ac->ac_b_ex; - h.flags = ac->ac_flags; - h.found = ac->ac_found; - h.groups = ac->ac_groups_scanned; - h.cr = ac->ac_criteria; - h.tail = ac->ac_tail; - h.buddy = ac->ac_buddy; - h.merged = 0; - if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) { - if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && - ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) - h.merged = 1; - h.goal = ac->ac_g_ex; - h.result = ac->ac_f_ex; - } - - spin_lock(&sbi->s_mb_history_lock); - memcpy(sbi->s_mb_history + sbi->s_mb_history_cur, &h, sizeof(h)); - if (++sbi->s_mb_history_cur >= sbi->s_mb_history_max) - sbi->s_mb_history_cur = 0; - spin_unlock(&sbi->s_mb_history_lock); -} - -#else -#define ext4_mb_history_release(sb) -#define ext4_mb_history_init(sb) -#endif - /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, @@ -2690,7 +2413,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; - sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT; sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC; sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); @@ -2708,7 +2430,9 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) spin_lock_init(&lg->lg_prealloc_lock); } - ext4_mb_history_init(sb); + if (sbi->s_proc) + proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, + &ext4_mb_seq_groups_fops, sb); if (sbi->s_journal) sbi->s_journal->j_commit_callback = release_blocks_on_commit; @@ -2788,7 +2512,8 @@ int ext4_mb_release(struct super_block *sb) } free_percpu(sbi->s_locality_groups); - ext4_mb_history_release(sb); + if (sbi->s_proc) + remove_proc_entry("mb_groups", sbi->s_proc); return 0; } @@ -3274,7 +2999,10 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) atomic_inc(&sbi->s_bal_breaks); } - ext4_mb_store_history(ac); + if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) + trace_ext4_mballoc_alloc(ac); + else + trace_ext4_mballoc_prealloc(ac); } /* @@ -3774,7 +3502,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, if (ac) { ac->ac_sb = sb; ac->ac_inode = pa->pa_inode; - ac->ac_op = EXT4_MB_HISTORY_DISCARD; } while (bit < end) { @@ -3794,7 +3521,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, ac->ac_b_ex.fe_start = bit; ac->ac_b_ex.fe_len = next - bit; ac->ac_b_ex.fe_logical = 0; - ext4_mb_store_history(ac); + trace_ext4_mballoc_discard(ac); } trace_ext4_mb_release_inode_pa(ac, pa, grp_blk_start + bit, @@ -3829,9 +3556,6 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, ext4_group_t group; ext4_grpblk_t bit; - if (ac) - ac->ac_op = EXT4_MB_HISTORY_DISCARD; - trace_ext4_mb_release_group_pa(ac, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); @@ -3846,7 +3570,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, ac->ac_b_ex.fe_start = bit; ac->ac_b_ex.fe_len = pa->pa_len; ac->ac_b_ex.fe_logical = 0; - ext4_mb_store_history(ac); + trace_ext4_mballoc_discard(ac); } return 0; @@ -4737,7 +4461,6 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode, ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); if (ac) { - ac->ac_op = EXT4_MB_HISTORY_FREE; ac->ac_inode = inode; ac->ac_sb = sb; } @@ -4804,7 +4527,7 @@ do_more: ac->ac_b_ex.fe_group = block_group; ac->ac_b_ex.fe_start = bit; ac->ac_b_ex.fe_len = count; - ext4_mb_store_history(ac); + trace_ext4_mballoc_free(ac); } err = ext4_mb_load_buddy(sb, block_group, &e4b); diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 14f25f253112..0ca811061bc7 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -52,18 +52,8 @@ extern u8 mb_enable_debug; #define mb_debug(n, fmt, a...) #endif -/* - * with EXT4_MB_HISTORY mballoc stores last N allocations in memory - * and you can monitor it in /proc/fs/ext4//mb_history - */ -#define EXT4_MB_HISTORY #define EXT4_MB_HISTORY_ALLOC 1 /* allocation */ #define EXT4_MB_HISTORY_PREALLOC 2 /* preallocated blocks used */ -#define EXT4_MB_HISTORY_DISCARD 4 /* preallocation discarded */ -#define EXT4_MB_HISTORY_FREE 8 /* free */ - -#define EXT4_MB_HISTORY_DEFAULT (EXT4_MB_HISTORY_ALLOC | \ - EXT4_MB_HISTORY_PREALLOC) /* * How long mballoc can look for a best extent (in found extents) @@ -217,22 +207,6 @@ struct ext4_allocation_context { #define AC_STATUS_FOUND 2 #define AC_STATUS_BREAK 3 -struct ext4_mb_history { - struct ext4_free_extent orig; /* orig allocation */ - struct ext4_free_extent goal; /* goal allocation */ - struct ext4_free_extent result; /* result allocation */ - unsigned pid; - unsigned ino; - __u16 found; /* how many extents have been found */ - __u16 groups; /* how many groups have been scanned */ - __u16 tail; /* what tail broke some buddy */ - __u16 buddy; /* buddy the tail ^^^ broke */ - __u16 flags; - __u8 cr:3; /* which phase the result extent was found at */ - __u8 op:4; - __u8 merged:1; -}; - struct ext4_buddy { struct page *bd_buddy_page; void *bd_buddy; @@ -247,13 +221,6 @@ struct ext4_buddy { #define EXT4_MB_BITMAP(e4b) ((e4b)->bd_bitmap) #define EXT4_MB_BUDDY(e4b) ((e4b)->bd_buddy) -#ifndef EXT4_MB_HISTORY -static inline void ext4_mb_store_history(struct ext4_allocation_context *ac) -{ - return; -} -#endif - #define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e5b206a043a5..12e726a7073f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -50,13 +50,6 @@ #define CREATE_TRACE_POINTS #include -static int default_mb_history_length = 1000; - -module_param_named(default_mb_history_length, default_mb_history_length, - int, 0644); -MODULE_PARM_DESC(default_mb_history_length, - "Default number of entries saved for mb_history"); - struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; @@ -1079,7 +1072,7 @@ enum { Opt_journal_update, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, - Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length, + Opt_data_err_abort, Opt_data_err_ignore, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, @@ -1126,7 +1119,6 @@ static const match_table_t tokens = { {Opt_data_writeback, "data=writeback"}, {Opt_data_err_abort, "data_err=abort"}, {Opt_data_err_ignore, "data_err=ignore"}, - {Opt_mb_history_length, "mb_history_length=%u"}, {Opt_offusrjquota, "usrjquota="}, {Opt_usrjquota, "usrjquota=%s"}, {Opt_offgrpjquota, "grpjquota="}, @@ -1367,13 +1359,6 @@ static int parse_options(char *options, struct super_block *sb, case Opt_data_err_ignore: clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT); break; - case Opt_mb_history_length: - if (match_int(&args[0], &option)) - return 0; - if (option < 0) - return 0; - sbi->s_mb_history_max = option; - break; #ifdef CONFIG_QUOTA case Opt_usrjquota: qtype = USRQUOTA; @@ -2435,7 +2420,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; - sbi->s_mb_history_max = default_mb_history_length; set_opt(sbi->s_mount_opt, BARRIER); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 7c6bbb7198a3..b8320256dc5d 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -743,6 +743,169 @@ TRACE_EVENT(ext4_alloc_da_blocks, __entry->data_blocks, __entry->meta_blocks) ); +TRACE_EVENT(ext4_mballoc_alloc, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u16, found ) + __field( __u16, groups ) + __field( __u16, buddy ) + __field( __u16, flags ) + __field( __u16, tail ) + __field( __u8, cr ) + __field( __u32, orig_logical ) + __field( int, orig_start ) + __field( __u32, orig_group ) + __field( int, orig_len ) + __field( __u32, goal_logical ) + __field( int, goal_start ) + __field( __u32, goal_group ) + __field( int, goal_len ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->found = ac->ac_found; + __entry->flags = ac->ac_flags; + __entry->groups = ac->ac_groups_scanned; + __entry->buddy = ac->ac_buddy; + __entry->tail = ac->ac_tail; + __entry->cr = ac->ac_criteria; + __entry->orig_logical = ac->ac_o_ex.fe_logical; + __entry->orig_start = ac->ac_o_ex.fe_start; + __entry->orig_group = ac->ac_o_ex.fe_group; + __entry->orig_len = ac->ac_o_ex.fe_len; + __entry->goal_logical = ac->ac_g_ex.fe_logical; + __entry->goal_start = ac->ac_g_ex.fe_start; + __entry->goal_group = ac->ac_g_ex.fe_group; + __entry->goal_len = ac->ac_g_ex.fe_len; + __entry->result_logical = ac->ac_f_ex.fe_logical; + __entry->result_start = ac->ac_f_ex.fe_start; + __entry->result_group = ac->ac_f_ex.fe_group; + __entry->result_len = ac->ac_f_ex.fe_len; + ), + + TP_printk("dev %s inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " + "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x " + "tail %u broken %u", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->orig_group, __entry->orig_start, + __entry->orig_len, __entry->orig_logical, + __entry->goal_group, __entry->goal_start, + __entry->goal_len, __entry->goal_logical, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical, + __entry->found, __entry->groups, __entry->cr, + __entry->flags, __entry->tail, + __entry->buddy ? 1 << __entry->buddy : 0) +); + +TRACE_EVENT(ext4_mballoc_prealloc, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u32, orig_logical ) + __field( int, orig_start ) + __field( __u32, orig_group ) + __field( int, orig_len ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->orig_logical = ac->ac_o_ex.fe_logical; + __entry->orig_start = ac->ac_o_ex.fe_start; + __entry->orig_group = ac->ac_o_ex.fe_group; + __entry->orig_len = ac->ac_o_ex.fe_len; + __entry->result_logical = ac->ac_b_ex.fe_logical; + __entry->result_start = ac->ac_b_ex.fe_start; + __entry->result_group = ac->ac_b_ex.fe_group; + __entry->result_len = ac->ac_b_ex.fe_len; + ), + + TP_printk("dev %s inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->orig_group, __entry->orig_start, + __entry->orig_len, __entry->orig_logical, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical) +); + +TRACE_EVENT(ext4_mballoc_discard, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->result_logical = ac->ac_b_ex.fe_logical; + __entry->result_start = ac->ac_b_ex.fe_start; + __entry->result_group = ac->ac_b_ex.fe_group; + __entry->result_len = ac->ac_b_ex.fe_len; + ), + + TP_printk("dev %s inode %lu extent %u/%d/%u@%u ", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical) +); + +TRACE_EVENT(ext4_mballoc_free, + TP_PROTO(struct ext4_allocation_context *ac), + + TP_ARGS(ac), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u32, result_logical ) + __field( int, result_start ) + __field( __u32, result_group ) + __field( int, result_len ) + ), + + TP_fast_assign( + __entry->dev = ac->ac_inode->i_sb->s_dev; + __entry->ino = ac->ac_inode->i_ino; + __entry->result_logical = ac->ac_b_ex.fe_logical; + __entry->result_start = ac->ac_b_ex.fe_start; + __entry->result_group = ac->ac_b_ex.fe_group; + __entry->result_len = ac->ac_b_ex.fe_len; + ), + + TP_printk("dev %s inode %lu extent %u/%d/%u@%u ", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->result_group, __entry->result_start, + __entry->result_len, __entry->result_logical) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ -- cgit v1.2.3 From bf6993276f74d46776f35c45ddef29b981b1d1c6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 30 Sep 2009 00:32:06 -0400 Subject: jbd2: Use tracepoints for history file The /proc/fs/jbd2//history was maintained manually; by using tracepoints, we can get all of the existing functionality of the /proc file plus extra capabilities thanks to the ftrace infrastructure. We save memory as a bonus. Signed-off-by: "Theodore Ts'o" --- fs/jbd2/checkpoint.c | 7 ++ fs/jbd2/commit.c | 59 +++++++------- fs/jbd2/journal.c | 187 +++----------------------------------------- include/linux/jbd2.h | 27 ++----- include/trace/events/jbd2.h | 78 ++++++++++++++++++ 5 files changed, 130 insertions(+), 228 deletions(-) (limited to 'include') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 5d70b3e6d49b..ca0f5eb62b20 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -643,6 +643,7 @@ out: int __jbd2_journal_remove_checkpoint(struct journal_head *jh) { + struct transaction_chp_stats_s *stats; transaction_t *transaction; journal_t *journal; int ret = 0; @@ -679,6 +680,12 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) /* OK, that was the last buffer for the transaction: we can now safely remove this transaction from the log */ + stats = &transaction->t_chp_stats; + if (stats->cs_chp_time) + stats->cs_chp_time = jbd2_time_diff(stats->cs_chp_time, + jiffies); + trace_jbd2_checkpoint_stats(journal->j_fs_dev->bd_dev, + transaction->t_tid, stats); __jbd2_journal_drop_transaction(journal, transaction); kfree(transaction); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 26d991ddc1e6..d4cfd6d2779e 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -410,10 +410,10 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (commit_transaction->t_synchronous_commit) write_op = WRITE_SYNC_PLUG; trace_jbd2_commit_locking(journal, commit_transaction); - stats.u.run.rs_wait = commit_transaction->t_max_wait; - stats.u.run.rs_locked = jiffies; - stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start, - stats.u.run.rs_locked); + stats.run.rs_wait = commit_transaction->t_max_wait; + stats.run.rs_locked = jiffies; + stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start, + stats.run.rs_locked); spin_lock(&commit_transaction->t_handle_lock); while (commit_transaction->t_updates) { @@ -486,9 +486,9 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_switch_revoke_table(journal); trace_jbd2_commit_flushing(journal, commit_transaction); - stats.u.run.rs_flushing = jiffies; - stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked, - stats.u.run.rs_flushing); + stats.run.rs_flushing = jiffies; + stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked, + stats.run.rs_flushing); commit_transaction->t_state = T_FLUSH; journal->j_committing_transaction = commit_transaction; @@ -523,11 +523,11 @@ void jbd2_journal_commit_transaction(journal_t *journal) spin_unlock(&journal->j_state_lock); trace_jbd2_commit_logging(journal, commit_transaction); - stats.u.run.rs_logging = jiffies; - stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing, - stats.u.run.rs_logging); - stats.u.run.rs_blocks = commit_transaction->t_outstanding_credits; - stats.u.run.rs_blocks_logged = 0; + stats.run.rs_logging = jiffies; + stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing, + stats.run.rs_logging); + stats.run.rs_blocks = commit_transaction->t_outstanding_credits; + stats.run.rs_blocks_logged = 0; J_ASSERT(commit_transaction->t_nr_buffers <= commit_transaction->t_outstanding_credits); @@ -695,7 +695,7 @@ start_journal_io: submit_bh(write_op, bh); } cond_resched(); - stats.u.run.rs_blocks_logged += bufs; + stats.run.rs_blocks_logged += bufs; /* Force a new descriptor to be generated next time round the loop. */ @@ -988,33 +988,30 @@ restart_loop: J_ASSERT(commit_transaction->t_state == T_COMMIT); commit_transaction->t_start = jiffies; - stats.u.run.rs_logging = jbd2_time_diff(stats.u.run.rs_logging, - commit_transaction->t_start); + stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging, + commit_transaction->t_start); /* - * File the transaction for history + * File the transaction statistics */ - stats.ts_type = JBD2_STATS_RUN; stats.ts_tid = commit_transaction->t_tid; - stats.u.run.rs_handle_count = commit_transaction->t_handle_count; - spin_lock(&journal->j_history_lock); - memcpy(journal->j_history + journal->j_history_cur, &stats, - sizeof(stats)); - if (++journal->j_history_cur == journal->j_history_max) - journal->j_history_cur = 0; + stats.run.rs_handle_count = commit_transaction->t_handle_count; + trace_jbd2_run_stats(journal->j_fs_dev->bd_dev, + commit_transaction->t_tid, &stats.run); /* * Calculate overall stats */ + spin_lock(&journal->j_history_lock); journal->j_stats.ts_tid++; - journal->j_stats.u.run.rs_wait += stats.u.run.rs_wait; - journal->j_stats.u.run.rs_running += stats.u.run.rs_running; - journal->j_stats.u.run.rs_locked += stats.u.run.rs_locked; - journal->j_stats.u.run.rs_flushing += stats.u.run.rs_flushing; - journal->j_stats.u.run.rs_logging += stats.u.run.rs_logging; - journal->j_stats.u.run.rs_handle_count += stats.u.run.rs_handle_count; - journal->j_stats.u.run.rs_blocks += stats.u.run.rs_blocks; - journal->j_stats.u.run.rs_blocks_logged += stats.u.run.rs_blocks_logged; + journal->j_stats.run.rs_wait += stats.run.rs_wait; + journal->j_stats.run.rs_running += stats.run.rs_running; + journal->j_stats.run.rs_locked += stats.run.rs_locked; + journal->j_stats.run.rs_flushing += stats.run.rs_flushing; + journal->j_stats.run.rs_logging += stats.run.rs_logging; + journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count; + journal->j_stats.run.rs_blocks += stats.run.rs_blocks; + journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged; spin_unlock(&journal->j_history_lock); commit_transaction->t_state = T_FINISHED; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 977a8dafb76d..761af77491f5 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -676,153 +676,6 @@ struct jbd2_stats_proc_session { int max; }; -static void *jbd2_history_skip_empty(struct jbd2_stats_proc_session *s, - struct transaction_stats_s *ts, - int first) -{ - if (ts == s->stats + s->max) - ts = s->stats; - if (!first && ts == s->stats + s->start) - return NULL; - while (ts->ts_type == 0) { - ts++; - if (ts == s->stats + s->max) - ts = s->stats; - if (ts == s->stats + s->start) - return NULL; - } - return ts; - -} - -static void *jbd2_seq_history_start(struct seq_file *seq, loff_t *pos) -{ - struct jbd2_stats_proc_session *s = seq->private; - struct transaction_stats_s *ts; - int l = *pos; - - if (l == 0) - return SEQ_START_TOKEN; - ts = jbd2_history_skip_empty(s, s->stats + s->start, 1); - if (!ts) - return NULL; - l--; - while (l) { - ts = jbd2_history_skip_empty(s, ++ts, 0); - if (!ts) - break; - l--; - } - return ts; -} - -static void *jbd2_seq_history_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct jbd2_stats_proc_session *s = seq->private; - struct transaction_stats_s *ts = v; - - ++*pos; - if (v == SEQ_START_TOKEN) - return jbd2_history_skip_empty(s, s->stats + s->start, 1); - else - return jbd2_history_skip_empty(s, ++ts, 0); -} - -static int jbd2_seq_history_show(struct seq_file *seq, void *v) -{ - struct transaction_stats_s *ts = v; - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%-4s %-5s %-5s %-5s %-5s %-5s %-5s %-6s %-5s " - "%-5s %-5s %-5s %-5s %-5s\n", "R/C", "tid", - "wait", "run", "lock", "flush", "log", "hndls", - "block", "inlog", "ctime", "write", "drop", - "close"); - return 0; - } - if (ts->ts_type == JBD2_STATS_RUN) - seq_printf(seq, "%-4s %-5lu %-5u %-5u %-5u %-5u %-5u " - "%-6lu %-5lu %-5lu\n", "R", ts->ts_tid, - jiffies_to_msecs(ts->u.run.rs_wait), - jiffies_to_msecs(ts->u.run.rs_running), - jiffies_to_msecs(ts->u.run.rs_locked), - jiffies_to_msecs(ts->u.run.rs_flushing), - jiffies_to_msecs(ts->u.run.rs_logging), - ts->u.run.rs_handle_count, - ts->u.run.rs_blocks, - ts->u.run.rs_blocks_logged); - else if (ts->ts_type == JBD2_STATS_CHECKPOINT) - seq_printf(seq, "%-4s %-5lu %48s %-5u %-5lu %-5lu %-5lu\n", - "C", ts->ts_tid, " ", - jiffies_to_msecs(ts->u.chp.cs_chp_time), - ts->u.chp.cs_written, ts->u.chp.cs_dropped, - ts->u.chp.cs_forced_to_close); - else - J_ASSERT(0); - return 0; -} - -static void jbd2_seq_history_stop(struct seq_file *seq, void *v) -{ -} - -static const struct seq_operations jbd2_seq_history_ops = { - .start = jbd2_seq_history_start, - .next = jbd2_seq_history_next, - .stop = jbd2_seq_history_stop, - .show = jbd2_seq_history_show, -}; - -static int jbd2_seq_history_open(struct inode *inode, struct file *file) -{ - journal_t *journal = PDE(inode)->data; - struct jbd2_stats_proc_session *s; - int rc, size; - - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (s == NULL) - return -ENOMEM; - size = sizeof(struct transaction_stats_s) * journal->j_history_max; - s->stats = kmalloc(size, GFP_KERNEL); - if (s->stats == NULL) { - kfree(s); - return -ENOMEM; - } - spin_lock(&journal->j_history_lock); - memcpy(s->stats, journal->j_history, size); - s->max = journal->j_history_max; - s->start = journal->j_history_cur % s->max; - spin_unlock(&journal->j_history_lock); - - rc = seq_open(file, &jbd2_seq_history_ops); - if (rc == 0) { - struct seq_file *m = file->private_data; - m->private = s; - } else { - kfree(s->stats); - kfree(s); - } - return rc; - -} - -static int jbd2_seq_history_release(struct inode *inode, struct file *file) -{ - struct seq_file *seq = file->private_data; - struct jbd2_stats_proc_session *s = seq->private; - - kfree(s->stats); - kfree(s); - return seq_release(inode, file); -} - -static struct file_operations jbd2_seq_history_fops = { - .owner = THIS_MODULE, - .open = jbd2_seq_history_open, - .read = seq_read, - .llseek = seq_lseek, - .release = jbd2_seq_history_release, -}; - static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos) { return *pos ? NULL : SEQ_START_TOKEN; @@ -839,29 +692,29 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v) if (v != SEQ_START_TOKEN) return 0; - seq_printf(seq, "%lu transaction, each upto %u blocks\n", + seq_printf(seq, "%lu transaction, each up to %u blocks\n", s->stats->ts_tid, s->journal->j_max_transaction_buffers); if (s->stats->ts_tid == 0) return 0; seq_printf(seq, "average: \n %ums waiting for transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_wait / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid)); seq_printf(seq, " %ums running transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_running / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid)); seq_printf(seq, " %ums transaction was being locked\n", - jiffies_to_msecs(s->stats->u.run.rs_locked / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid)); seq_printf(seq, " %ums flushing data (in ordered mode)\n", - jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid)); seq_printf(seq, " %ums logging transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid)); seq_printf(seq, " %lluus average transaction commit time\n", div_u64(s->journal->j_average_commit_time, 1000)); seq_printf(seq, " %lu handles per transaction\n", - s->stats->u.run.rs_handle_count / s->stats->ts_tid); + s->stats->run.rs_handle_count / s->stats->ts_tid); seq_printf(seq, " %lu blocks per transaction\n", - s->stats->u.run.rs_blocks / s->stats->ts_tid); + s->stats->run.rs_blocks / s->stats->ts_tid); seq_printf(seq, " %lu logged blocks per transaction\n", - s->stats->u.run.rs_blocks_logged / s->stats->ts_tid); + s->stats->run.rs_blocks_logged / s->stats->ts_tid); return 0; } @@ -931,8 +784,6 @@ static void jbd2_stats_proc_init(journal_t *journal) { journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { - proc_create_data("history", S_IRUGO, journal->j_proc_entry, - &jbd2_seq_history_fops, journal); proc_create_data("info", S_IRUGO, journal->j_proc_entry, &jbd2_seq_info_fops, journal); } @@ -941,27 +792,9 @@ static void jbd2_stats_proc_init(journal_t *journal) static void jbd2_stats_proc_exit(journal_t *journal) { remove_proc_entry("info", journal->j_proc_entry); - remove_proc_entry("history", journal->j_proc_entry); remove_proc_entry(journal->j_devname, proc_jbd2_stats); } -static void journal_init_stats(journal_t *journal) -{ - int size; - - if (!proc_jbd2_stats) - return; - - journal->j_history_max = 100; - size = sizeof(struct transaction_stats_s) * journal->j_history_max; - journal->j_history = kzalloc(size, GFP_KERNEL); - if (!journal->j_history) { - journal->j_history_max = 0; - return; - } - spin_lock_init(&journal->j_history_lock); -} - /* * Management for journal control blocks: functions to create and * destroy journal_t structures, and to initialise and read existing @@ -1006,7 +839,7 @@ static journal_t * journal_init_common (void) goto fail; } - journal_init_stats(journal); + spin_lock_init(&journal->j_history_lock); return journal; fail: diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 52695d3dfd0b..f1011f7f3d41 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -464,9 +464,9 @@ struct handle_s */ struct transaction_chp_stats_s { unsigned long cs_chp_time; - unsigned long cs_forced_to_close; - unsigned long cs_written; - unsigned long cs_dropped; + __u32 cs_forced_to_close; + __u32 cs_written; + __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It @@ -668,23 +668,16 @@ struct transaction_run_stats_s { unsigned long rs_flushing; unsigned long rs_logging; - unsigned long rs_handle_count; - unsigned long rs_blocks; - unsigned long rs_blocks_logged; + __u32 rs_handle_count; + __u32 rs_blocks; + __u32 rs_blocks_logged; }; struct transaction_stats_s { - int ts_type; unsigned long ts_tid; - union { - struct transaction_run_stats_s run; - struct transaction_chp_stats_s chp; - } u; + struct transaction_run_stats_s run; }; -#define JBD2_STATS_RUN 1 -#define JBD2_STATS_CHECKPOINT 2 - static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { @@ -988,12 +981,6 @@ struct journal_s /* * Journal statistics */ - struct transaction_stats_s *j_history; - int j_history_max; - int j_history_cur; - /* - * Protect the transactions statistics history - */ spinlock_t j_history_lock; struct proc_dir_entry *j_proc_entry; struct transaction_stats_s j_stats; diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index b851f0b4701c..3c60b75adb9e 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -7,6 +7,9 @@ #include #include +struct transaction_chp_stats_s; +struct transaction_run_stats_s; + TRACE_EVENT(jbd2_checkpoint, TP_PROTO(journal_t *journal, int result), @@ -162,6 +165,81 @@ TRACE_EVENT(jbd2_submit_inode_data, jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) ); +TRACE_EVENT(jbd2_run_stats, + TP_PROTO(dev_t dev, unsigned long tid, + struct transaction_run_stats_s *stats), + + TP_ARGS(dev, tid, stats), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( unsigned long, tid ) + __field( unsigned long, wait ) + __field( unsigned long, running ) + __field( unsigned long, locked ) + __field( unsigned long, flushing ) + __field( unsigned long, logging ) + __field( __u32, handle_count ) + __field( __u32, blocks ) + __field( __u32, blocks_logged ) + ), + + TP_fast_assign( + __entry->dev = dev; + __entry->tid = tid; + __entry->wait = stats->rs_wait; + __entry->running = stats->rs_running; + __entry->locked = stats->rs_locked; + __entry->flushing = stats->rs_flushing; + __entry->logging = stats->rs_logging; + __entry->handle_count = stats->rs_handle_count; + __entry->blocks = stats->rs_blocks; + __entry->blocks_logged = stats->rs_blocks_logged; + ), + + TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u " + "logging %u handle_count %u blocks %u blocks_logged %u", + jbd2_dev_to_name(__entry->dev), __entry->tid, + jiffies_to_msecs(__entry->wait), + jiffies_to_msecs(__entry->running), + jiffies_to_msecs(__entry->locked), + jiffies_to_msecs(__entry->flushing), + jiffies_to_msecs(__entry->logging), + __entry->handle_count, __entry->blocks, + __entry->blocks_logged) +); + +TRACE_EVENT(jbd2_checkpoint_stats, + TP_PROTO(dev_t dev, unsigned long tid, + struct transaction_chp_stats_s *stats), + + TP_ARGS(dev, tid, stats), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( unsigned long, tid ) + __field( unsigned long, chp_time ) + __field( __u32, forced_to_close ) + __field( __u32, written ) + __field( __u32, dropped ) + ), + + TP_fast_assign( + __entry->dev = dev; + __entry->tid = tid; + __entry->chp_time = stats->cs_chp_time; + __entry->forced_to_close= stats->cs_forced_to_close; + __entry->written = stats->cs_written; + __entry->dropped = stats->cs_dropped; + ), + + TP_printk("dev %s tid %lu chp_time %u forced_to_close %u " + "written %u dropped %u", + jbd2_dev_to_name(__entry->dev), __entry->tid, + jiffies_to_msecs(__entry->chp_time), + __entry->forced_to_close, __entry->written, __entry->dropped) +); + #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 0ef122494020521309be855bfdeeb41f34bf8c94 Mon Sep 17 00:00:00 2001 From: Josh Stone Date: Wed, 30 Sep 2009 00:51:22 -0400 Subject: ext4: Add a stub for mpage_da_data in the trace header The tracepoint ext4_da_write_pages has a struct mpage_da_data* parameter, but that struct is only defined in fs/ext4/ext4.h. This patch adds a forward declaration for that struct, so this tracepoint header can still be used by tools like SystemTap. This is a continuation of the fix in commit 3661d286. http://sourceware.org/bugzilla/show_bug.cgi?id=10703 Signed-off-by: Josh Stone Signed-off-by: "Theodore Ts'o" --- include/trace/events/ext4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index b8320256dc5d..d09550bf3f95 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -11,6 +11,7 @@ struct ext4_allocation_context; struct ext4_allocation_request; struct ext4_prealloc_space; struct ext4_inode_info; +struct mpage_da_data; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) -- cgit v1.2.3 From 9fcd66e572b94974365a9119b073e0a43d496eb7 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Fri, 18 Sep 2009 13:04:58 +0200 Subject: MIPS: BCM63xx: Add serial driver for bcm63xx integrated UART. Signed-off-by: Maxime Bizon Acked-by: Greg Kroah-Hartman Signed-off-by: Ralf Baechle --- arch/mips/bcm63xx/Makefile | 2 +- arch/mips/bcm63xx/boards/board_bcm963xx.c | 3 + arch/mips/bcm63xx/dev-uart.c | 41 + .../include/asm/mach-bcm63xx/bcm63xx_dev_uart.h | 6 + drivers/serial/Kconfig | 19 + drivers/serial/Makefile | 1 + drivers/serial/bcm63xx_uart.c | 890 +++++++++++++++++++++ include/linux/serial_core.h | 3 + 8 files changed, 964 insertions(+), 1 deletion(-) create mode 100644 arch/mips/bcm63xx/dev-uart.c create mode 100644 arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h create mode 100644 drivers/serial/bcm63xx_uart.c (limited to 'include') diff --git a/arch/mips/bcm63xx/Makefile b/arch/mips/bcm63xx/Makefile index aaa585cf26e3..cff75de8449b 100644 --- a/arch/mips/bcm63xx/Makefile +++ b/arch/mips/bcm63xx/Makefile @@ -1,5 +1,5 @@ obj-y += clk.o cpu.o cs.o gpio.o irq.o prom.o setup.o timer.o \ - dev-dsp.o dev-enet.o + dev-dsp.o dev-enet.o dev-uart.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-y += boards/ diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index 12add0ca9fed..5a327f3a7167 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #define PFX "board_bcm963xx: " @@ -792,6 +793,8 @@ int __init board_register_devices(void) { u32 val; + bcm63xx_uart_register(); + if (board.has_enet0 && !board_get_mac_address(board.enet0.mac_addr)) bcm63xx_enet_register(0, &board.enet0); diff --git a/arch/mips/bcm63xx/dev-uart.c b/arch/mips/bcm63xx/dev-uart.c new file mode 100644 index 000000000000..5f3d89c4a988 --- /dev/null +++ b/arch/mips/bcm63xx/dev-uart.c @@ -0,0 +1,41 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2008 Maxime Bizon + */ + +#include +#include +#include +#include +#include + +static struct resource uart_resources[] = { + { + .start = -1, /* filled at runtime */ + .end = -1, /* filled at runtime */ + .flags = IORESOURCE_MEM, + }, + { + .start = -1, /* filled at runtime */ + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bcm63xx_uart_device = { + .name = "bcm63xx_uart", + .id = 0, + .num_resources = ARRAY_SIZE(uart_resources), + .resource = uart_resources, +}; + +int __init bcm63xx_uart_register(void) +{ + uart_resources[0].start = bcm63xx_regset_address(RSET_UART0); + uart_resources[0].end = uart_resources[0].start; + uart_resources[0].end += RSET_UART_SIZE - 1; + uart_resources[1].start = bcm63xx_get_irq_number(IRQ_UART0); + return platform_device_register(&bcm63xx_uart_device); +} diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h new file mode 100644 index 000000000000..bf348f573bbc --- /dev/null +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h @@ -0,0 +1,6 @@ +#ifndef BCM63XX_DEV_UART_H_ +#define BCM63XX_DEV_UART_H_ + +int bcm63xx_uart_register(void); + +#endif /* BCM63XX_DEV_UART_H_ */ diff --git a/drivers/serial/Kconfig b/drivers/serial/Kconfig index 03422ce878cf..e70712044a7e 100644 --- a/drivers/serial/Kconfig +++ b/drivers/serial/Kconfig @@ -1458,4 +1458,23 @@ config SERIAL_TIMBERDALE ---help--- Add support for UART controller on timberdale. +config SERIAL_BCM63XX + tristate "bcm63xx serial port support" + select SERIAL_CORE + depends on BCM63XX + help + If you have a bcm63xx CPU, you can enable its onboard + serial port by enabling this options. + + To compile this driver as a module, choose M here: the + module will be called bcm963xx_uart. + +config SERIAL_BCM63XX_CONSOLE + bool "Console on bcm63xx serial port" + depends on SERIAL_BCM63XX=y + select SERIAL_CORE_CONSOLE + help + If you have enabled the serial port on the bcm63xx CPU + you can make it the console by answering Y to this option. + endmenu diff --git a/drivers/serial/Makefile b/drivers/serial/Makefile index 97f6fcc8b432..d21d5dd5d048 100644 --- a/drivers/serial/Makefile +++ b/drivers/serial/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_SERIAL_CLPS711X) += clps711x.o obj-$(CONFIG_SERIAL_PXA) += pxa.o obj-$(CONFIG_SERIAL_PNX8XXX) += pnx8xxx_uart.o obj-$(CONFIG_SERIAL_SA1100) += sa1100.o +obj-$(CONFIG_SERIAL_BCM63XX) += bcm63xx_uart.o obj-$(CONFIG_SERIAL_BFIN) += bfin_5xx.o obj-$(CONFIG_SERIAL_BFIN_SPORT) += bfin_sport_uart.o obj-$(CONFIG_SERIAL_SAMSUNG) += samsung.o diff --git a/drivers/serial/bcm63xx_uart.c b/drivers/serial/bcm63xx_uart.c new file mode 100644 index 000000000000..beddaa6e9069 --- /dev/null +++ b/drivers/serial/bcm63xx_uart.c @@ -0,0 +1,890 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Derived from many drivers using generic_serial interface. + * + * Copyright (C) 2008 Maxime Bizon + * + * Serial driver for BCM63xx integrated UART. + * + * Hardware flow control was _not_ tested since I only have RX/TX on + * my board. + */ + +#if defined(CONFIG_SERIAL_BCM63XX_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) +#define SUPPORT_SYSRQ +#endif + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define BCM63XX_NR_UARTS 1 + +static struct uart_port ports[BCM63XX_NR_UARTS]; + +/* + * rx interrupt mask / stat + * + * mask: + * - rx fifo full + * - rx fifo above threshold + * - rx fifo not empty for too long + */ +#define UART_RX_INT_MASK (UART_IR_MASK(UART_IR_RXOVER) | \ + UART_IR_MASK(UART_IR_RXTHRESH) | \ + UART_IR_MASK(UART_IR_RXTIMEOUT)) + +#define UART_RX_INT_STAT (UART_IR_STAT(UART_IR_RXOVER) | \ + UART_IR_STAT(UART_IR_RXTHRESH) | \ + UART_IR_STAT(UART_IR_RXTIMEOUT)) + +/* + * tx interrupt mask / stat + * + * mask: + * - tx fifo empty + * - tx fifo below threshold + */ +#define UART_TX_INT_MASK (UART_IR_MASK(UART_IR_TXEMPTY) | \ + UART_IR_MASK(UART_IR_TXTRESH)) + +#define UART_TX_INT_STAT (UART_IR_STAT(UART_IR_TXEMPTY) | \ + UART_IR_STAT(UART_IR_TXTRESH)) + +/* + * external input interrupt + * + * mask: any edge on CTS, DCD + */ +#define UART_EXTINP_INT_MASK (UART_EXTINP_IRMASK(UART_EXTINP_IR_CTS) | \ + UART_EXTINP_IRMASK(UART_EXTINP_IR_DCD)) + +/* + * handy uart register accessor + */ +static inline unsigned int bcm_uart_readl(struct uart_port *port, + unsigned int offset) +{ + return bcm_readl(port->membase + offset); +} + +static inline void bcm_uart_writel(struct uart_port *port, + unsigned int value, unsigned int offset) +{ + bcm_writel(value, port->membase + offset); +} + +/* + * serial core request to check if uart tx fifo is empty + */ +static unsigned int bcm_uart_tx_empty(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + return (val & UART_IR_STAT(UART_IR_TXEMPTY)) ? 1 : 0; +} + +/* + * serial core request to set RTS and DTR pin state and loopback mode + */ +static void bcm_uart_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_MCTL_REG); + val &= ~(UART_MCTL_DTR_MASK | UART_MCTL_RTS_MASK); + /* invert of written value is reflected on the pin */ + if (!(mctrl & TIOCM_DTR)) + val |= UART_MCTL_DTR_MASK; + if (!(mctrl & TIOCM_RTS)) + val |= UART_MCTL_RTS_MASK; + bcm_uart_writel(port, val, UART_MCTL_REG); + + val = bcm_uart_readl(port, UART_CTL_REG); + if (mctrl & TIOCM_LOOP) + val |= UART_CTL_LOOPBACK_MASK; + else + val &= ~UART_CTL_LOOPBACK_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * serial core request to return RI, CTS, DCD and DSR pin state + */ +static unsigned int bcm_uart_get_mctrl(struct uart_port *port) +{ + unsigned int val, mctrl; + + mctrl = 0; + val = bcm_uart_readl(port, UART_EXTINP_REG); + if (val & UART_EXTINP_RI_MASK) + mctrl |= TIOCM_RI; + if (val & UART_EXTINP_CTS_MASK) + mctrl |= TIOCM_CTS; + if (val & UART_EXTINP_DCD_MASK) + mctrl |= TIOCM_CD; + if (val & UART_EXTINP_DSR_MASK) + mctrl |= TIOCM_DSR; + return mctrl; +} + +/* + * serial core request to disable tx ASAP (used for flow control) + */ +static void bcm_uart_stop_tx(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_CTL_REG); + val &= ~(UART_CTL_TXEN_MASK); + bcm_uart_writel(port, val, UART_CTL_REG); + + val = bcm_uart_readl(port, UART_IR_REG); + val &= ~UART_TX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); +} + +/* + * serial core request to (re)enable tx + */ +static void bcm_uart_start_tx(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + val |= UART_TX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); + + val = bcm_uart_readl(port, UART_CTL_REG); + val |= UART_CTL_TXEN_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * serial core request to stop rx, called before port shutdown + */ +static void bcm_uart_stop_rx(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + val &= ~UART_RX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); +} + +/* + * serial core request to enable modem status interrupt reporting + */ +static void bcm_uart_enable_ms(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + val |= UART_IR_MASK(UART_IR_EXTIP); + bcm_uart_writel(port, val, UART_IR_REG); +} + +/* + * serial core request to start/stop emitting break char + */ +static void bcm_uart_break_ctl(struct uart_port *port, int ctl) +{ + unsigned long flags; + unsigned int val; + + spin_lock_irqsave(&port->lock, flags); + + val = bcm_uart_readl(port, UART_CTL_REG); + if (ctl) + val |= UART_CTL_XMITBRK_MASK; + else + val &= ~UART_CTL_XMITBRK_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); + + spin_unlock_irqrestore(&port->lock, flags); +} + +/* + * return port type in string format + */ +static const char *bcm_uart_type(struct uart_port *port) +{ + return (port->type == PORT_BCM63XX) ? "bcm63xx_uart" : NULL; +} + +/* + * read all chars in rx fifo and send them to core + */ +static void bcm_uart_do_rx(struct uart_port *port) +{ + struct tty_struct *tty; + unsigned int max_count; + + /* limit number of char read in interrupt, should not be + * higher than fifo size anyway since we're much faster than + * serial port */ + max_count = 32; + tty = port->info->port.tty; + do { + unsigned int iestat, c, cstat; + char flag; + + /* get overrun/fifo empty information from ier + * register */ + iestat = bcm_uart_readl(port, UART_IR_REG); + if (!(iestat & UART_IR_STAT(UART_IR_RXNOTEMPTY))) + break; + + cstat = c = bcm_uart_readl(port, UART_FIFO_REG); + port->icount.rx++; + flag = TTY_NORMAL; + c &= 0xff; + + if (unlikely((cstat & UART_FIFO_ANYERR_MASK))) { + /* do stats first */ + if (cstat & UART_FIFO_BRKDET_MASK) { + port->icount.brk++; + if (uart_handle_break(port)) + continue; + } + + if (cstat & UART_FIFO_PARERR_MASK) + port->icount.parity++; + if (cstat & UART_FIFO_FRAMEERR_MASK) + port->icount.frame++; + + /* update flag wrt read_status_mask */ + cstat &= port->read_status_mask; + if (cstat & UART_FIFO_BRKDET_MASK) + flag = TTY_BREAK; + if (cstat & UART_FIFO_FRAMEERR_MASK) + flag = TTY_FRAME; + if (cstat & UART_FIFO_PARERR_MASK) + flag = TTY_PARITY; + } + + if (uart_handle_sysrq_char(port, c)) + continue; + + if (unlikely(iestat & UART_IR_STAT(UART_IR_RXOVER))) { + port->icount.overrun++; + tty_insert_flip_char(tty, 0, TTY_OVERRUN); + } + + if ((cstat & port->ignore_status_mask) == 0) + tty_insert_flip_char(tty, c, flag); + + } while (--max_count); + + tty_flip_buffer_push(tty); +} + +/* + * fill tx fifo with chars to send, stop when fifo is about to be full + * or when all chars have been sent. + */ +static void bcm_uart_do_tx(struct uart_port *port) +{ + struct circ_buf *xmit; + unsigned int val, max_count; + + if (port->x_char) { + bcm_uart_writel(port, port->x_char, UART_FIFO_REG); + port->icount.tx++; + port->x_char = 0; + return; + } + + if (uart_tx_stopped(port)) { + bcm_uart_stop_tx(port); + return; + } + + xmit = &port->info->xmit; + if (uart_circ_empty(xmit)) + goto txq_empty; + + val = bcm_uart_readl(port, UART_MCTL_REG); + val = (val & UART_MCTL_TXFIFOFILL_MASK) >> UART_MCTL_TXFIFOFILL_SHIFT; + max_count = port->fifosize - val; + + while (max_count--) { + unsigned int c; + + c = xmit->buf[xmit->tail]; + bcm_uart_writel(port, c, UART_FIFO_REG); + xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); + port->icount.tx++; + if (uart_circ_empty(xmit)) + break; + } + + if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) + uart_write_wakeup(port); + + if (uart_circ_empty(xmit)) + goto txq_empty; + return; + +txq_empty: + /* nothing to send, disable transmit interrupt */ + val = bcm_uart_readl(port, UART_IR_REG); + val &= ~UART_TX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); + return; +} + +/* + * process uart interrupt + */ +static irqreturn_t bcm_uart_interrupt(int irq, void *dev_id) +{ + struct uart_port *port; + unsigned int irqstat; + + port = dev_id; + spin_lock(&port->lock); + + irqstat = bcm_uart_readl(port, UART_IR_REG); + if (irqstat & UART_RX_INT_STAT) + bcm_uart_do_rx(port); + + if (irqstat & UART_TX_INT_STAT) + bcm_uart_do_tx(port); + + if (irqstat & UART_IR_MASK(UART_IR_EXTIP)) { + unsigned int estat; + + estat = bcm_uart_readl(port, UART_EXTINP_REG); + if (estat & UART_EXTINP_IRSTAT(UART_EXTINP_IR_CTS)) + uart_handle_cts_change(port, + estat & UART_EXTINP_CTS_MASK); + if (estat & UART_EXTINP_IRSTAT(UART_EXTINP_IR_DCD)) + uart_handle_dcd_change(port, + estat & UART_EXTINP_DCD_MASK); + } + + spin_unlock(&port->lock); + return IRQ_HANDLED; +} + +/* + * enable rx & tx operation on uart + */ +static void bcm_uart_enable(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_CTL_REG); + val |= (UART_CTL_BRGEN_MASK | UART_CTL_TXEN_MASK | UART_CTL_RXEN_MASK); + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * disable rx & tx operation on uart + */ +static void bcm_uart_disable(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_CTL_REG); + val &= ~(UART_CTL_BRGEN_MASK | UART_CTL_TXEN_MASK | + UART_CTL_RXEN_MASK); + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * clear all unread data in rx fifo and unsent data in tx fifo + */ +static void bcm_uart_flush(struct uart_port *port) +{ + unsigned int val; + + /* empty rx and tx fifo */ + val = bcm_uart_readl(port, UART_CTL_REG); + val |= UART_CTL_RSTRXFIFO_MASK | UART_CTL_RSTTXFIFO_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); + + /* read any pending char to make sure all irq status are + * cleared */ + (void)bcm_uart_readl(port, UART_FIFO_REG); +} + +/* + * serial core request to initialize uart and start rx operation + */ +static int bcm_uart_startup(struct uart_port *port) +{ + unsigned int val; + int ret; + + /* mask all irq and flush port */ + bcm_uart_disable(port); + bcm_uart_writel(port, 0, UART_IR_REG); + bcm_uart_flush(port); + + /* clear any pending external input interrupt */ + (void)bcm_uart_readl(port, UART_EXTINP_REG); + + /* set rx/tx fifo thresh to fifo half size */ + val = bcm_uart_readl(port, UART_MCTL_REG); + val &= ~(UART_MCTL_RXFIFOTHRESH_MASK | UART_MCTL_TXFIFOTHRESH_MASK); + val |= (port->fifosize / 2) << UART_MCTL_RXFIFOTHRESH_SHIFT; + val |= (port->fifosize / 2) << UART_MCTL_TXFIFOTHRESH_SHIFT; + bcm_uart_writel(port, val, UART_MCTL_REG); + + /* set rx fifo timeout to 1 char time */ + val = bcm_uart_readl(port, UART_CTL_REG); + val &= ~UART_CTL_RXTMOUTCNT_MASK; + val |= 1 << UART_CTL_RXTMOUTCNT_SHIFT; + bcm_uart_writel(port, val, UART_CTL_REG); + + /* report any edge on dcd and cts */ + val = UART_EXTINP_INT_MASK; + val |= UART_EXTINP_DCD_NOSENSE_MASK; + val |= UART_EXTINP_CTS_NOSENSE_MASK; + bcm_uart_writel(port, val, UART_EXTINP_REG); + + /* register irq and enable rx interrupts */ + ret = request_irq(port->irq, bcm_uart_interrupt, 0, + bcm_uart_type(port), port); + if (ret) + return ret; + bcm_uart_writel(port, UART_RX_INT_MASK, UART_IR_REG); + bcm_uart_enable(port); + return 0; +} + +/* + * serial core request to flush & disable uart + */ +static void bcm_uart_shutdown(struct uart_port *port) +{ + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + bcm_uart_writel(port, 0, UART_IR_REG); + spin_unlock_irqrestore(&port->lock, flags); + + bcm_uart_disable(port); + bcm_uart_flush(port); + free_irq(port->irq, port); +} + +/* + * serial core request to change current uart setting + */ +static void bcm_uart_set_termios(struct uart_port *port, + struct ktermios *new, + struct ktermios *old) +{ + unsigned int ctl, baud, quot, ier; + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + + /* disable uart while changing speed */ + bcm_uart_disable(port); + bcm_uart_flush(port); + + /* update Control register */ + ctl = bcm_uart_readl(port, UART_CTL_REG); + ctl &= ~UART_CTL_BITSPERSYM_MASK; + + switch (new->c_cflag & CSIZE) { + case CS5: + ctl |= (0 << UART_CTL_BITSPERSYM_SHIFT); + break; + case CS6: + ctl |= (1 << UART_CTL_BITSPERSYM_SHIFT); + break; + case CS7: + ctl |= (2 << UART_CTL_BITSPERSYM_SHIFT); + break; + default: + ctl |= (3 << UART_CTL_BITSPERSYM_SHIFT); + break; + } + + ctl &= ~UART_CTL_STOPBITS_MASK; + if (new->c_cflag & CSTOPB) + ctl |= UART_CTL_STOPBITS_2; + else + ctl |= UART_CTL_STOPBITS_1; + + ctl &= ~(UART_CTL_RXPAREN_MASK | UART_CTL_TXPAREN_MASK); + if (new->c_cflag & PARENB) + ctl |= (UART_CTL_RXPAREN_MASK | UART_CTL_TXPAREN_MASK); + ctl &= ~(UART_CTL_RXPAREVEN_MASK | UART_CTL_TXPAREVEN_MASK); + if (new->c_cflag & PARODD) + ctl |= (UART_CTL_RXPAREVEN_MASK | UART_CTL_TXPAREVEN_MASK); + bcm_uart_writel(port, ctl, UART_CTL_REG); + + /* update Baudword register */ + baud = uart_get_baud_rate(port, new, old, 0, port->uartclk / 16); + quot = uart_get_divisor(port, baud) - 1; + bcm_uart_writel(port, quot, UART_BAUD_REG); + + /* update Interrupt register */ + ier = bcm_uart_readl(port, UART_IR_REG); + + ier &= ~UART_IR_MASK(UART_IR_EXTIP); + if (UART_ENABLE_MS(port, new->c_cflag)) + ier |= UART_IR_MASK(UART_IR_EXTIP); + + bcm_uart_writel(port, ier, UART_IR_REG); + + /* update read/ignore mask */ + port->read_status_mask = UART_FIFO_VALID_MASK; + if (new->c_iflag & INPCK) { + port->read_status_mask |= UART_FIFO_FRAMEERR_MASK; + port->read_status_mask |= UART_FIFO_PARERR_MASK; + } + if (new->c_iflag & (BRKINT)) + port->read_status_mask |= UART_FIFO_BRKDET_MASK; + + port->ignore_status_mask = 0; + if (new->c_iflag & IGNPAR) + port->ignore_status_mask |= UART_FIFO_PARERR_MASK; + if (new->c_iflag & IGNBRK) + port->ignore_status_mask |= UART_FIFO_BRKDET_MASK; + if (!(new->c_cflag & CREAD)) + port->ignore_status_mask |= UART_FIFO_VALID_MASK; + + uart_update_timeout(port, new->c_cflag, baud); + bcm_uart_enable(port); + spin_unlock_irqrestore(&port->lock, flags); +} + +/* + * serial core request to claim uart iomem + */ +static int bcm_uart_request_port(struct uart_port *port) +{ + unsigned int size; + + size = RSET_UART_SIZE; + if (!request_mem_region(port->mapbase, size, "bcm63xx")) { + dev_err(port->dev, "Memory region busy\n"); + return -EBUSY; + } + + port->membase = ioremap(port->mapbase, size); + if (!port->membase) { + dev_err(port->dev, "Unable to map registers\n"); + release_mem_region(port->mapbase, size); + return -EBUSY; + } + return 0; +} + +/* + * serial core request to release uart iomem + */ +static void bcm_uart_release_port(struct uart_port *port) +{ + release_mem_region(port->mapbase, RSET_UART_SIZE); + iounmap(port->membase); +} + +/* + * serial core request to do any port required autoconfiguration + */ +static void bcm_uart_config_port(struct uart_port *port, int flags) +{ + if (flags & UART_CONFIG_TYPE) { + if (bcm_uart_request_port(port)) + return; + port->type = PORT_BCM63XX; + } +} + +/* + * serial core request to check that port information in serinfo are + * suitable + */ +static int bcm_uart_verify_port(struct uart_port *port, + struct serial_struct *serinfo) +{ + if (port->type != PORT_BCM63XX) + return -EINVAL; + if (port->irq != serinfo->irq) + return -EINVAL; + if (port->iotype != serinfo->io_type) + return -EINVAL; + if (port->mapbase != (unsigned long)serinfo->iomem_base) + return -EINVAL; + return 0; +} + +/* serial core callbacks */ +static struct uart_ops bcm_uart_ops = { + .tx_empty = bcm_uart_tx_empty, + .get_mctrl = bcm_uart_get_mctrl, + .set_mctrl = bcm_uart_set_mctrl, + .start_tx = bcm_uart_start_tx, + .stop_tx = bcm_uart_stop_tx, + .stop_rx = bcm_uart_stop_rx, + .enable_ms = bcm_uart_enable_ms, + .break_ctl = bcm_uart_break_ctl, + .startup = bcm_uart_startup, + .shutdown = bcm_uart_shutdown, + .set_termios = bcm_uart_set_termios, + .type = bcm_uart_type, + .release_port = bcm_uart_release_port, + .request_port = bcm_uart_request_port, + .config_port = bcm_uart_config_port, + .verify_port = bcm_uart_verify_port, +}; + + + +#ifdef CONFIG_SERIAL_BCM63XX_CONSOLE +static inline void wait_for_xmitr(struct uart_port *port) +{ + unsigned int tmout; + + /* Wait up to 10ms for the character(s) to be sent. */ + tmout = 10000; + while (--tmout) { + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + if (val & UART_IR_STAT(UART_IR_TXEMPTY)) + break; + udelay(1); + } + + /* Wait up to 1s for flow control if necessary */ + if (port->flags & UPF_CONS_FLOW) { + tmout = 1000000; + while (--tmout) { + unsigned int val; + + val = bcm_uart_readl(port, UART_EXTINP_REG); + if (val & UART_EXTINP_CTS_MASK) + break; + udelay(1); + } + } +} + +/* + * output given char + */ +static void bcm_console_putchar(struct uart_port *port, int ch) +{ + wait_for_xmitr(port); + bcm_uart_writel(port, ch, UART_FIFO_REG); +} + +/* + * console core request to output given string + */ +static void bcm_console_write(struct console *co, const char *s, + unsigned int count) +{ + struct uart_port *port; + unsigned long flags; + int locked; + + port = &ports[co->index]; + + local_irq_save(flags); + if (port->sysrq) { + /* bcm_uart_interrupt() already took the lock */ + locked = 0; + } else if (oops_in_progress) { + locked = spin_trylock(&port->lock); + } else { + spin_lock(&port->lock); + locked = 1; + } + + /* call helper to deal with \r\n */ + uart_console_write(port, s, count, bcm_console_putchar); + + /* and wait for char to be transmitted */ + wait_for_xmitr(port); + + if (locked) + spin_unlock(&port->lock); + local_irq_restore(flags); +} + +/* + * console core request to setup given console, find matching uart + * port and setup it. + */ +static int bcm_console_setup(struct console *co, char *options) +{ + struct uart_port *port; + int baud = 9600; + int bits = 8; + int parity = 'n'; + int flow = 'n'; + + if (co->index < 0 || co->index >= BCM63XX_NR_UARTS) + return -EINVAL; + port = &ports[co->index]; + if (!port->membase) + return -ENODEV; + if (options) + uart_parse_options(options, &baud, &parity, &bits, &flow); + + return uart_set_options(port, co, baud, parity, bits, flow); +} + +static struct uart_driver bcm_uart_driver; + +static struct console bcm63xx_console = { + .name = "ttyS", + .write = bcm_console_write, + .device = uart_console_device, + .setup = bcm_console_setup, + .flags = CON_PRINTBUFFER, + .index = -1, + .data = &bcm_uart_driver, +}; + +static int __init bcm63xx_console_init(void) +{ + register_console(&bcm63xx_console); + return 0; +} + +console_initcall(bcm63xx_console_init); + +#define BCM63XX_CONSOLE (&bcm63xx_console) +#else +#define BCM63XX_CONSOLE NULL +#endif /* CONFIG_SERIAL_BCM63XX_CONSOLE */ + +static struct uart_driver bcm_uart_driver = { + .owner = THIS_MODULE, + .driver_name = "bcm63xx_uart", + .dev_name = "ttyS", + .major = TTY_MAJOR, + .minor = 64, + .nr = 1, + .cons = BCM63XX_CONSOLE, +}; + +/* + * platform driver probe/remove callback + */ +static int __devinit bcm_uart_probe(struct platform_device *pdev) +{ + struct resource *res_mem, *res_irq; + struct uart_port *port; + struct clk *clk; + int ret; + + if (pdev->id < 0 || pdev->id >= BCM63XX_NR_UARTS) + return -EINVAL; + + if (ports[pdev->id].membase) + return -EBUSY; + + res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res_mem) + return -ENODEV; + + res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!res_irq) + return -ENODEV; + + clk = clk_get(&pdev->dev, "periph"); + if (IS_ERR(clk)) + return -ENODEV; + + port = &ports[pdev->id]; + memset(port, 0, sizeof(*port)); + port->iotype = UPIO_MEM; + port->mapbase = res_mem->start; + port->irq = res_irq->start; + port->ops = &bcm_uart_ops; + port->flags = UPF_BOOT_AUTOCONF; + port->dev = &pdev->dev; + port->fifosize = 16; + port->uartclk = clk_get_rate(clk) / 2; + clk_put(clk); + + ret = uart_add_one_port(&bcm_uart_driver, port); + if (ret) { + kfree(port); + return ret; + } + platform_set_drvdata(pdev, port); + return 0; +} + +static int __devexit bcm_uart_remove(struct platform_device *pdev) +{ + struct uart_port *port; + + port = platform_get_drvdata(pdev); + uart_remove_one_port(&bcm_uart_driver, port); + platform_set_drvdata(pdev, NULL); + /* mark port as free */ + ports[pdev->id].membase = 0; + return 0; +} + +/* + * platform driver stuff + */ +static struct platform_driver bcm_uart_platform_driver = { + .probe = bcm_uart_probe, + .remove = __devexit_p(bcm_uart_remove), + .driver = { + .owner = THIS_MODULE, + .name = "bcm63xx_uart", + }, +}; + +static int __init bcm_uart_init(void) +{ + int ret; + + ret = uart_register_driver(&bcm_uart_driver); + if (ret) + return ret; + + ret = platform_driver_register(&bcm_uart_platform_driver); + if (ret) + uart_unregister_driver(&bcm_uart_driver); + + return ret; +} + +static void __exit bcm_uart_exit(void) +{ + platform_driver_unregister(&bcm_uart_platform_driver); + uart_unregister_driver(&bcm_uart_driver); +} + +module_init(bcm_uart_init); +module_exit(bcm_uart_exit); + +MODULE_AUTHOR("Maxime Bizon "); +MODULE_DESCRIPTION("Broadcom 63 -- cgit v1.2.3 From b7058842c940ad2c08dd829b21e5c92ebe3b8758 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 30 Sep 2009 16:12:20 -0700 Subject: net: Make setsockopt() optlen be unsigned. This provides safety against negative optlen at the type level instead of depending upon (sometimes non-trivial) checks against this sprinkled all over the the place, in each and every implementation. Based upon work done by Arjan van de Ven and feedback from Linus Torvalds. Signed-off-by: David S. Miller --- drivers/atm/ambassador.c | 8 ----- drivers/atm/eni.c | 2 +- drivers/atm/firestream.c | 2 +- drivers/atm/fore200e.c | 2 +- drivers/atm/horizon.c | 2 +- drivers/atm/iphase.c | 2 +- drivers/atm/zatm.c | 2 +- drivers/isdn/mISDN/socket.c | 2 +- drivers/net/pppol2tp.c | 2 +- include/linux/atmdev.h | 2 +- include/linux/mroute.h | 4 +-- include/linux/mroute6.h | 4 +-- include/linux/net.h | 8 ++--- include/linux/netfilter.h | 4 +-- include/net/compat.h | 4 +-- include/net/inet_connection_sock.h | 6 ++-- include/net/ip.h | 4 +-- include/net/ipv6.h | 4 +-- include/net/sctp/structs.h | 4 +-- include/net/sock.h | 12 ++++---- include/net/tcp.h | 4 +-- include/net/udp.h | 2 +- net/atm/common.c | 2 +- net/atm/common.h | 2 +- net/atm/pvc.c | 2 +- net/atm/svc.c | 2 +- net/ax25/af_ax25.c | 2 +- net/bluetooth/hci_sock.c | 2 +- net/bluetooth/l2cap.c | 4 +-- net/bluetooth/rfcomm/sock.c | 4 +-- net/bluetooth/sco.c | 2 +- net/can/raw.c | 2 +- net/compat.c | 12 ++++---- net/core/sock.c | 8 ++--- net/dccp/dccp.h | 4 +-- net/dccp/proto.c | 10 +++--- net/decnet/af_decnet.c | 6 ++-- net/ieee802154/dgram.c | 2 +- net/ieee802154/raw.c | 2 +- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/ip_sockglue.c | 6 ++-- net/ipv4/ipmr.c | 2 +- net/ipv4/raw.c | 6 ++-- net/ipv4/tcp.c | 6 ++-- net/ipv4/udp.c | 6 ++-- net/ipv4/udp_impl.h | 4 +-- net/ipv6/ip6mr.c | 2 +- net/ipv6/ipv6_sockglue.c | 6 ++-- net/ipv6/raw.c | 6 ++-- net/ipv6/udp.c | 4 +-- net/ipv6/udp_impl.h | 4 +-- net/ipx/af_ipx.c | 2 +- net/irda/af_irda.c | 2 +- net/iucv/af_iucv.c | 2 +- net/llc/af_llc.c | 2 +- net/netfilter/nf_sockopt.c | 4 +-- net/netlink/af_netlink.c | 2 +- net/netrom/af_netrom.c | 2 +- net/packet/af_packet.c | 2 +- net/phonet/pep.c | 2 +- net/rds/af_rds.c | 2 +- net/rose/af_rose.c | 2 +- net/rxrpc/af_rxrpc.c | 2 +- net/sctp/socket.c | 62 ++++++++++++++++++++------------------ net/socket.c | 2 +- net/tipc/socket.c | 2 +- net/x25/af_x25.c | 2 +- 67 files changed, 149 insertions(+), 153 deletions(-) (limited to 'include') diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c index 703364b52170..66e181345b3a 100644 --- a/drivers/atm/ambassador.c +++ b/drivers/atm/ambassador.c @@ -1306,14 +1306,6 @@ static void amb_close (struct atm_vcc * atm_vcc) { return; } -/********** Set socket options for a VC **********/ - -// int amb_getsockopt (struct atm_vcc * atm_vcc, int level, int optname, void * optval, int optlen); - -/********** Set socket options for a VC **********/ - -// int amb_setsockopt (struct atm_vcc * atm_vcc, int level, int optname, void * optval, int optlen); - /********** Send **********/ static int amb_send (struct atm_vcc * atm_vcc, struct sk_buff * skb) { diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 5503bfc8e132..0c3026145443 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2031,7 +2031,7 @@ static int eni_getsockopt(struct atm_vcc *vcc,int level,int optname, static int eni_setsockopt(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen) + void __user *optval,unsigned int optlen) { return -EINVAL; } diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index b119640e1ee9..cd5049af47a9 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -1244,7 +1244,7 @@ static int fs_getsockopt(struct atm_vcc *vcc,int level,int optname, static int fs_setsockopt(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen) + void __user *optval,unsigned int optlen) { func_enter (); func_exit (); diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 10f000dbe448..f766cc46b4c4 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -1795,7 +1795,7 @@ fore200e_getsockopt(struct atm_vcc* vcc, int level, int optname, void __user *op static int -fore200e_setsockopt(struct atm_vcc* vcc, int level, int optname, void __user *optval, int optlen) +fore200e_setsockopt(struct atm_vcc* vcc, int level, int optname, void __user *optval, unsigned int optlen) { /* struct fore200e* fore200e = FORE200E_DEV(vcc->dev); */ diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c index 01ce241dbeae..4e49021e67ee 100644 --- a/drivers/atm/horizon.c +++ b/drivers/atm/horizon.c @@ -2590,7 +2590,7 @@ static int hrz_getsockopt (struct atm_vcc * atm_vcc, int level, int optname, } static int hrz_setsockopt (struct atm_vcc * atm_vcc, int level, int optname, - void *optval, int optlen) { + void *optval, unsigned int optlen) { hrz_dev * dev = HRZ_DEV(atm_vcc->dev); PRINTD (DBG_FLOW|DBG_VCC, "hrz_setsockopt"); switch (level) { diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 78c9736c3579..b2c1b37ab2e4 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -2862,7 +2862,7 @@ static int ia_getsockopt(struct atm_vcc *vcc, int level, int optname, } static int ia_setsockopt(struct atm_vcc *vcc, int level, int optname, - void __user *optval, int optlen) + void __user *optval, unsigned int optlen) { IF_EVENT(printk(">ia_setsockopt\n");) return -EINVAL; diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index 752b1ba81f7e..2e9635be048c 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1517,7 +1517,7 @@ static int zatm_getsockopt(struct atm_vcc *vcc,int level,int optname, static int zatm_setsockopt(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen) + void __user *optval,unsigned int optlen) { return -EINVAL; } diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index c36f52137456..feb0fa45b664 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -415,7 +415,7 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } static int data_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int len) + char __user *optval, unsigned int len) { struct sock *sk = sock->sk; int err = 0, opt = 0; diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c index cc394d073755..5910df60c93e 100644 --- a/drivers/net/pppol2tp.c +++ b/drivers/net/pppol2tp.c @@ -2179,7 +2179,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk, * session or the special tunnel type. */ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct pppol2tp_session *session = sk->sk_user_data; diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 086e5c362d3a..817b23705c91 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -397,7 +397,7 @@ struct atmdev_ops { /* only send is required */ int (*getsockopt)(struct atm_vcc *vcc,int level,int optname, void __user *optval,int optlen); int (*setsockopt)(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen); + void __user *optval,unsigned int optlen); int (*send)(struct atm_vcc *vcc,struct sk_buff *skb); int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags); void (*phy_put)(struct atm_dev *dev,unsigned char value, diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 0d45b4e8d367..08bc776d05e2 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -145,14 +145,14 @@ static inline int ip_mroute_opt(int opt) #endif #ifdef CONFIG_IP_MROUTE -extern int ip_mroute_setsockopt(struct sock *, int, char __user *, int); +extern int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); extern int ip_mr_init(void); #else static inline int ip_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 43dc97e32183..b191865a6ca3 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -134,7 +134,7 @@ static inline int ip6_mroute_opt(int opt) struct sock; #ifdef CONFIG_IPV6_MROUTE -extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, int); +extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); @@ -143,7 +143,7 @@ extern void ip6_mr_cleanup(void); #else static inline int ip6_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/net.h b/include/linux/net.h index 9040a10584f7..529a0931711d 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -178,11 +178,11 @@ struct proto_ops { int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int (*compat_setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); int (*compat_getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int (*sendmsg) (struct kiocb *iocb, struct socket *sock, @@ -256,7 +256,7 @@ extern int kernel_getpeername(struct socket *sock, struct sockaddr *addr, extern int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen); extern int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, int optlen); + char *optval, unsigned int optlen); extern int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); @@ -313,7 +313,7 @@ SOCKCALL_WRAP(name, compat_ioctl, (struct socket *sock, unsigned int cmd, \ SOCKCALL_WRAP(name, listen, (struct socket *sock, int len), (sock, len)) \ SOCKCALL_WRAP(name, shutdown, (struct socket *sock, int flags), (sock, flags)) \ SOCKCALL_WRAP(name, setsockopt, (struct socket *sock, int level, int optname, \ - char __user *optval, int optlen), (sock, level, optname, optval, optlen)) \ + char __user *optval, unsigned int optlen), (sock, level, optname, optval, optlen)) \ SOCKCALL_WRAP(name, getsockopt, (struct socket *sock, int level, int optname, \ char __user *optval, int __user *optlen), (sock, level, optname, optval, optlen)) \ SOCKCALL_WRAP(name, sendmsg, (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len), \ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 48cfe51bfddc..6132b5e6d9d3 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -221,12 +221,12 @@ __ret;}) /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, - int len); + unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, int len); + char __user *opt, unsigned int len); int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); diff --git a/include/net/compat.h b/include/net/compat.h index 5bbf8bf9efea..7c3002832d05 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -40,8 +40,8 @@ extern int put_cmsg_compat(struct msghdr*, int, int, int, void *); extern int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *, unsigned char *, int); -extern int compat_mc_setsockopt(struct sock *, int, int, char __user *, int, - int (*)(struct sock *, int, int, char __user *, int)); +extern int compat_mc_setsockopt(struct sock *, int, int, char __user *, unsigned int, + int (*)(struct sock *, int, int, char __user *, unsigned int)); extern int compat_mc_getsockopt(struct sock *, int, int, char __user *, int __user *, int (*)(struct sock *, int, int, char __user *, int __user *)); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 03cffd9f64e3..696d6e4ce68a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -48,13 +48,13 @@ struct inet_connection_sock_af_ops { u16 net_header_len; u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #ifdef CONFIG_COMPAT int (*compat_setsockopt)(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); int (*compat_getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); @@ -332,5 +332,5 @@ extern void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/ip.h b/include/net/ip.h index 5b26a0bd178e..2f47e5482b55 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -381,10 +381,10 @@ extern int ip_options_rcv_srr(struct sk_buff *skb); extern void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb); extern int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc); -extern int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen); +extern int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); extern int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int compat_ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); extern int compat_ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index ad9a51130254..8c31d8a0c1fe 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -550,7 +550,7 @@ extern int ipv6_find_tlv(struct sk_buff *skb, int offset, int type); extern int ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); extern int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, @@ -559,7 +559,7 @@ extern int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); extern int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 42d00ced5eb8..6e5f0e0c7967 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -544,7 +544,7 @@ struct sctp_af { int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*getsockopt) (struct sock *sk, int level, int optname, @@ -554,7 +554,7 @@ struct sctp_af { int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*compat_getsockopt) (struct sock *sk, int level, int optname, diff --git a/include/net/sock.h b/include/net/sock.h index 950409dcec3d..1621935aad5b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -624,7 +624,7 @@ struct proto { void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); @@ -632,7 +632,7 @@ struct proto { int (*compat_setsockopt)(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*compat_getsockopt)(struct sock *sk, int level, int optname, char __user *optval, @@ -951,7 +951,7 @@ extern void sock_rfree(struct sk_buff *skb); extern int sock_setsockopt(struct socket *sock, int level, int op, char __user *optval, - int optlen); + unsigned int optlen); extern int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, @@ -993,7 +993,7 @@ extern int sock_no_shutdown(struct socket *, int); extern int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); extern int sock_no_setsockopt(struct socket *, int, int, - char __user *, int); + char __user *, unsigned int); extern int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); extern int sock_no_recvmsg(struct kiocb *, struct socket *, @@ -1015,11 +1015,11 @@ extern int sock_common_getsockopt(struct socket *sock, int level, int optname, extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags); extern int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); extern int compat_sock_common_setsockopt(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); extern void sk_common_release(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 56b76027b85e..03a49c703377 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -394,13 +394,13 @@ extern int tcp_getsockopt(struct sock *sk, int level, int __user *optlen); extern int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); extern int compat_tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int compat_tcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern void tcp_set_keepalive(struct sock *sk, int val); extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, diff --git a/include/net/udp.h b/include/net/udp.h index 5fb029f817a3..f98abd2ce709 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -144,7 +144,7 @@ extern unsigned int udp_poll(struct file *file, struct socket *sock, extern int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen, + char __user *optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, diff --git a/net/atm/common.c b/net/atm/common.c index 8c4d843eb17f..950bd16d2383 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -679,7 +679,7 @@ static int check_qos(const struct atm_qos *qos) } int vcc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct atm_vcc *vcc; unsigned long value; diff --git a/net/atm/common.h b/net/atm/common.h index 92e2981f479f..f48a76b6cdf4 100644 --- a/net/atm/common.h +++ b/net/atm/common.h @@ -21,7 +21,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait); int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int vcc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); int vcc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); diff --git a/net/atm/pvc.c b/net/atm/pvc.c index e1d22d9430dd..d4c024504f99 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -59,7 +59,7 @@ static int pvc_connect(struct socket *sock,struct sockaddr *sockaddr, } static int pvc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int error; diff --git a/net/atm/svc.c b/net/atm/svc.c index 7b831b526d0b..f90d143c4b25 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -446,7 +446,7 @@ int svc_change_qos(struct atm_vcc *vcc,struct atm_qos *qos) static int svc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 4102de1022ee..cd1c3dc0fe01 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -534,7 +534,7 @@ ax25_cb *ax25_create_cb(void) */ static int ax25_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; ax25_cb *ax25; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 4f9621f759a0..75302a986067 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -466,7 +466,7 @@ drop: goto done; } -static int hci_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int len) +static int hci_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int len) { struct hci_ufilter uf = { .opcode = 0 }; struct sock *sk = sock->sk; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index b03012564647..555d9da1869b 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1698,7 +1698,7 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms return bt_sock_recvmsg(iocb, sock, msg, len, flags); } -static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen) +static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct l2cap_options opts; @@ -1755,7 +1755,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us return err; } -static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct bt_security sec; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 0b85e8116859..8a20aaf1f231 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -730,7 +730,7 @@ out: return copied ? : err; } -static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen) +static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; @@ -766,7 +766,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u return err; } -static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct bt_security sec; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 13c27f17192c..77f4153bdb5e 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -644,7 +644,7 @@ static int sco_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return err; } -static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; diff --git a/net/can/raw.c b/net/can/raw.c index db3152df7d2b..b5e897922d32 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -411,7 +411,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, } static int raw_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); diff --git a/net/compat.c b/net/compat.c index 12728b17a226..a407c3addbae 100644 --- a/net/compat.c +++ b/net/compat.c @@ -331,7 +331,7 @@ struct compat_sock_fprog { }; static int do_set_attach_filter(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog)); @@ -351,7 +351,7 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname, } static int do_set_sock_timeout(struct socket *sock, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct compat_timeval __user *up = (struct compat_timeval __user *) optval; struct timeval ktime; @@ -373,7 +373,7 @@ static int do_set_sock_timeout(struct socket *sock, int level, } static int compat_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (optname == SO_ATTACH_FILTER) return do_set_attach_filter(sock, level, optname, @@ -385,7 +385,7 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, } asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; struct socket *sock; @@ -558,8 +558,8 @@ struct compat_group_filter { int compat_mc_setsockopt(struct sock *sock, int level, int optname, - char __user *optval, int optlen, - int (*setsockopt)(struct sock *,int,int,char __user *,int)) + char __user *optval, unsigned int optlen, + int (*setsockopt)(struct sock *,int,int,char __user *,unsigned int)) { char __user *koptval = optval; int koptlen = optlen; diff --git a/net/core/sock.c b/net/core/sock.c index 524712a7b154..77fbfed332e8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -446,7 +446,7 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) */ int sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int val; @@ -1697,7 +1697,7 @@ int sock_no_shutdown(struct socket *sock, int how) EXPORT_SYMBOL(sock_no_shutdown); int sock_no_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } @@ -2018,7 +2018,7 @@ EXPORT_SYMBOL(sock_common_recvmsg); * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; @@ -2028,7 +2028,7 @@ EXPORT_SYMBOL(sock_common_setsockopt); #ifdef CONFIG_COMPAT int compat_sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index d6bc47363b1c..5ef32c2f0d6a 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -290,14 +290,14 @@ extern int dccp_disconnect(struct sock *sk, int flags); extern int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT extern int compat_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #endif extern int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index bc4467082a00..a156319fd0ac 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -393,7 +393,7 @@ out: EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; @@ -464,7 +464,7 @@ static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) } static int dccp_setsockopt_ccid(struct sock *sk, int type, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { u8 *val; int rc = 0; @@ -494,7 +494,7 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type, } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; @@ -546,7 +546,7 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, } int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, @@ -559,7 +559,7 @@ EXPORT_SYMBOL_GPL(dccp_setsockopt); #ifdef CONFIG_COMPAT int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk_compat_setsockopt(sk, level, optname, diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 77d40289653c..7a58c87baf17 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -157,7 +157,7 @@ static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE]; static struct hlist_head dn_wild_sk; static atomic_t decnet_memory_allocated; -static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen, int flags); +static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen, int flags); static int __dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen, int flags); static struct hlist_head *dn_find_list(struct sock *sk) @@ -1325,7 +1325,7 @@ out: return err; } -static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err; @@ -1337,7 +1337,7 @@ static int dn_setsockopt(struct socket *sock, int level, int optname, char __use return err; } -static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, int optlen, int flags) +static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, unsigned int optlen, int flags) { struct sock *sk = sock->sk; struct dn_scp *scp = DN_SK(sk); diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 51593a48f2dd..a413b1bf4465 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -414,7 +414,7 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname, } static int dgram_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dgram_sock *ro = dgram_sk(sk); int val; diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 13198859982e..30e74eee07d6 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -244,7 +244,7 @@ static int raw_getsockopt(struct sock *sk, int level, int optname, } static int raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 22cd19ee44e5..4351ca2cf0b8 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -714,7 +714,7 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt); int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5a0693576e82..0c0b6e363a20 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -440,7 +440,7 @@ out: */ static int do_ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); int val = 0, err; @@ -950,7 +950,7 @@ e_inval: } int ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { int err; @@ -975,7 +975,7 @@ EXPORT_SYMBOL(ip_setsockopt); #ifdef CONFIG_COMPAT int compat_ip_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c43ec2d51ce2..630a56df7b47 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -931,7 +931,7 @@ static void mrtsock_destruct(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { int ret; struct vifctl vif; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ebb1e5848bc6..757c9171e7c2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -741,7 +741,7 @@ out: return ret; } static int do_raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->num != IPPROTO_ICMP) @@ -753,7 +753,7 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname, } static int raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_RAW) return ip_setsockopt(sk, level, optname, optval, optlen); @@ -762,7 +762,7 @@ static int raw_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT static int compat_raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_RAW) return compat_ip_setsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 21387ebabf00..5a15e7629d8e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2032,7 +2032,7 @@ int tcp_disconnect(struct sock *sk, int flags) * Socket option code for TCP. */ static int do_tcp_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -2220,7 +2220,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, } int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen) + unsigned int optlen) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -2232,7 +2232,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, #ifdef CONFIG_COMPAT int compat_tcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_TCP) return inet_csk_compat_setsockopt(sk, level, optname, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ebaaa7f973d7..3326aff65906 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1359,7 +1359,7 @@ void udp_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen, + char __user *optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); @@ -1441,7 +1441,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1451,7 +1451,7 @@ int udp_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index 9f4a6165f722..aaad650d47d9 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -11,13 +11,13 @@ extern void __udp4_lib_err(struct sk_buff *, u32, struct udp_table *); extern int udp_v4_get_port(struct sock *sk, unsigned short snum); extern int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #ifdef CONFIG_COMPAT extern int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 090675e269ee..716153941fc4 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1281,7 +1281,7 @@ int ip6mr_sk_done(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { int ret; struct mif6ctl vif; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index f5e0682b402d..14f54eb5a7fc 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -123,7 +123,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, } static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); @@ -773,7 +773,7 @@ e_inval: } int ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; @@ -801,7 +801,7 @@ EXPORT_SYMBOL(ipv6_setsockopt); #ifdef CONFIG_COMPAT int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d675b8d82d3..4f24570b0869 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -957,7 +957,7 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; @@ -1000,7 +1000,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, } static int rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch(level) { case SOL_RAW: @@ -1024,7 +1024,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b265b7047d3e..3a60f12b34ed 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1044,7 +1044,7 @@ void udpv6_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1054,7 +1054,7 @@ int udpv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 6bb303471e20..d7571046bfc4 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -16,10 +16,10 @@ extern int udp_v6_get_port(struct sock *sk, unsigned short snum); extern int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT extern int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index f1118d92a191..66c7a20011f3 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1292,7 +1292,7 @@ const char *ipx_device_name(struct ipx_interface *intrfc) * socket object. */ static int ipx_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int opt; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 50b43c57d5d8..dd35641835f4 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1826,7 +1826,7 @@ static int irda_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon * */ static int irda_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index d985d163dcfc..bada1b9c670b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1387,7 +1387,7 @@ static int iucv_sock_release(struct socket *sock) /* getsockopt and setsockopt */ static int iucv_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c45eee1c0e8d..7aa4fd170104 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -973,7 +973,7 @@ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd, * Set various connection specific parameters. */ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index 8ab829f86574..f042ae521557 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -113,7 +113,7 @@ static int nf_sockopt(struct sock *sk, u_int8_t pf, int val, } int nf_setsockopt(struct sock *sk, u_int8_t pf, int val, char __user *opt, - int len) + unsigned int len) { return nf_sockopt(sk, pf, val, opt, &len, 0); } @@ -154,7 +154,7 @@ static int compat_nf_sockopt(struct sock *sk, u_int8_t pf, int val, } int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, - int val, char __user *opt, int len) + int val, char __user *opt, unsigned int len) { return compat_nf_sockopt(sk, pf, val, opt, &len, 0); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index dd85320907cb..19e98007691c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1150,7 +1150,7 @@ static void netlink_update_socket_mc(struct netlink_sock *nlk, } static int netlink_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ce1a34b99c23..7a834952f67f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -301,7 +301,7 @@ void nr_destroy_socket(struct sock *sk) */ static int nr_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d3d52c66cdc2..1238949e66a9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1701,7 +1701,7 @@ static void packet_flush_mclist(struct sock *sk) } static int -packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index b8252d289cd7..5f32d217535b 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -742,7 +742,7 @@ static int pep_init(struct sock *sk) } static int pep_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct pep_sock *pn = pep_sk(sk); int val = 0, err = 0; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 6b58aeff4c7a..98e05382fd3c 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -248,7 +248,7 @@ static int rds_cong_monitor(struct rds_sock *rs, char __user *optval, } static int rds_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); int ret; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 1e166c9685aa..502cce76621d 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -370,7 +370,7 @@ void rose_destroy_socket(struct sock *sk) */ static int rose_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index bfe493ebf27c..a86afceaa94f 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -507,7 +507,7 @@ out: * set RxRPC socket options */ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); unsigned min_sec_level; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 89af37a6c871..c8d05758661d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2027,7 +2027,8 @@ out: * instead a error will be indicated to the user. */ static int sctp_setsockopt_disable_fragments(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { int val; @@ -2043,7 +2044,7 @@ static int sctp_setsockopt_disable_fragments(struct sock *sk, } static int sctp_setsockopt_events(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; @@ -2064,7 +2065,7 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, * association is closed. */ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); @@ -2318,7 +2319,8 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } static int sctp_setsockopt_peer_addr_params(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_paddrparams params; struct sctp_transport *trans = NULL; @@ -2430,7 +2432,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, */ static int sctp_setsockopt_delayed_ack(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sctp_sack_info params; struct sctp_transport *trans = NULL; @@ -2546,7 +2548,7 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ -static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_initmsg sinit; struct sctp_sock *sp = sctp_sk(sk); @@ -2583,7 +2585,8 @@ static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int opt * to this call if the caller is using the UDP model. */ static int sctp_setsockopt_default_send_param(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_sndrcvinfo info; struct sctp_association *asoc; @@ -2622,7 +2625,7 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, * association peer's addresses. */ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_prim prim; struct sctp_transport *trans; @@ -2651,7 +2654,7 @@ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, * integer boolean flag. */ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -2676,7 +2679,8 @@ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, * be changed. * */ -static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int optlen) { +static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigned int optlen) +{ struct sctp_rtoinfo rtoinfo; struct sctp_association *asoc; @@ -2728,7 +2732,7 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int opt * See [SCTP] for more information. * */ -static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_assocparams assocparams; @@ -2800,7 +2804,7 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int o * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ -static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsigned int optlen) { int val; struct sctp_sock *sp = sctp_sk(sk); @@ -2844,7 +2848,7 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int op * changed (effecting future associations only). * assoc_value: This parameter specifies the maximum size in bytes. */ -static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; @@ -2899,7 +2903,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optl * set primary request: */ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -2950,7 +2954,7 @@ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optva } static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_setadaptation adaptation; @@ -2979,7 +2983,7 @@ static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval * saved with outbound messages. */ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_assoc_value params; struct sctp_sock *sp; @@ -3030,7 +3034,7 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, */ static int sctp_setsockopt_fragment_interleave(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -3063,7 +3067,7 @@ static int sctp_setsockopt_fragment_interleave(struct sock *sk, */ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { u32 val; @@ -3096,7 +3100,7 @@ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, */ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_assoc_value params; struct sctp_sock *sp; @@ -3140,8 +3144,8 @@ static int sctp_setsockopt_maxburst(struct sock *sk, * will only effect future associations on the socket. */ static int sctp_setsockopt_auth_chunk(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authchunk val; @@ -3172,8 +3176,8 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, * endpoint requires the peer to use. */ static int sctp_setsockopt_hmac_ident(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_hmacalgo *hmacs; u32 idents; @@ -3215,7 +3219,7 @@ out: */ static int sctp_setsockopt_auth_key(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_authkey *authkey; struct sctp_association *asoc; @@ -3260,8 +3264,8 @@ out: * the association shared key. */ static int sctp_setsockopt_active_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; @@ -3288,8 +3292,8 @@ static int sctp_setsockopt_active_key(struct sock *sk, * This set option will delete a shared secret key from use. */ static int sctp_setsockopt_del_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; @@ -3332,7 +3336,7 @@ static int sctp_setsockopt_del_key(struct sock *sk, * optlen - the size of the buffer. */ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int retval = 0; diff --git a/net/socket.c b/net/socket.c index 41e8847508aa..75655365b5fd 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2391,7 +2391,7 @@ int kernel_getsockopt(struct socket *sock, int level, int optname, } int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, int optlen) + char *optval, unsigned int optlen) { mm_segment_t oldfs = get_fs(); int err; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e8254e809b79..e6d9abf7440e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1658,7 +1658,7 @@ restart: */ static int setsockopt(struct socket *sock, - int lvl, int opt, char __user *ov, int ol) + int lvl, int opt, char __user *ov, unsigned int ol) { struct sock *sk = sock->sk; struct tipc_port *tport = tipc_sk_port(sk); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5e6c072c64d3..7fa9c7ad3d3b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -409,7 +409,7 @@ static void x25_destroy_socket(struct sock *sk) */ static int x25_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int opt; struct sock *sk = sock->sk; -- cgit v1.2.3 From c15227de132f1295f3db6b7df9079956b1020fd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:52:12 +0200 Subject: block: use normal I/O path for discard requests prepare_discard_fn() was being called in a place where memory allocation was effectively impossible. This makes it inappropriate for all but the most trivial translations of Linux's DISCARD operation to the block command set. Additionally adding a payload there makes the ownership of the bio backing unclear as it's now allocated by the device driver and not the submitter as usual. It is replaced with QUEUE_FLAG_DISCARD which is used to indicate whether the queue supports discard operations or not. blkdev_issue_discard now allocates a one-page, sector-length payload which is the right thing for the common ATA and SCSI implementations. The mtd implementation of prepare_discard_fn() is replaced with simply checking for the request being a discard. Largely based on a previous patch from Matthew Wilcox which did the prepare_discard_fn but not the different payload allocation yet. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 35 ++++++++++++++++++++++++++++++----- block/blk-core.c | 3 +-- block/blk-settings.c | 17 ----------------- drivers/mtd/mtd_blkdevs.c | 19 +++++-------------- drivers/staging/dst/dcore.c | 2 +- include/linux/blkdev.h | 6 ++---- 6 files changed, 39 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 6593ab39cfe9..21f5025c3945 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -350,6 +350,7 @@ static void blkdev_discard_end_io(struct bio *bio, int err) if (bio->bi_private) complete(bio->bi_private); + __free_page(bio_page(bio)); bio_put(bio); } @@ -372,26 +373,44 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct request_queue *q = bdev_get_queue(bdev); int type = flags & DISCARD_FL_BARRIER ? DISCARD_BARRIER : DISCARD_NOBARRIER; + struct bio *bio; + struct page *page; int ret = 0; if (!q) return -ENXIO; - if (!q->prepare_discard_fn) + if (!blk_queue_discard(q)) return -EOPNOTSUPP; while (nr_sects && !ret) { - struct bio *bio = bio_alloc(gfp_mask, 0); - if (!bio) - return -ENOMEM; + unsigned int sector_size = q->limits.logical_block_size; + bio = bio_alloc(gfp_mask, 1); + if (!bio) + goto out; + bio->bi_sector = sector; bio->bi_end_io = blkdev_discard_end_io; bio->bi_bdev = bdev; if (flags & DISCARD_FL_WAIT) bio->bi_private = &wait; - bio->bi_sector = sector; + /* + * Add a zeroed one-sector payload as that's what + * our current implementations need. If we'll ever need + * more the interface will need revisiting. + */ + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto out_free_bio; + if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size) + goto out_free_page; + /* + * And override the bio size - the way discard works we + * touch many more blocks on disk than the actual payload + * length. + */ if (nr_sects > queue_max_hw_sectors(q)) { bio->bi_size = queue_max_hw_sectors(q) << 9; nr_sects -= queue_max_hw_sectors(q); @@ -414,5 +433,11 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_put(bio); } return ret; +out_free_page: + __free_page(page); +out_free_bio: + bio_put(bio); +out: + return -ENOMEM; } EXPORT_SYMBOL(blkdev_issue_discard); diff --git a/block/blk-core.c b/block/blk-core.c index 8135228e4b29..80a020dd1580 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1124,7 +1124,6 @@ void init_request_from_bio(struct request *req, struct bio *bio) req->cmd_flags |= REQ_DISCARD; if (bio_rw_flagged(bio, BIO_RW_BARRIER)) req->cmd_flags |= REQ_SOFTBARRIER; - req->q->prepare_discard_fn(req->q, req); } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) req->cmd_flags |= REQ_HARDBARRIER; @@ -1470,7 +1469,7 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; if (bio_rw_flagged(bio, BIO_RW_DISCARD) && - !q->prepare_discard_fn) { + !blk_queue_discard(q)) { err = -EOPNOTSUPP; goto end_io; } diff --git a/block/blk-settings.c b/block/blk-settings.c index eaf122ff5f16..d29498ef1eb5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -33,23 +33,6 @@ void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn) } EXPORT_SYMBOL(blk_queue_prep_rq); -/** - * blk_queue_set_discard - set a discard_sectors function for queue - * @q: queue - * @dfn: prepare_discard function - * - * It's possible for a queue to register a discard callback which is used - * to transform a discard request into the appropriate type for the - * hardware. If none is registered, then discard requests are failed - * with %EOPNOTSUPP. - * - */ -void blk_queue_set_discard(struct request_queue *q, prepare_discard_fn *dfn) -{ - q->prepare_discard_fn = dfn; -} -EXPORT_SYMBOL(blk_queue_set_discard); - /** * blk_queue_merge_bvec - set a merge_bvec function for queue * @q: queue diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 0acbf4f5be50..8ca17a3e96ea 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -32,14 +32,6 @@ struct mtd_blkcore_priv { spinlock_t queue_lock; }; -static int blktrans_discard_request(struct request_queue *q, - struct request *req) -{ - req->cmd_type = REQ_TYPE_LINUX_BLOCK; - req->cmd[0] = REQ_LB_OP_DISCARD; - return 0; -} - static int do_blktrans_request(struct mtd_blktrans_ops *tr, struct mtd_blktrans_dev *dev, struct request *req) @@ -52,10 +44,6 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, buf = req->buffer; - if (req->cmd_type == REQ_TYPE_LINUX_BLOCK && - req->cmd[0] == REQ_LB_OP_DISCARD) - return tr->discard(dev, block, nsect); - if (!blk_fs_request(req)) return -EIO; @@ -63,6 +51,9 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, get_capacity(req->rq_disk)) return -EIO; + if (blk_discard_rq(req)) + return tr->discard(dev, block, nsect); + switch(rq_data_dir(req)) { case READ: for (; nsect > 0; nsect--, block++, buf += tr->blksize) @@ -380,8 +371,8 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) tr->blkcore_priv->rq->queuedata = tr; blk_queue_logical_block_size(tr->blkcore_priv->rq, tr->blksize); if (tr->discard) - blk_queue_set_discard(tr->blkcore_priv->rq, - blktrans_discard_request); + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, + tr->blkcore_priv->rq); tr->blkshift = ffs(tr->blksize) - 1; diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c index ac8577358ba0..5e8db0677582 100644 --- a/drivers/staging/dst/dcore.c +++ b/drivers/staging/dst/dcore.c @@ -102,7 +102,7 @@ static int dst_request(struct request_queue *q, struct bio *bio) struct dst_node *n = q->queuedata; int err = -EIO; - if (bio_empty_barrier(bio) && !q->prepare_discard_fn) { + if (bio_empty_barrier(bio) && !blk_queue_discard(q)) { /* * This is a dirty^Wnice hack, but if we complete this * operation with -EOPNOTSUPP like intended, XFS diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e23a86cae5ac..f62d45e87618 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -82,7 +82,6 @@ enum rq_cmd_type_bits { enum { REQ_LB_OP_EJECT = 0x40, /* eject request */ REQ_LB_OP_FLUSH = 0x41, /* flush request */ - REQ_LB_OP_DISCARD = 0x42, /* discard sectors */ }; /* @@ -261,7 +260,6 @@ typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unplug_fn) (struct request_queue *); -typedef int (prepare_discard_fn) (struct request_queue *, struct request *); struct bio_vec; struct bvec_merge_data { @@ -340,7 +338,6 @@ struct request_queue make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unplug_fn *unplug_fn; - prepare_discard_fn *prepare_discard_fn; merge_bvec_fn *merge_bvec_fn; prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; @@ -460,6 +457,7 @@ struct request_queue #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_CQ 16 /* hardware does queuing */ +#define QUEUE_FLAG_DISCARD 17 /* supports DISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -591,6 +589,7 @@ enum { #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) +#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) #define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) @@ -955,7 +954,6 @@ extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); -extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -- cgit v1.2.3 From 67efc9258010da35b27b3854d0880c7e193004ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:54:20 +0200 Subject: block: allow large discard requests Currently we set the bio size to the byte equivalent of the blocks to be trimmed when submitting the initial DISCARD ioctl. That means it is subject to the max_hw_sectors limitation of the HBA which is much lower than the size of a DISCARD request we can support. Add a separate max_discard_sectors tunable to limit the size for discard requests. We limit the max discard request size in bytes to 32bit as that is the limit for bio->bi_size. This could be much larger if we had a way to pass that information through the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 10 ++++++---- block/blk-core.c | 3 ++- block/blk-settings.c | 13 +++++++++++++ include/linux/blkdev.h | 3 +++ 4 files changed, 24 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 21f5025c3945..8873b9b439ff 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -385,6 +385,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, while (nr_sects && !ret) { unsigned int sector_size = q->limits.logical_block_size; + unsigned int max_discard_sectors = + min(q->limits.max_discard_sectors, UINT_MAX >> 9); bio = bio_alloc(gfp_mask, 1); if (!bio) @@ -411,10 +413,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, * touch many more blocks on disk than the actual payload * length. */ - if (nr_sects > queue_max_hw_sectors(q)) { - bio->bi_size = queue_max_hw_sectors(q) << 9; - nr_sects -= queue_max_hw_sectors(q); - sector += queue_max_hw_sectors(q); + if (nr_sects > max_discard_sectors) { + bio->bi_size = max_discard_sectors << 9; + nr_sects -= max_discard_sectors; + sector += max_discard_sectors; } else { bio->bi_size = nr_sects << 9; nr_sects = 0; diff --git a/block/blk-core.c b/block/blk-core.c index 80a020dd1580..34504f309728 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1436,7 +1436,8 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; } - if (unlikely(nr_sectors > queue_max_hw_sectors(q))) { + if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) && + nr_sectors > queue_max_hw_sectors(q))) { printk(KERN_ERR "bio too big device %s (%u > %u)\n", bdevname(bio->bi_bdev, b), bio_sectors(bio), diff --git a/block/blk-settings.c b/block/blk-settings.c index d29498ef1eb5..e0695bca7027 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -96,6 +96,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_segment_size = MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; lim->max_hw_sectors = INT_MAX; + lim->max_discard_sectors = SAFE_MAX_SECTORS; lim->logical_block_size = lim->physical_block_size = lim->io_min = 512; lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT); lim->alignment_offset = 0; @@ -238,6 +239,18 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors) } EXPORT_SYMBOL(blk_queue_max_hw_sectors); +/** + * blk_queue_max_discard_sectors - set max sectors for a single discard + * @q: the request queue for the device + * @max_discard: maximum number of sectors to discard + **/ +void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors) +{ + q->limits.max_discard_sectors = max_discard_sectors; +} +EXPORT_SYMBOL(blk_queue_max_discard_sectors); + /** * blk_queue_max_phys_segments - set max phys segments for a request for this queue * @q: the request queue for the device diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f62d45e87618..1a03b715dfad 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -311,6 +311,7 @@ struct queue_limits { unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; + unsigned int max_discard_sectors; unsigned short logical_block_size; unsigned short max_hw_segments; @@ -928,6 +929,8 @@ extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); +extern void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); extern void blk_queue_alignment_offset(struct request_queue *q, -- cgit v1.2.3 From b0da3f0dada78832c9da03ad2152ae76bd9a2496 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Thu, 1 Oct 2009 21:16:13 +0200 Subject: Add a tracepoint for block request remapping Since 2.6.31 now has request-based device-mapper, it's useful to have a tracepoint for request-remapping as well as bio-remapping. This patch adds a tracepoint for request-remapping, trace_block_rq_remap(). Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Cc: Alasdair G Kergon Cc: Li Zefan Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + include/linux/blktrace_api.h | 2 +- include/trace/events/block.h | 33 +++++++++++++++++++++++++++++++++ kernel/trace/blktrace.c | 34 ++++++++++++++++++++++++++++++++++ 4 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 34504f309728..ddaaea4fdffc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -34,6 +34,7 @@ #include "blk.h" EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap); +EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); static int __make_request(struct request_queue *q, struct bio *bio); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 622939a23299..3b73b9992b26 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -212,7 +212,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) -# define blk_trace_remove_sysfs(struct device *dev) do { } while (0) +# define blk_trace_remove_sysfs(dev) do { } while (0) static inline int blk_trace_init_sysfs(struct device *dev) { return 0; diff --git a/include/trace/events/block.h b/include/trace/events/block.h index d86af94691c2..00405b5f624a 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -488,6 +488,39 @@ TRACE_EVENT(block_remap, (unsigned long long)__entry->old_sector) ); +TRACE_EVENT(block_rq_remap, + + TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev, + sector_t from), + + TP_ARGS(q, rq, dev, from), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( unsigned int, nr_sector ) + __field( dev_t, old_dev ) + __field( sector_t, old_sector ) + __array( char, rwbs, 6 ) + ), + + TP_fast_assign( + __entry->dev = disk_devt(rq->rq_disk); + __entry->sector = blk_rq_pos(rq); + __entry->nr_sector = blk_rq_sectors(rq); + __entry->old_dev = dev; + __entry->old_sector = from; + blk_fill_rwbs_rq(__entry->rwbs, rq); + ), + + TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, + MAJOR(__entry->old_dev), MINOR(__entry->old_dev), + (unsigned long long)__entry->old_sector) +); + #endif /* _TRACE_BLOCK_H */ /* This part must be outside protection */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 60b5c5a3d4b4..d9d6206e0b14 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -855,6 +855,37 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio, sizeof(r), &r); } +/** + * blk_add_trace_rq_remap - Add a trace for a request-remap operation + * @q: queue the io is for + * @rq: the source request + * @dev: target device + * @from: source sector + * + * Description: + * Device mapper remaps request to other devices. + * Add a trace for that action. + * + **/ +static void blk_add_trace_rq_remap(struct request_queue *q, + struct request *rq, dev_t dev, + sector_t from) +{ + struct blk_trace *bt = q->blk_trace; + struct blk_io_trace_remap r; + + if (likely(!bt)) + return; + + r.device_from = cpu_to_be32(dev); + r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); + r.sector_from = cpu_to_be64(from); + + __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), + rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors, + sizeof(r), &r); +} + /** * blk_add_driver_data - Add binary message with driver-specific data * @q: queue the io is for @@ -922,10 +953,13 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_remap(blk_add_trace_remap); WARN_ON(ret); + ret = register_trace_block_rq_remap(blk_add_trace_rq_remap); + WARN_ON(ret); } static void blk_unregister_tracepoints(void) { + unregister_trace_block_rq_remap(blk_add_trace_rq_remap); unregister_trace_block_remap(blk_add_trace_remap); unregister_trace_block_split(blk_add_trace_split); unregister_trace_block_unplug_io(blk_add_trace_unplug_io); -- cgit v1.2.3 From 828c09509b9695271bcbdc53e9fc9a6a737148d2 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 1 Oct 2009 15:43:56 -0700 Subject: const: constify remaining file_operations [akpm@linux-foundation.org: fix KVM] Signed-off-by: Alexey Dobriyan Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mach-ns9xxx/clock.c | 2 +- arch/blackfin/mach-bf561/coreb.c | 2 +- arch/cris/arch-v10/drivers/sync_serial.c | 2 +- arch/cris/arch-v32/drivers/mach-fs/gpio.c | 2 +- arch/powerpc/kvm/timing.c | 2 +- arch/powerpc/platforms/cell/spufs/file.c | 2 +- arch/powerpc/platforms/pseries/dtl.c | 2 +- arch/x86/xen/debugfs.c | 2 +- drivers/acpi/video.c | 2 +- drivers/block/cciss.c | 2 +- drivers/char/apm-emulation.c | 2 +- drivers/char/bfin-otp.c | 2 +- drivers/char/xilinx_hwicap/xilinx_hwicap.c | 2 +- drivers/gpio/gpiolib.c | 2 +- drivers/hwmon/fschmd.c | 2 +- drivers/lguest/lguest_user.c | 2 +- drivers/media/dvb/dvb-core/dmxdev.c | 2 +- drivers/media/dvb/firewire/firedtv-ci.c | 2 +- drivers/misc/phantom.c | 2 +- drivers/misc/sgi-gru/grufile.c | 3 +-- drivers/mmc/core/debugfs.c | 2 +- drivers/s390/cio/qdio_debug.c | 2 +- drivers/s390/cio/qdio_perf.c | 2 +- drivers/scsi/sg.c | 43 +++++++++++++++++++++--------- drivers/spi/spidev.c | 2 +- drivers/usb/class/usbtmc.c | 2 +- drivers/usb/gadget/printer.c | 2 +- drivers/usb/host/whci/debug.c | 6 ++--- drivers/usb/misc/rio500.c | 3 +-- drivers/uwb/uwb-debug.c | 6 ++--- fs/btrfs/ctree.h | 2 +- fs/btrfs/file.c | 2 +- fs/btrfs/inode.c | 4 +-- fs/jbd2/journal.c | 2 +- fs/nfsd/nfsctl.c | 2 +- fs/nilfs2/dir.c | 2 +- fs/nilfs2/file.c | 2 +- fs/nilfs2/mdt.c | 2 +- fs/nilfs2/nilfs.h | 4 +-- fs/ocfs2/cluster/heartbeat.c | 2 +- fs/ocfs2/cluster/netdebug.c | 4 +-- fs/ocfs2/dlm/dlmdebug.c | 8 +++--- fs/ocfs2/super.c | 2 +- fs/omfs/dir.c | 2 +- fs/omfs/file.c | 2 +- fs/omfs/omfs.h | 4 +-- include/linux/cgroup.h | 2 +- include/linux/fs.h | 2 +- kernel/cgroup.c | 10 +++---- kernel/kprobes.c | 4 +-- kernel/rcutree_trace.c | 10 +++---- kernel/sched.c | 2 +- kernel/time/timer_list.c | 2 +- kernel/time/timer_stats.c | 2 +- samples/tracepoints/tracepoint-sample.c | 2 +- security/integrity/ima/ima_fs.c | 10 +++---- virt/kvm/kvm_main.c | 2 +- 57 files changed, 110 insertions(+), 95 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-ns9xxx/clock.c b/arch/arm/mach-ns9xxx/clock.c index 44ed20d4a388..cf81cbc57544 100644 --- a/arch/arm/mach-ns9xxx/clock.c +++ b/arch/arm/mach-ns9xxx/clock.c @@ -195,7 +195,7 @@ static int clk_debugfs_open(struct inode *inode, struct file *file) return single_open(file, clk_debugfs_show, NULL); } -static struct file_operations clk_debugfs_operations = { +static const struct file_operations clk_debugfs_operations = { .open = clk_debugfs_open, .read = seq_read, .llseek = seq_lseek, diff --git a/arch/blackfin/mach-bf561/coreb.c b/arch/blackfin/mach-bf561/coreb.c index 93635a766f9c..1e60a92dd602 100644 --- a/arch/blackfin/mach-bf561/coreb.c +++ b/arch/blackfin/mach-bf561/coreb.c @@ -48,7 +48,7 @@ coreb_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned l return ret; } -static struct file_operations coreb_fops = { +static const struct file_operations coreb_fops = { .owner = THIS_MODULE, .ioctl = coreb_ioctl, }; diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c index 6cc1a0319a5d..562b9a7feae7 100644 --- a/arch/cris/arch-v10/drivers/sync_serial.c +++ b/arch/cris/arch-v10/drivers/sync_serial.c @@ -244,7 +244,7 @@ static unsigned sync_serial_prescale_shadow; #define NUMBER_OF_PORTS 2 -static struct file_operations sync_serial_fops = { +static const struct file_operations sync_serial_fops = { .owner = THIS_MODULE, .write = sync_serial_write, .read = sync_serial_read, diff --git a/arch/cris/arch-v32/drivers/mach-fs/gpio.c b/arch/cris/arch-v32/drivers/mach-fs/gpio.c index fe1fde893887..d89ab80498ed 100644 --- a/arch/cris/arch-v32/drivers/mach-fs/gpio.c +++ b/arch/cris/arch-v32/drivers/mach-fs/gpio.c @@ -855,7 +855,7 @@ gpio_leds_ioctl(unsigned int cmd, unsigned long arg) return 0; } -struct file_operations gpio_fops = { +static const struct file_operations gpio_fops = { .owner = THIS_MODULE, .poll = gpio_poll, .ioctl = gpio_ioctl, diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c index 47ee603f558e..2aa371e30079 100644 --- a/arch/powerpc/kvm/timing.c +++ b/arch/powerpc/kvm/timing.c @@ -201,7 +201,7 @@ static int kvmppc_exit_timing_open(struct inode *inode, struct file *file) return single_open(file, kvmppc_exit_timing_show, inode->i_private); } -static struct file_operations kvmppc_exit_timing_fops = { +static const struct file_operations kvmppc_exit_timing_fops = { .owner = THIS_MODULE, .open = kvmppc_exit_timing_open, .read = seq_read, diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 961309446170..884e8bcec499 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -147,7 +147,7 @@ static int __fops ## _open(struct inode *inode, struct file *file) \ __simple_attr_check_format(__fmt, 0ull); \ return spufs_attr_open(inode, file, __get, __set, __fmt); \ } \ -static struct file_operations __fops = { \ +static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = spufs_attr_release, \ diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index ab69925d579b..937a544a236d 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -209,7 +209,7 @@ static ssize_t dtl_file_read(struct file *filp, char __user *buf, size_t len, return n_read * sizeof(struct dtl_entry); } -static struct file_operations dtl_fops = { +static const struct file_operations dtl_fops = { .open = dtl_file_open, .release = dtl_file_release, .read = dtl_file_read, diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c index b53225d2cac3..e133ce25e290 100644 --- a/arch/x86/xen/debugfs.c +++ b/arch/x86/xen/debugfs.c @@ -100,7 +100,7 @@ static int xen_array_release(struct inode *inode, struct file *file) return 0; } -static struct file_operations u32_array_fops = { +static const struct file_operations u32_array_fops = { .owner = THIS_MODULE, .open = u32_array_open, .release= xen_array_release, diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index a4fddb24476f..f6e54bf8dd96 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -285,7 +285,7 @@ static int acpi_video_device_brightness_open_fs(struct inode *inode, struct file *file); static ssize_t acpi_video_device_write_brightness(struct file *file, const char __user *buffer, size_t count, loff_t *data); -static struct file_operations acpi_video_device_brightness_fops = { +static const struct file_operations acpi_video_device_brightness_fops = { .owner = THIS_MODULE, .open = acpi_video_device_brightness_open_fs, .read = seq_read, diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 24c3e21ab263..1ece0b47b581 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -426,7 +426,7 @@ out: return err; } -static struct file_operations cciss_proc_fops = { +static const struct file_operations cciss_proc_fops = { .owner = THIS_MODULE, .open = cciss_seq_open, .read = seq_read, diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c index aaca40283be9..4f568cb9af3f 100644 --- a/drivers/char/apm-emulation.c +++ b/drivers/char/apm-emulation.c @@ -393,7 +393,7 @@ static int apm_open(struct inode * inode, struct file * filp) return as ? 0 : -ENOMEM; } -static struct file_operations apm_bios_fops = { +static const struct file_operations apm_bios_fops = { .owner = THIS_MODULE, .read = apm_read, .poll = apm_poll, diff --git a/drivers/char/bfin-otp.c b/drivers/char/bfin-otp.c index e3dd24bff514..836d4f0a876f 100644 --- a/drivers/char/bfin-otp.c +++ b/drivers/char/bfin-otp.c @@ -217,7 +217,7 @@ static long bfin_otp_ioctl(struct file *filp, unsigned cmd, unsigned long arg) # define bfin_otp_ioctl NULL #endif -static struct file_operations bfin_otp_fops = { +static const struct file_operations bfin_otp_fops = { .owner = THIS_MODULE, .unlocked_ioctl = bfin_otp_ioctl, .read = bfin_otp_read, diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c index f40ab699860f..4846d50199f3 100644 --- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c +++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c @@ -559,7 +559,7 @@ static int hwicap_release(struct inode *inode, struct file *file) return status; } -static struct file_operations hwicap_fops = { +static const struct file_operations hwicap_fops = { .owner = THIS_MODULE, .write = hwicap_write, .read = hwicap_read, diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index bb11a429394a..662ed923d9eb 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1487,7 +1487,7 @@ static int gpiolib_open(struct inode *inode, struct file *file) return single_open(file, gpiolib_show, NULL); } -static struct file_operations gpiolib_operations = { +static const struct file_operations gpiolib_operations = { .open = gpiolib_open, .read = seq_read, .llseek = seq_lseek, diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c index ea955edde87e..2a7a85a6dc36 100644 --- a/drivers/hwmon/fschmd.c +++ b/drivers/hwmon/fschmd.c @@ -915,7 +915,7 @@ static int watchdog_ioctl(struct inode *inode, struct file *filp, return ret; } -static struct file_operations watchdog_fops = { +static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, .llseek = no_llseek, .open = watchdog_open, diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index b4d3f7ca554f..bd1632388e4a 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -508,7 +508,7 @@ static int close(struct inode *inode, struct file *file) * uses: reading and writing a character device called /dev/lguest. All the * work happens in the read(), write() and close() routines: */ -static struct file_operations lguest_fops = { +static const struct file_operations lguest_fops = { .owner = THIS_MODULE, .release = close, .write = write, diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c index 3750ff48cba1..516414983593 100644 --- a/drivers/media/dvb/dvb-core/dmxdev.c +++ b/drivers/media/dvb/dvb-core/dmxdev.c @@ -1203,7 +1203,7 @@ static unsigned int dvb_dvr_poll(struct file *file, poll_table *wait) return mask; } -static struct file_operations dvb_dvr_fops = { +static const struct file_operations dvb_dvr_fops = { .owner = THIS_MODULE, .read = dvb_dvr_read, .write = dvb_dvr_write, diff --git a/drivers/media/dvb/firewire/firedtv-ci.c b/drivers/media/dvb/firewire/firedtv-ci.c index eeb80d0ea3ff..853e04b7cb36 100644 --- a/drivers/media/dvb/firewire/firedtv-ci.c +++ b/drivers/media/dvb/firewire/firedtv-ci.c @@ -215,7 +215,7 @@ static unsigned int fdtv_ca_io_poll(struct file *file, poll_table *wait) return POLLIN; } -static struct file_operations fdtv_ca_fops = { +static const struct file_operations fdtv_ca_fops = { .owner = THIS_MODULE, .ioctl = dvb_generic_ioctl, .open = dvb_generic_open, diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index fa57b67593ae..90a95ce8dc34 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -271,7 +271,7 @@ static unsigned int phantom_poll(struct file *file, poll_table *wait) return mask; } -static struct file_operations phantom_file_ops = { +static const struct file_operations phantom_file_ops = { .open = phantom_open, .release = phantom_release, .unlocked_ioctl = phantom_ioctl, diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index 300e7ba391a0..41c8fe2a928c 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -53,7 +53,6 @@ struct gru_stats_s gru_stats; /* Guaranteed user available resources on each node */ static int max_user_cbrs, max_user_dsr_bytes; -static struct file_operations gru_fops; static struct miscdevice gru_miscdev; @@ -426,7 +425,7 @@ static void __exit gru_exit(void) gru_proc_exit(); } -static struct file_operations gru_fops = { +static const struct file_operations gru_fops = { .owner = THIS_MODULE, .unlocked_ioctl = gru_file_unlocked_ioctl, .mmap = gru_file_mmap, diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c index 610dbd1fcc82..96d10f40fb23 100644 --- a/drivers/mmc/core/debugfs.c +++ b/drivers/mmc/core/debugfs.c @@ -240,7 +240,7 @@ static int mmc_ext_csd_release(struct inode *inode, struct file *file) return 0; } -static struct file_operations mmc_dbg_ext_csd_fops = { +static const struct file_operations mmc_dbg_ext_csd_fops = { .open = mmc_ext_csd_open, .read = mmc_ext_csd_read, .release = mmc_ext_csd_release, diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c index 1b78f639ead3..76769978285f 100644 --- a/drivers/s390/cio/qdio_debug.c +++ b/drivers/s390/cio/qdio_debug.c @@ -125,7 +125,7 @@ static int qstat_seq_open(struct inode *inode, struct file *filp) filp->f_path.dentry->d_inode->i_private); } -static struct file_operations debugfs_fops = { +static const struct file_operations debugfs_fops = { .owner = THIS_MODULE, .open = qstat_seq_open, .read = seq_read, diff --git a/drivers/s390/cio/qdio_perf.c b/drivers/s390/cio/qdio_perf.c index eff943923c6f..968e3c7c2632 100644 --- a/drivers/s390/cio/qdio_perf.c +++ b/drivers/s390/cio/qdio_perf.c @@ -84,7 +84,7 @@ static int qdio_perf_seq_open(struct inode *inode, struct file *filp) return single_open(filp, qdio_perf_proc_show, NULL); } -static struct file_operations qdio_perf_proc_fops = { +static const struct file_operations qdio_perf_proc_fops = { .owner = THIS_MODULE, .open = qdio_perf_seq_open, .read = seq_read, diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 0cb049f5cc56..747a5e5c1276 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1317,7 +1317,7 @@ static void sg_rq_end_io(struct request *rq, int uptodate) } } -static struct file_operations sg_fops = { +static const struct file_operations sg_fops = { .owner = THIS_MODULE, .read = sg_read, .write = sg_write, @@ -2194,9 +2194,11 @@ static int sg_proc_seq_show_int(struct seq_file *s, void *v); static int sg_proc_single_open_adio(struct inode *inode, struct file *file); static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer, size_t count, loff_t *off); -static struct file_operations adio_fops = { - /* .owner, .read and .llseek added in sg_proc_init() */ +static const struct file_operations adio_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_adio, + .read = seq_read, + .llseek = seq_lseek, .write = sg_proc_write_adio, .release = single_release, }; @@ -2204,23 +2206,32 @@ static struct file_operations adio_fops = { static int sg_proc_single_open_dressz(struct inode *inode, struct file *file); static ssize_t sg_proc_write_dressz(struct file *filp, const char __user *buffer, size_t count, loff_t *off); -static struct file_operations dressz_fops = { +static const struct file_operations dressz_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_dressz, + .read = seq_read, + .llseek = seq_lseek, .write = sg_proc_write_dressz, .release = single_release, }; static int sg_proc_seq_show_version(struct seq_file *s, void *v); static int sg_proc_single_open_version(struct inode *inode, struct file *file); -static struct file_operations version_fops = { +static const struct file_operations version_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_version, + .read = seq_read, + .llseek = seq_lseek, .release = single_release, }; static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v); static int sg_proc_single_open_devhdr(struct inode *inode, struct file *file); -static struct file_operations devhdr_fops = { +static const struct file_operations devhdr_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_devhdr, + .read = seq_read, + .llseek = seq_lseek, .release = single_release, }; @@ -2229,8 +2240,11 @@ static int sg_proc_open_dev(struct inode *inode, struct file *file); static void * dev_seq_start(struct seq_file *s, loff_t *pos); static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos); static void dev_seq_stop(struct seq_file *s, void *v); -static struct file_operations dev_fops = { +static const struct file_operations dev_fops = { + .owner = THIS_MODULE, .open = sg_proc_open_dev, + .read = seq_read, + .llseek = seq_lseek, .release = seq_release, }; static const struct seq_operations dev_seq_ops = { @@ -2242,8 +2256,11 @@ static const struct seq_operations dev_seq_ops = { static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v); static int sg_proc_open_devstrs(struct inode *inode, struct file *file); -static struct file_operations devstrs_fops = { +static const struct file_operations devstrs_fops = { + .owner = THIS_MODULE, .open = sg_proc_open_devstrs, + .read = seq_read, + .llseek = seq_lseek, .release = seq_release, }; static const struct seq_operations devstrs_seq_ops = { @@ -2255,8 +2272,11 @@ static const struct seq_operations devstrs_seq_ops = { static int sg_proc_seq_show_debug(struct seq_file *s, void *v); static int sg_proc_open_debug(struct inode *inode, struct file *file); -static struct file_operations debug_fops = { +static const struct file_operations debug_fops = { + .owner = THIS_MODULE, .open = sg_proc_open_debug, + .read = seq_read, + .llseek = seq_lseek, .release = seq_release, }; static const struct seq_operations debug_seq_ops = { @@ -2269,7 +2289,7 @@ static const struct seq_operations debug_seq_ops = { struct sg_proc_leaf { const char * name; - struct file_operations * fops; + const struct file_operations * fops; }; static struct sg_proc_leaf sg_proc_leaf_arr[] = { @@ -2295,9 +2315,6 @@ sg_proc_init(void) for (k = 0; k < num_leaves; ++k) { leaf = &sg_proc_leaf_arr[k]; mask = leaf->fops->write ? S_IRUGO | S_IWUSR : S_IRUGO; - leaf->fops->owner = THIS_MODULE; - leaf->fops->read = seq_read; - leaf->fops->llseek = seq_lseek; proc_create(leaf->name, mask, sg_proc_sgp, leaf->fops); } return 0; diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index f921bd1109e1..5d23983f02fc 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -537,7 +537,7 @@ static int spidev_release(struct inode *inode, struct file *filp) return status; } -static struct file_operations spidev_fops = { +static const struct file_operations spidev_fops = { .owner = THIS_MODULE, /* REVISIT switch to aio primitives, so that userspace * gets more complete API coverage. It'll simplify things diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 333ee02e7b2b..864f0ba6a344 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -993,7 +993,7 @@ skip_io_on_zombie: return retval; } -static struct file_operations fops = { +static const struct file_operations fops = { .owner = THIS_MODULE, .read = usbtmc_read, .write = usbtmc_write, diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c index 29500154d00c..2d867fd22413 100644 --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -875,7 +875,7 @@ printer_ioctl(struct file *fd, unsigned int code, unsigned long arg) } /* used after endpoint configuration */ -static struct file_operations printer_io_operations = { +static const struct file_operations printer_io_operations = { .owner = THIS_MODULE, .open = printer_open, .read = printer_read, diff --git a/drivers/usb/host/whci/debug.c b/drivers/usb/host/whci/debug.c index cf2d45946c57..2273c815941f 100644 --- a/drivers/usb/host/whci/debug.c +++ b/drivers/usb/host/whci/debug.c @@ -134,7 +134,7 @@ static int pzl_open(struct inode *inode, struct file *file) return single_open(file, pzl_print, inode->i_private); } -static struct file_operations di_fops = { +static const struct file_operations di_fops = { .open = di_open, .read = seq_read, .llseek = seq_lseek, @@ -142,7 +142,7 @@ static struct file_operations di_fops = { .owner = THIS_MODULE, }; -static struct file_operations asl_fops = { +static const struct file_operations asl_fops = { .open = asl_open, .read = seq_read, .llseek = seq_lseek, @@ -150,7 +150,7 @@ static struct file_operations asl_fops = { .owner = THIS_MODULE, }; -static struct file_operations pzl_fops = { +static const struct file_operations pzl_fops = { .open = pzl_open, .read = seq_read, .llseek = seq_lseek, diff --git a/drivers/usb/misc/rio500.c b/drivers/usb/misc/rio500.c index d645f3899fe1..32d0199d0c32 100644 --- a/drivers/usb/misc/rio500.c +++ b/drivers/usb/misc/rio500.c @@ -429,8 +429,7 @@ read_rio(struct file *file, char __user *buffer, size_t count, loff_t * ppos) return read_count; } -static struct -file_operations usb_rio_fops = { +static const struct file_operations usb_rio_fops = { .owner = THIS_MODULE, .read = read_rio, .write = write_rio, diff --git a/drivers/uwb/uwb-debug.c b/drivers/uwb/uwb-debug.c index 4a42993700c1..2eecec0c13c9 100644 --- a/drivers/uwb/uwb-debug.c +++ b/drivers/uwb/uwb-debug.c @@ -205,7 +205,7 @@ static ssize_t command_write(struct file *file, const char __user *buf, return ret < 0 ? ret : len; } -static struct file_operations command_fops = { +static const struct file_operations command_fops = { .open = command_open, .write = command_write, .read = NULL, @@ -255,7 +255,7 @@ static int reservations_open(struct inode *inode, struct file *file) return single_open(file, reservations_print, inode->i_private); } -static struct file_operations reservations_fops = { +static const struct file_operations reservations_fops = { .open = reservations_open, .read = seq_read, .llseek = seq_lseek, @@ -283,7 +283,7 @@ static int drp_avail_open(struct inode *inode, struct file *file) return single_open(file, drp_avail_print, inode->i_private); } -static struct file_operations drp_avail_fops = { +static const struct file_operations drp_avail_fops = { .open = drp_avail_open, .read = seq_read, .llseek = seq_lseek, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 80599b4e42bd..4484eb3408af 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2326,7 +2326,7 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync); int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, int skip_pinned); int btrfs_check_file(struct btrfs_root *root, struct inode *inode); -extern struct file_operations btrfs_file_operations; +extern const struct file_operations btrfs_file_operations; int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, u64 start, u64 end, u64 locked_end, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a3492a3ad96b..9ed17dbe5c6e 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1196,7 +1196,7 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) return 0; } -struct file_operations btrfs_file_operations = { +const struct file_operations btrfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .aio_read = generic_file_aio_read, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e9b76bcd1c12..b9fe06d751c0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -62,7 +62,7 @@ static const struct inode_operations btrfs_special_inode_operations; static const struct inode_operations btrfs_file_inode_operations; static const struct address_space_operations btrfs_aops; static const struct address_space_operations btrfs_symlink_aops; -static struct file_operations btrfs_dir_file_operations; +static const struct file_operations btrfs_dir_file_operations; static struct extent_io_ops btrfs_extent_io_ops; static struct kmem_cache *btrfs_inode_cachep; @@ -5544,7 +5544,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = { .permission = btrfs_permission, }; -static struct file_operations btrfs_dir_file_operations = { +static const struct file_operations btrfs_dir_file_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = btrfs_real_readdir, diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 761af77491f5..b0ab5219becb 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -770,7 +770,7 @@ static int jbd2_seq_info_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static struct file_operations jbd2_seq_info_fops = { +static const struct file_operations jbd2_seq_info_fops = { .owner = THIS_MODULE, .open = jbd2_seq_info_open, .read = seq_read, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 00388d2a3c99..5c01fc148ce8 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -176,7 +176,7 @@ static const struct file_operations exports_operations = { extern int nfsd_pool_stats_open(struct inode *inode, struct file *file); extern int nfsd_pool_stats_release(struct inode *inode, struct file *file); -static struct file_operations pool_stats_operations = { +static const struct file_operations pool_stats_operations = { .open = nfsd_pool_stats_open, .read = seq_read, .llseek = seq_lseek, diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 1a4fa04cf071..e097099bfc8f 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -697,7 +697,7 @@ not_empty: return 0; } -struct file_operations nilfs_dir_operations = { +const struct file_operations nilfs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = nilfs_readdir, diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 7d7b4983dee3..30292df443ce 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -134,7 +134,7 @@ static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) * We have mostly NULL's here: the current defaults are ok for * the nilfs filesystem. */ -struct file_operations nilfs_file_operations = { +const struct file_operations nilfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index b18c4998f8d0..f6326112d647 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -433,7 +433,7 @@ static const struct address_space_operations def_mdt_aops = { }; static const struct inode_operations def_mdt_iops; -static struct file_operations def_mdt_fops; +static const struct file_operations def_mdt_fops; /* * NILFS2 uses pseudo inodes for meta data files such as DAT, cpfile, sufile, diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index bad7368782d0..4da6f67e9a91 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -294,9 +294,9 @@ void nilfs_clear_gcdat_inode(struct the_nilfs *); /* * Inodes and files operations */ -extern struct file_operations nilfs_dir_operations; +extern const struct file_operations nilfs_dir_operations; extern const struct inode_operations nilfs_file_inode_operations; -extern struct file_operations nilfs_file_operations; +extern const struct file_operations nilfs_file_operations; extern const struct address_space_operations nilfs_aops; extern const struct inode_operations nilfs_dir_inode_operations; extern const struct inode_operations nilfs_special_inode_operations; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 09cc25d04611..c452d116b892 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -966,7 +966,7 @@ static ssize_t o2hb_debug_read(struct file *file, char __user *buf, } #endif /* CONFIG_DEBUG_FS */ -static struct file_operations o2hb_debug_fops = { +static const struct file_operations o2hb_debug_fops = { .open = o2hb_debug_open, .release = o2hb_debug_release, .read = o2hb_debug_read, diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index cfb2be708abe..da794bc07a6c 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -207,7 +207,7 @@ static int nst_fop_release(struct inode *inode, struct file *file) return seq_release_private(inode, file); } -static struct file_operations nst_seq_fops = { +static const struct file_operations nst_seq_fops = { .open = nst_fop_open, .read = seq_read, .llseek = seq_lseek, @@ -388,7 +388,7 @@ static int sc_fop_release(struct inode *inode, struct file *file) return seq_release_private(inode, file); } -static struct file_operations sc_seq_fops = { +static const struct file_operations sc_seq_fops = { .open = sc_fop_open, .read = seq_read, .llseek = seq_lseek, diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index ca46002ec10e..42b0bad7a612 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -478,7 +478,7 @@ bail: return -ENOMEM; } -static struct file_operations debug_purgelist_fops = { +static const struct file_operations debug_purgelist_fops = { .open = debug_purgelist_open, .release = debug_buffer_release, .read = debug_buffer_read, @@ -538,7 +538,7 @@ bail: return -ENOMEM; } -static struct file_operations debug_mle_fops = { +static const struct file_operations debug_mle_fops = { .open = debug_mle_open, .release = debug_buffer_release, .read = debug_buffer_read, @@ -741,7 +741,7 @@ static int debug_lockres_release(struct inode *inode, struct file *file) return seq_release_private(inode, file); } -static struct file_operations debug_lockres_fops = { +static const struct file_operations debug_lockres_fops = { .open = debug_lockres_open, .release = debug_lockres_release, .read = seq_read, @@ -925,7 +925,7 @@ bail: return -ENOMEM; } -static struct file_operations debug_state_fops = { +static const struct file_operations debug_state_fops = { .open = debug_state_open, .release = debug_buffer_release, .read = debug_buffer_read, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 4cc3c890a2cd..c0e48aeebb1c 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -373,7 +373,7 @@ static ssize_t ocfs2_debug_read(struct file *file, char __user *buf, } #endif /* CONFIG_DEBUG_FS */ -static struct file_operations ocfs2_osb_debug_fops = { +static const struct file_operations ocfs2_osb_debug_fops = { .open = ocfs2_osb_debug_open, .release = ocfs2_debug_release, .read = ocfs2_debug_read, diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index 3680bae335b5..b42d62419034 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -498,7 +498,7 @@ const struct inode_operations omfs_dir_inops = { .rmdir = omfs_rmdir, }; -struct file_operations omfs_dir_operations = { +const struct file_operations omfs_dir_operations = { .read = generic_read_dir, .readdir = omfs_readdir, .llseek = generic_file_llseek, diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 4845fbb18e6e..399487c09364 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -322,7 +322,7 @@ static sector_t omfs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, omfs_get_block); } -struct file_operations omfs_file_operations = { +const struct file_operations omfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, diff --git a/fs/omfs/omfs.h b/fs/omfs/omfs.h index df71039945ac..ebe2fdbe535e 100644 --- a/fs/omfs/omfs.h +++ b/fs/omfs/omfs.h @@ -44,14 +44,14 @@ extern int omfs_allocate_range(struct super_block *sb, int min_request, extern int omfs_clear_range(struct super_block *sb, u64 block, int count); /* dir.c */ -extern struct file_operations omfs_dir_operations; +extern const struct file_operations omfs_dir_operations; extern const struct inode_operations omfs_dir_inops; extern int omfs_make_empty(struct inode *inode, struct super_block *sb); extern int omfs_is_bad(struct omfs_sb_info *sbi, struct omfs_header *header, u64 fsblock); /* file.c */ -extern struct file_operations omfs_file_operations; +extern const struct file_operations omfs_file_operations; extern const struct inode_operations omfs_file_inops; extern const struct address_space_operations omfs_aops; extern void omfs_make_empty_table(struct buffer_head *bh, int offset); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b62bb9294d0c..0008dee66514 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -37,7 +37,7 @@ extern void cgroup_exit(struct task_struct *p, int run_callbacks); extern int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); -extern struct file_operations proc_cgroup_operations; +extern const struct file_operations proc_cgroup_operations; /* Define the enumeration of all cgroup subsystems */ #define SUBSYS(_x) _x ## _subsys_id, diff --git a/include/linux/fs.h b/include/linux/fs.h index 2adaa2529f18..a1e6899d4b6c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2446,7 +2446,7 @@ static int __fops ## _open(struct inode *inode, struct file *file) \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ -static struct file_operations __fops = { \ +static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7ccba4bc5e3b..d2b88596efde 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -703,7 +703,7 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp); static const struct inode_operations cgroup_dir_inode_operations; -static struct file_operations proc_cgroupstats_operations; +static const struct file_operations proc_cgroupstats_operations; static struct backing_dev_info cgroup_backing_dev_info = { .name = "cgroup", @@ -1863,7 +1863,7 @@ static int cgroup_seqfile_release(struct inode *inode, struct file *file) return single_release(inode, file); } -static struct file_operations cgroup_seqfile_operations = { +static const struct file_operations cgroup_seqfile_operations = { .read = seq_read, .write = cgroup_file_write, .llseek = seq_lseek, @@ -1922,7 +1922,7 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry, return simple_rename(old_dir, old_dentry, new_dir, new_dentry); } -static struct file_operations cgroup_file_operations = { +static const struct file_operations cgroup_file_operations = { .read = cgroup_file_read, .write = cgroup_file_write, .llseek = generic_file_llseek, @@ -3369,7 +3369,7 @@ static int cgroup_open(struct inode *inode, struct file *file) return single_open(file, proc_cgroup_show, pid); } -struct file_operations proc_cgroup_operations = { +const struct file_operations proc_cgroup_operations = { .open = cgroup_open, .read = seq_read, .llseek = seq_lseek, @@ -3398,7 +3398,7 @@ static int cgroupstats_open(struct inode *inode, struct file *file) return single_open(file, proc_cgroupstats_show, NULL); } -static struct file_operations proc_cgroupstats_operations = { +static const struct file_operations proc_cgroupstats_operations = { .open = cgroupstats_open, .read = seq_read, .llseek = seq_lseek, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index cfadc1291d0b..5240d75f4c60 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1333,7 +1333,7 @@ static int __kprobes kprobes_open(struct inode *inode, struct file *filp) return seq_open(filp, &kprobes_seq_ops); } -static struct file_operations debugfs_kprobes_operations = { +static const struct file_operations debugfs_kprobes_operations = { .open = kprobes_open, .read = seq_read, .llseek = seq_lseek, @@ -1515,7 +1515,7 @@ static ssize_t write_enabled_file_bool(struct file *file, return count; } -static struct file_operations fops_kp = { +static const struct file_operations fops_kp = { .read = read_enabled_file_bool, .write = write_enabled_file_bool, }; diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index c89f5e9fd173..179e6ad80dc0 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -93,7 +93,7 @@ static int rcudata_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata, NULL); } -static struct file_operations rcudata_fops = { +static const struct file_operations rcudata_fops = { .owner = THIS_MODULE, .open = rcudata_open, .read = seq_read, @@ -145,7 +145,7 @@ static int rcudata_csv_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata_csv, NULL); } -static struct file_operations rcudata_csv_fops = { +static const struct file_operations rcudata_csv_fops = { .owner = THIS_MODULE, .open = rcudata_csv_open, .read = seq_read, @@ -196,7 +196,7 @@ static int rcuhier_open(struct inode *inode, struct file *file) return single_open(file, show_rcuhier, NULL); } -static struct file_operations rcuhier_fops = { +static const struct file_operations rcuhier_fops = { .owner = THIS_MODULE, .open = rcuhier_open, .read = seq_read, @@ -222,7 +222,7 @@ static int rcugp_open(struct inode *inode, struct file *file) return single_open(file, show_rcugp, NULL); } -static struct file_operations rcugp_fops = { +static const struct file_operations rcugp_fops = { .owner = THIS_MODULE, .open = rcugp_open, .read = seq_read, @@ -276,7 +276,7 @@ static int rcu_pending_open(struct inode *inode, struct file *file) return single_open(file, show_rcu_pending, NULL); } -static struct file_operations rcu_pending_fops = { +static const struct file_operations rcu_pending_fops = { .owner = THIS_MODULE, .open = rcu_pending_open, .read = seq_read, diff --git a/kernel/sched.c b/kernel/sched.c index ee61f454a98b..1535f3884b88 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -780,7 +780,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp) return single_open(filp, sched_feat_show, NULL); } -static struct file_operations sched_feat_fops = { +static const struct file_operations sched_feat_fops = { .open = sched_feat_open, .write = sched_feat_write, .read = seq_read, diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index fddd69d16e03..1b5b7aa2fdfd 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -275,7 +275,7 @@ static int timer_list_open(struct inode *inode, struct file *filp) return single_open(filp, timer_list_show, NULL); } -static struct file_operations timer_list_fops = { +static const struct file_operations timer_list_fops = { .open = timer_list_open, .read = seq_read, .llseek = seq_lseek, diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index 4cde8b9c716f..ee5681f8d7ec 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -395,7 +395,7 @@ static int tstats_open(struct inode *inode, struct file *filp) return single_open(filp, tstats_show, NULL); } -static struct file_operations tstats_fops = { +static const struct file_operations tstats_fops = { .open = tstats_open, .read = seq_read, .write = tstats_write, diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c index 9cf80a11e8b6..26fab33ffa8c 100644 --- a/samples/tracepoints/tracepoint-sample.c +++ b/samples/tracepoints/tracepoint-sample.c @@ -28,7 +28,7 @@ static int my_open(struct inode *inode, struct file *file) return -EPERM; } -static struct file_operations mark_ops = { +static const struct file_operations mark_ops = { .open = my_open, }; diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index 8e9777b76405..0c72c9c38956 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -43,7 +43,7 @@ static ssize_t ima_show_htable_violations(struct file *filp, return ima_show_htable_value(buf, count, ppos, &ima_htable.violations); } -static struct file_operations ima_htable_violations_ops = { +static const struct file_operations ima_htable_violations_ops = { .read = ima_show_htable_violations }; @@ -55,7 +55,7 @@ static ssize_t ima_show_measurements_count(struct file *filp, } -static struct file_operations ima_measurements_count_ops = { +static const struct file_operations ima_measurements_count_ops = { .read = ima_show_measurements_count }; @@ -158,7 +158,7 @@ static int ima_measurements_open(struct inode *inode, struct file *file) return seq_open(file, &ima_measurments_seqops); } -static struct file_operations ima_measurements_ops = { +static const struct file_operations ima_measurements_ops = { .open = ima_measurements_open, .read = seq_read, .llseek = seq_lseek, @@ -233,7 +233,7 @@ static int ima_ascii_measurements_open(struct inode *inode, struct file *file) return seq_open(file, &ima_ascii_measurements_seqops); } -static struct file_operations ima_ascii_measurements_ops = { +static const struct file_operations ima_ascii_measurements_ops = { .open = ima_ascii_measurements_open, .read = seq_read, .llseek = seq_lseek, @@ -313,7 +313,7 @@ static int ima_release_policy(struct inode *inode, struct file *file) return 0; } -static struct file_operations ima_measure_policy_ops = { +static const struct file_operations ima_measure_policy_ops = { .open = ima_open_policy, .write = ima_write_policy, .release = ima_release_policy diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b5e7e3f1183f..e79c54034bcd 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2625,7 +2625,7 @@ static int vcpu_stat_get(void *_offset, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n"); -static struct file_operations *stat_fops[] = { +static const struct file_operations *stat_fops[] = { [KVM_STAT_VCPU] = &vcpu_stat_fops, [KVM_STAT_VM] = &vm_stat_fops, }; -- cgit v1.2.3 From b3db4a8ad19173a8fd0ced13d47c97910f1ab14b Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Thu, 1 Oct 2009 15:43:56 -0700 Subject: asm-generic/gpio.h: pull in linux/kernel.h for might_sleep() The asm-generic/gpio.h header uses the might_sleep() macro but doesn't include the header for it, so any source code that might include linux/gpio.h before linux/kernel.h can easily lead to a build failure. Signed-off-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index 9cca3785cab8..66d6106a2067 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -1,6 +1,7 @@ #ifndef _ASM_GENERIC_GPIO_H #define _ASM_GENERIC_GPIO_H +#include #include #include -- cgit v1.2.3 From 4e649152cbaa1aedd01821d200ab9d597fe469e4 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 1 Oct 2009 15:44:11 -0700 Subject: memcg: some modification to softlimit under hierarchical memory reclaim. This patch clean up/fixes for memcg's uncharge soft limit path. Problems: Now, res_counter_charge()/uncharge() handles softlimit information at charge/uncharge and softlimit-check is done when event counter per memcg goes over limit. Now, event counter per memcg is updated only when memory usage is over soft limit. Here, considering hierarchical memcg management, ancesotors should be taken care of. Now, ancerstors(hierarchy) are handled in charge() but not in uncharge(). This is not good. Prolems: 1. memcg's event counter incremented only when softlimit hits. That's bad. It makes event counter hard to be reused for other purpose. 2. At uncharge, only the lowest level rescounter is handled. This is bug. Because ancesotor's event counter is not incremented, children should take care of them. 3. res_counter_uncharge()'s 3rd argument is NULL in most case. ops under res_counter->lock should be small. No "if" sentense is better. Fixes: * Removed soft_limit_xx poitner and checks in charge and uncharge. Do-check-only-when-necessary scheme works enough well without them. * make event-counter of memcg incremented at every charge/uncharge. (per-cpu area will be accessed soon anyway) * All ancestors are checked at soft-limit-check. This is necessary because ancesotor's event counter may never be modified. Then, they should be checked at the same time. Reviewed-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Cc: Li Zefan Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 6 +-- kernel/res_counter.c | 18 +------ mm/memcontrol.c | 113 ++++++++++++++++++++------------------------ 3 files changed, 54 insertions(+), 83 deletions(-) (limited to 'include') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 731af71cddc9..fcb9884df618 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -114,8 +114,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent); int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val, struct res_counter **limit_fail_at, - struct res_counter **soft_limit_at); + unsigned long val, struct res_counter **limit_fail_at); /* * uncharge - tell that some portion of the resource is released @@ -128,8 +127,7 @@ int __must_check res_counter_charge(struct res_counter *counter, */ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); -void res_counter_uncharge(struct res_counter *counter, unsigned long val, - bool *was_soft_limit_excess); +void res_counter_uncharge(struct res_counter *counter, unsigned long val); static inline bool res_counter_limit_check_locked(struct res_counter *cnt) { diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 88faec23e833..bcdabf37c40b 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -37,27 +37,17 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val) } int res_counter_charge(struct res_counter *counter, unsigned long val, - struct res_counter **limit_fail_at, - struct res_counter **soft_limit_fail_at) + struct res_counter **limit_fail_at) { int ret; unsigned long flags; struct res_counter *c, *u; *limit_fail_at = NULL; - if (soft_limit_fail_at) - *soft_limit_fail_at = NULL; local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); ret = res_counter_charge_locked(c, val); - /* - * With soft limits, we return the highest ancestor - * that exceeds its soft limit - */ - if (soft_limit_fail_at && - !res_counter_soft_limit_check_locked(c)) - *soft_limit_fail_at = c; spin_unlock(&c->lock); if (ret < 0) { *limit_fail_at = c; @@ -85,8 +75,7 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) counter->usage -= val; } -void res_counter_uncharge(struct res_counter *counter, unsigned long val, - bool *was_soft_limit_excess) +void res_counter_uncharge(struct res_counter *counter, unsigned long val) { unsigned long flags; struct res_counter *c; @@ -94,9 +83,6 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val, local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); - if (was_soft_limit_excess) - *was_soft_limit_excess = - !res_counter_soft_limit_check_locked(c); res_counter_uncharge_locked(c, val); spin_unlock(&c->lock); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 21a30629ca80..1ae8c439584a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -352,16 +352,6 @@ __mem_cgroup_remove_exceeded(struct mem_cgroup *mem, mz->on_tree = false; } -static void -mem_cgroup_insert_exceeded(struct mem_cgroup *mem, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) -{ - spin_lock(&mctz->lock); - __mem_cgroup_insert_exceeded(mem, mz, mctz); - spin_unlock(&mctz->lock); -} - static void mem_cgroup_remove_exceeded(struct mem_cgroup *mem, struct mem_cgroup_per_zone *mz, @@ -392,34 +382,40 @@ static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem) static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) { - unsigned long long prev_usage_in_excess, new_usage_in_excess; - bool updated_tree = false; + unsigned long long new_usage_in_excess; struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; - - mz = mem_cgroup_zoneinfo(mem, page_to_nid(page), page_zonenum(page)); + int nid = page_to_nid(page); + int zid = page_zonenum(page); mctz = soft_limit_tree_from_page(page); /* - * We do updates in lazy mode, mem's are removed - * lazily from the per-zone, per-node rb tree + * Necessary to update all ancestors when hierarchy is used. + * because their event counter is not touched. */ - prev_usage_in_excess = mz->usage_in_excess; - - new_usage_in_excess = res_counter_soft_limit_excess(&mem->res); - if (prev_usage_in_excess) { - mem_cgroup_remove_exceeded(mem, mz, mctz); - updated_tree = true; - } - if (!new_usage_in_excess) - goto done; - mem_cgroup_insert_exceeded(mem, mz, mctz); - -done: - if (updated_tree) { - spin_lock(&mctz->lock); - mz->usage_in_excess = new_usage_in_excess; - spin_unlock(&mctz->lock); + for (; mem; mem = parent_mem_cgroup(mem)) { + mz = mem_cgroup_zoneinfo(mem, nid, zid); + new_usage_in_excess = + res_counter_soft_limit_excess(&mem->res); + /* + * We have to update the tree if mz is on RB-tree or + * mem is over its softlimit. + */ + if (new_usage_in_excess || mz->on_tree) { + spin_lock(&mctz->lock); + /* if on-tree, remove it */ + if (mz->on_tree) + __mem_cgroup_remove_exceeded(mem, mz, mctz); + /* + * if over soft limit, insert again. mz->usage_in_excess + * will be updated properly. + */ + if (new_usage_in_excess) + __mem_cgroup_insert_exceeded(mem, mz, mctz); + else + mz->usage_in_excess = 0; + spin_unlock(&mctz->lock); + } } } @@ -1271,9 +1267,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom, struct page *page) { - struct mem_cgroup *mem, *mem_over_limit, *mem_over_soft_limit; + struct mem_cgroup *mem, *mem_over_limit; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct res_counter *fail_res, *soft_fail_res = NULL; + struct res_counter *fail_res; if (unlikely(test_thread_flag(TIF_MEMDIE))) { /* Don't account this! */ @@ -1305,17 +1301,16 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (mem_cgroup_is_root(mem)) goto done; - ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res, - &soft_fail_res); + ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); if (likely(!ret)) { if (!do_swap_account) break; ret = res_counter_charge(&mem->memsw, PAGE_SIZE, - &fail_res, NULL); + &fail_res); if (likely(!ret)) break; /* mem+swap counter fails */ - res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->res, PAGE_SIZE); flags |= MEM_CGROUP_RECLAIM_NOSWAP; mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); @@ -1354,16 +1349,11 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, } } /* - * Insert just the ancestor, we should trickle down to the correct - * cgroup for reclaim, since the other nodes will be below their - * soft limit + * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. + * if they exceeds softlimit. */ - if (soft_fail_res) { - mem_over_soft_limit = - mem_cgroup_from_res_counter(soft_fail_res, res); - if (mem_cgroup_soft_limit_check(mem_over_soft_limit)) - mem_cgroup_update_tree(mem_over_soft_limit, page); - } + if (mem_cgroup_soft_limit_check(mem)) + mem_cgroup_update_tree(mem, page); done: return 0; nomem: @@ -1438,10 +1428,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); if (!mem_cgroup_is_root(mem)) { - res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->res, PAGE_SIZE); if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE, - NULL); + res_counter_uncharge(&mem->memsw, PAGE_SIZE); } css_put(&mem->css); return; @@ -1520,7 +1509,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, goto out; if (!mem_cgroup_is_root(from)) - res_counter_uncharge(&from->res, PAGE_SIZE, NULL); + res_counter_uncharge(&from->res, PAGE_SIZE); mem_cgroup_charge_statistics(from, pc, false); page = pc->page; @@ -1540,7 +1529,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, } if (do_swap_account && !mem_cgroup_is_root(from)) - res_counter_uncharge(&from->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&from->memsw, PAGE_SIZE); css_put(&from->css); css_get(&to->css); @@ -1611,9 +1600,9 @@ uncharge: css_put(&parent->css); /* uncharge if move fails */ if (!mem_cgroup_is_root(parent)) { - res_counter_uncharge(&parent->res, PAGE_SIZE, NULL); + res_counter_uncharge(&parent->res, PAGE_SIZE); if (do_swap_account) - res_counter_uncharge(&parent->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&parent->memsw, PAGE_SIZE); } return ret; } @@ -1804,8 +1793,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, * calling css_tryget */ if (!mem_cgroup_is_root(memcg)) - res_counter_uncharge(&memcg->memsw, PAGE_SIZE, - NULL); + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } @@ -1832,9 +1820,9 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) if (!mem) return; if (!mem_cgroup_is_root(mem)) { - res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->res, PAGE_SIZE); if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->memsw, PAGE_SIZE); } css_put(&mem->css); } @@ -1849,7 +1837,6 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) struct page_cgroup *pc; struct mem_cgroup *mem = NULL; struct mem_cgroup_per_zone *mz; - bool soft_limit_excess = false; if (mem_cgroup_disabled()) return NULL; @@ -1889,10 +1876,10 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) } if (!mem_cgroup_is_root(mem)) { - res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess); + res_counter_uncharge(&mem->res, PAGE_SIZE); if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) - res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->memsw, PAGE_SIZE); } if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) mem_cgroup_swap_statistics(mem, true); @@ -1909,7 +1896,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mz = page_cgroup_zoneinfo(pc); unlock_page_cgroup(pc); - if (soft_limit_excess && mem_cgroup_soft_limit_check(mem)) + if (mem_cgroup_soft_limit_check(mem)) mem_cgroup_update_tree(mem, page); /* at swapout, this memcg will be accessed to record to swap */ if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT) @@ -1987,7 +1974,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) * This memcg can be obsolete one. We avoid calling css_tryget */ if (!mem_cgroup_is_root(memcg)) - res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } -- cgit v1.2.3 From 293500a23f4b0698cb04abfecfc9a954d8ab2742 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:04 +0000 Subject: connector: Keep the skb in cn_callback_data Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- drivers/connector/cn_queue.c | 3 ++- drivers/connector/connector.c | 11 +++++------ include/linux/connector.h | 4 ++-- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c index 4a1dfe1f4ba9..b4cfac93f723 100644 --- a/drivers/connector/cn_queue.c +++ b/drivers/connector/cn_queue.c @@ -78,8 +78,9 @@ void cn_queue_wrapper(struct work_struct *work) struct cn_callback_entry *cbq = container_of(work, struct cn_callback_entry, work); struct cn_callback_data *d = &cbq->data; + struct cn_msg *msg = NLMSG_DATA(nlmsg_hdr(d->skb)); - d->callback(d->callback_priv); + d->callback(msg); d->destruct_data(d->ddata); d->ddata = NULL; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 74f52af79563..fc9887fa453f 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -129,10 +129,11 @@ EXPORT_SYMBOL_GPL(cn_netlink_send); /* * Callback helper - queues work and setup destructor for given data. */ -static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), void *data) +static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), void *data) { struct cn_callback_entry *__cbq, *__new_cbq; struct cn_dev *dev = &cdev; + struct cn_msg *msg = NLMSG_DATA(nlmsg_hdr(skb)); int err = -ENODEV; spin_lock_bh(&dev->cbdev->queue_lock); @@ -140,7 +141,7 @@ static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), v if (cn_cb_equal(&__cbq->id.id, &msg->id)) { if (likely(!work_pending(&__cbq->work) && __cbq->data.ddata == NULL)) { - __cbq->data.callback_priv = msg; + __cbq->data.skb = skb; __cbq->data.ddata = data; __cbq->data.destruct_data = destruct_data; @@ -156,7 +157,7 @@ static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), v __new_cbq = kzalloc(sizeof(struct cn_callback_entry), GFP_ATOMIC); if (__new_cbq) { d = &__new_cbq->data; - d->callback_priv = msg; + d->skb = skb; d->callback = __cbq->data.callback; d->ddata = data; d->destruct_data = destruct_data; @@ -191,7 +192,6 @@ static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), v */ static void cn_rx_skb(struct sk_buff *__skb) { - struct cn_msg *msg; struct nlmsghdr *nlh; int err; struct sk_buff *skb; @@ -208,8 +208,7 @@ static void cn_rx_skb(struct sk_buff *__skb) return; } - msg = NLMSG_DATA(nlh); - err = cn_call_callback(msg, (void (*)(void *))kfree_skb, skb); + err = cn_call_callback(skb, (void (*)(void *))kfree_skb, skb); if (err < 0) kfree_skb(skb); } diff --git a/include/linux/connector.h b/include/linux/connector.h index 47ebf416f512..05a7a14126d8 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -134,8 +134,8 @@ struct cn_callback_id { struct cn_callback_data { void (*destruct_data) (void *); void *ddata; - - void *callback_priv; + + struct sk_buff *skb; void (*callback) (struct cn_msg *); void *free; -- cgit v1.2.3 From 7069331dbe7155f23966f5944109f909fea0c7e4 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:05 +0000 Subject: connector: Provide the sender's credentials to the callback Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- Documentation/connector/cn_test.c | 2 +- Documentation/connector/connector.txt | 8 ++++---- drivers/connector/cn_queue.c | 7 ++++--- drivers/connector/connector.c | 4 ++-- drivers/md/dm-log-userspace-transfer.c | 2 +- drivers/staging/dst/dcore.c | 2 +- drivers/staging/pohmelfs/config.c | 2 +- drivers/video/uvesafb.c | 2 +- drivers/w1/w1_netlink.c | 2 +- include/linux/connector.h | 6 +++--- 10 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c index 1711adc33373..b07add3467f1 100644 --- a/Documentation/connector/cn_test.c +++ b/Documentation/connector/cn_test.c @@ -34,7 +34,7 @@ static char cn_test_name[] = "cn_test"; static struct sock *nls; static struct timer_list cn_test_timer; -static void cn_test_callback(struct cn_msg *msg) +static void cn_test_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { pr_info("%s: %lu: idx=%x, val=%x, seq=%u, ack=%u, len=%d: %s.\n", __func__, jiffies, msg->id.idx, msg->id.val, diff --git a/Documentation/connector/connector.txt b/Documentation/connector/connector.txt index 81e6bf6ead57..78c9466a9aa8 100644 --- a/Documentation/connector/connector.txt +++ b/Documentation/connector/connector.txt @@ -23,7 +23,7 @@ handling, etc... The Connector driver allows any kernelspace agents to use netlink based networking for inter-process communication in a significantly easier way: -int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *)); +int cn_add_callback(struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *)); void cn_netlink_send(struct cn_msg *msg, u32 __group, int gfp_mask); struct cb_id @@ -53,15 +53,15 @@ struct cn_msg Connector interfaces. /*****************************************/ -int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *)); +int cn_add_callback(struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *)); Registers new callback with connector core. struct cb_id *id - unique connector's user identifier. It must be registered in connector.h for legal in-kernel users. char *name - connector's callback symbolic name. - void (*callback) (void *) - connector's callback. - Argument must be dereferenced to struct cn_msg *. + void (*callback) (struct cn..) - connector's callback. + cn_msg and the sender's credentials void cn_del_callback(struct cb_id *id); diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c index b4cfac93f723..163c3e3d0d11 100644 --- a/drivers/connector/cn_queue.c +++ b/drivers/connector/cn_queue.c @@ -79,8 +79,9 @@ void cn_queue_wrapper(struct work_struct *work) container_of(work, struct cn_callback_entry, work); struct cn_callback_data *d = &cbq->data; struct cn_msg *msg = NLMSG_DATA(nlmsg_hdr(d->skb)); + struct netlink_skb_parms *nsp = &NETLINK_CB(d->skb); - d->callback(msg); + d->callback(msg, nsp); d->destruct_data(d->ddata); d->ddata = NULL; @@ -90,7 +91,7 @@ void cn_queue_wrapper(struct work_struct *work) static struct cn_callback_entry * cn_queue_alloc_callback_entry(char *name, struct cb_id *id, - void (*callback)(struct cn_msg *)) + void (*callback)(struct cn_msg *, struct netlink_skb_parms *)) { struct cn_callback_entry *cbq; @@ -124,7 +125,7 @@ int cn_cb_equal(struct cb_id *i1, struct cb_id *i2) } int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, - void (*callback)(struct cn_msg *)) + void (*callback)(struct cn_msg *, struct netlink_skb_parms *)) { struct cn_callback_entry *cbq, *__cbq; int found = 0; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index fc9887fa453f..e59f0ab8f828 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -269,7 +269,7 @@ static void cn_notify(struct cb_id *id, u32 notify_event) * May sleep. */ int cn_add_callback(struct cb_id *id, char *name, - void (*callback)(struct cn_msg *)) + void (*callback)(struct cn_msg *, struct netlink_skb_parms *)) { int err; struct cn_dev *dev = &cdev; @@ -351,7 +351,7 @@ static int cn_ctl_msg_equals(struct cn_ctl_msg *m1, struct cn_ctl_msg *m2) * * Used for notification of a request's processing. */ -static void cn_callback(struct cn_msg *msg) +static void cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct cn_ctl_msg *ctl; struct cn_ctl_entry *ent; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index ba0edad2d048..556131f7d847 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -129,7 +129,7 @@ static int fill_pkg(struct cn_msg *msg, struct dm_ulog_request *tfr) * This is the connector callback that delivers data * that was sent from userspace. */ -static void cn_ulog_callback(void *data) +static void cn_ulog_callback(void *data, struct netlink_skb_parms *nsp) { struct cn_msg *msg = (struct cn_msg *)data; struct dm_ulog_request *tfr = (struct dm_ulog_request *)(msg + 1); diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c index ac8577358ba0..3943c91e6c96 100644 --- a/drivers/staging/dst/dcore.c +++ b/drivers/staging/dst/dcore.c @@ -847,7 +847,7 @@ static dst_command_func dst_commands[] = { /* * Configuration parser. */ -static void cn_dst_callback(struct cn_msg *msg) +static void cn_dst_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct dst_ctl *ctl; int err; diff --git a/drivers/staging/pohmelfs/config.c b/drivers/staging/pohmelfs/config.c index 90f962ee5fd8..c9162b3f0bf3 100644 --- a/drivers/staging/pohmelfs/config.c +++ b/drivers/staging/pohmelfs/config.c @@ -527,7 +527,7 @@ out_unlock: return err; } -static void pohmelfs_cn_callback(struct cn_msg *msg) +static void pohmelfs_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { int err; diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c index e98baf6916b8..aa7cd959cced 100644 --- a/drivers/video/uvesafb.c +++ b/drivers/video/uvesafb.c @@ -67,7 +67,7 @@ static DEFINE_MUTEX(uvfb_lock); * find the kernel part of the task struct, copy the registers and * the buffer contents and then complete the task. */ -static void uvesafb_cn_callback(struct cn_msg *msg) +static void uvesafb_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct uvesafb_task *utask; struct uvesafb_ktask *task; diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c index 52ccb3d3a963..45c126fea31d 100644 --- a/drivers/w1/w1_netlink.c +++ b/drivers/w1/w1_netlink.c @@ -306,7 +306,7 @@ static int w1_netlink_send_error(struct cn_msg *rcmsg, struct w1_netlink_msg *rm return error; } -static void w1_cn_callback(struct cn_msg *msg) +static void w1_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct w1_netlink_msg *m = (struct w1_netlink_msg *)(msg + 1); struct w1_netlink_cmd *cmd; diff --git a/include/linux/connector.h b/include/linux/connector.h index 05a7a14126d8..545728e20b63 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -136,7 +136,7 @@ struct cn_callback_data { void *ddata; struct sk_buff *skb; - void (*callback) (struct cn_msg *); + void (*callback) (struct cn_msg *, struct netlink_skb_parms *); void *free; }; @@ -167,11 +167,11 @@ struct cn_dev { struct cn_queue_dev *cbdev; }; -int cn_add_callback(struct cb_id *, char *, void (*callback) (struct cn_msg *)); +int cn_add_callback(struct cb_id *, char *, void (*callback) (struct cn_msg *, struct netlink_skb_parms *)); void cn_del_callback(struct cb_id *); int cn_netlink_send(struct cn_msg *, u32, gfp_t); -int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(struct cn_msg *)); +int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(struct cn_msg *, struct netlink_skb_parms *)); void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id); int queue_cn_work(struct cn_callback_entry *cbq, struct work_struct *work); -- cgit v1.2.3 From f1489cfb173509a3c13444b46b6c989bad4f5b16 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:07 +0000 Subject: connector: Removed the destruct_data callback since it is always kfree_skb() Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- drivers/connector/cn_queue.c | 4 ++-- drivers/connector/connector.c | 11 +++-------- include/linux/connector.h | 3 --- 3 files changed, 5 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c index 163c3e3d0d11..210338ea222f 100644 --- a/drivers/connector/cn_queue.c +++ b/drivers/connector/cn_queue.c @@ -83,8 +83,8 @@ void cn_queue_wrapper(struct work_struct *work) d->callback(msg, nsp); - d->destruct_data(d->ddata); - d->ddata = NULL; + kfree_skb(d->skb); + d->skb = NULL; kfree(d->free); } diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index e59f0ab8f828..f06024668f99 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -129,7 +129,7 @@ EXPORT_SYMBOL_GPL(cn_netlink_send); /* * Callback helper - queues work and setup destructor for given data. */ -static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), void *data) +static int cn_call_callback(struct sk_buff *skb) { struct cn_callback_entry *__cbq, *__new_cbq; struct cn_dev *dev = &cdev; @@ -140,12 +140,9 @@ static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), list_for_each_entry(__cbq, &dev->cbdev->queue_list, callback_entry) { if (cn_cb_equal(&__cbq->id.id, &msg->id)) { if (likely(!work_pending(&__cbq->work) && - __cbq->data.ddata == NULL)) { + __cbq->data.skb == NULL)) { __cbq->data.skb = skb; - __cbq->data.ddata = data; - __cbq->data.destruct_data = destruct_data; - if (queue_cn_work(__cbq, &__cbq->work)) err = 0; else @@ -159,8 +156,6 @@ static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), d = &__new_cbq->data; d->skb = skb; d->callback = __cbq->data.callback; - d->ddata = data; - d->destruct_data = destruct_data; d->free = __new_cbq; __new_cbq->pdev = __cbq->pdev; @@ -208,7 +203,7 @@ static void cn_rx_skb(struct sk_buff *__skb) return; } - err = cn_call_callback(skb, (void (*)(void *))kfree_skb, skb); + err = cn_call_callback(skb); if (err < 0) kfree_skb(skb); } diff --git a/include/linux/connector.h b/include/linux/connector.h index 545728e20b63..3a14615fd35c 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -132,9 +132,6 @@ struct cn_callback_id { }; struct cn_callback_data { - void (*destruct_data) (void *); - void *ddata; - struct sk_buff *skb; void (*callback) (struct cn_msg *, struct netlink_skb_parms *); -- cgit v1.2.3 From 8e2967555571659d2c8a70dd120710110ed7bba4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 3 Oct 2009 16:26:03 +0200 Subject: cfq-iosched: implement slower async initiate and queue ramp up This slowly ramps up the async queue depth based on the time passed since the sync IO, and doesn't allow async at all until a sync slice period has passed. Signed-off-by: Jens Axboe --- block/blk-core.c | 8 ++++++++ block/cfq-iosched.c | 56 ++++++++++++++++++++++++++++++++------------------ include/linux/blkdev.h | 4 ++++ 3 files changed, 48 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index ddaaea4fdffc..a8c7fbe52e24 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2492,6 +2492,14 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay) +{ + return queue_delayed_work(kblockd_workqueue, work, delay); +} +EXPORT_SYMBOL(kblockd_schedule_delayed_work); + int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 70b48ea0e3e9..fce8a749f4be 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -150,7 +150,7 @@ struct cfq_data { * idle window management */ struct timer_list idle_slice_timer; - struct work_struct unplug_work; + struct delayed_work unplug_work; struct cfq_queue *active_queue; struct cfq_io_context *active_cic; @@ -268,11 +268,13 @@ static inline int cfq_bio_sync(struct bio *bio) * scheduler run of queue, if there are requests pending and no one in the * driver that will restart queueing */ -static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) +static inline void cfq_schedule_dispatch(struct cfq_data *cfqd, + unsigned long delay) { if (cfqd->busy_queues) { cfq_log(cfqd, "schedule dispatch"); - kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work); + kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work, + delay); } } @@ -1316,8 +1318,6 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) * Does this cfqq already have too much IO in flight? */ if (cfqq->dispatched >= max_dispatch) { - unsigned long load_at = cfqd->last_end_sync_rq + cfq_slice_sync; - /* * idle queue must always only have a single IO in flight */ @@ -1331,20 +1331,36 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) return 0; /* - * If a sync request has completed recently, don't overload - * the dispatch queue yet with async requests. + * Sole queue user, allow bigger slice */ - if (cfqd->cfq_desktop && !cfq_cfqq_sync(cfqq) - && time_before(jiffies, load_at)) - return 0; + max_dispatch *= 4; + } + + /* + * Async queues must wait a bit before being allowed dispatch. + * We also ramp up the dispatch depth gradually for async IO, + * based on the last sync IO we serviced + */ + if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_desktop) { + unsigned long last_sync = jiffies - cfqd->last_end_sync_rq; + unsigned int depth; /* - * we are the only queue, allow up to 4 times of 'quantum' + * must wait a bit longer */ - if (cfqq->dispatched >= 4 * max_dispatch) + if (last_sync < cfq_slice_sync) { + cfq_schedule_dispatch(cfqd, cfq_slice_sync - last_sync); return 0; + } + + depth = last_sync / cfq_slice_sync; + if (depth < max_dispatch) + max_dispatch = depth; } + if (cfqq->dispatched >= max_dispatch) + return 0; + /* * Dispatch a request from this cfqq */ @@ -1389,7 +1405,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } kmem_cache_free(cfq_pool, cfqq); @@ -1484,7 +1500,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (unlikely(cfqq == cfqd->active_queue)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } cfq_put_queue(cfqq); @@ -2201,7 +2217,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) } if (!rq_in_driver(cfqd)) - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } /* @@ -2331,7 +2347,7 @@ queue_fail: if (cic) put_io_context(cic->ioc); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); spin_unlock_irqrestore(q->queue_lock, flags); cfq_log(cfqd, "set_request fail"); return 1; @@ -2340,7 +2356,7 @@ queue_fail: static void cfq_kick_queue(struct work_struct *work) { struct cfq_data *cfqd = - container_of(work, struct cfq_data, unplug_work); + container_of(work, struct cfq_data, unplug_work.work); struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); @@ -2394,7 +2410,7 @@ static void cfq_idle_slice_timer(unsigned long data) expire: cfq_slice_expired(cfqd, timed_out); out_kick: - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); out_cont: spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); } @@ -2402,7 +2418,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - cancel_work_sync(&cfqd->unplug_work); + cancel_delayed_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2484,7 +2500,7 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->idle_slice_timer.function = cfq_idle_slice_timer; cfqd->idle_slice_timer.data = (unsigned long) cfqd; - INIT_WORK(&cfqd->unplug_work, cfq_kick_queue); + INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue); cfqd->cfq_quantum = cfq_quantum; cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0]; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1a03b715dfad..a7323930d2ba 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1147,7 +1147,11 @@ static inline void put_dev_sector(Sector p) } struct work_struct; +struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From ac481c20ef8f6c6f2be75d581863f40c43874ef7 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Sat, 3 Oct 2009 20:52:01 +0200 Subject: block: Topology ioctls Not all users of the topology information want to use libblkid. Provide the topology information through bdev ioctls. Also clarify sector size comments for existing BLK ioctls. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/compat_ioctl.c | 13 +++++++++++++ block/ioctl.c | 17 +++++++++++++++-- include/linux/blkdev.h | 35 ++++++++++++++++++++++++++++++----- include/linux/fs.h | 4 ++++ 4 files changed, 62 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 7865a34e0faa..9bd086c1a4d5 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -21,6 +21,11 @@ static int compat_put_int(unsigned long arg, int val) return put_user(val, (compat_int_t __user *)compat_ptr(arg)); } +static int compat_put_uint(unsigned long arg, unsigned int val) +{ + return put_user(val, (compat_uint_t __user *)compat_ptr(arg)); +} + static int compat_put_long(unsigned long arg, long val) { return put_user(val, (compat_long_t __user *)compat_ptr(arg)); @@ -734,6 +739,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) switch (cmd) { case HDIO_GETGEO: return compat_hdio_getgeo(disk, bdev, compat_ptr(arg)); + case BLKPBSZGET: + return compat_put_uint(arg, bdev_physical_block_size(bdev)); + case BLKIOMIN: + return compat_put_uint(arg, bdev_io_min(bdev)); + case BLKIOOPT: + return compat_put_uint(arg, bdev_io_opt(bdev)); + case BLKALIGNOFF: + return compat_put_int(arg, bdev_alignment_offset(bdev)); case BLKFLSBUF: case BLKROSET: case BLKDISCARD: diff --git a/block/ioctl.c b/block/ioctl.c index d3e6b5827a34..1f4d1de12b09 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -138,6 +138,11 @@ static int put_int(unsigned long arg, int val) return put_user(val, (int __user *)arg); } +static int put_uint(unsigned long arg, unsigned int val) +{ + return put_user(val, (unsigned int __user *)arg); +} + static int put_long(unsigned long arg, long val) { return put_user(val, (long __user *)arg); @@ -263,10 +268,18 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); case BLKROGET: return put_int(arg, bdev_read_only(bdev) != 0); - case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */ + case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(arg, block_size(bdev)); - case BLKSSZGET: /* get block device hardware sector size */ + case BLKSSZGET: /* get block device logical block size */ return put_int(arg, bdev_logical_block_size(bdev)); + case BLKPBSZGET: /* get block device physical block size */ + return put_uint(arg, bdev_physical_block_size(bdev)); + case BLKIOMIN: + return put_uint(arg, bdev_io_min(bdev)); + case BLKIOOPT: + return put_uint(arg, bdev_io_opt(bdev)); + case BLKALIGNOFF: + return put_int(arg, bdev_alignment_offset(bdev)); case BLKSECTGET: return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev))); case BLKRASET: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a7323930d2ba..25119041e034 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1081,25 +1081,37 @@ static inline unsigned int queue_physical_block_size(struct request_queue *q) return q->limits.physical_block_size; } +static inline int bdev_physical_block_size(struct block_device *bdev) +{ + return queue_physical_block_size(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_min(struct request_queue *q) { return q->limits.io_min; } +static inline int bdev_io_min(struct block_device *bdev) +{ + return queue_io_min(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_opt(struct request_queue *q) { return q->limits.io_opt; } +static inline int bdev_io_opt(struct block_device *bdev) +{ + return queue_io_opt(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(struct request_queue *q) { - if (q && q->limits.misaligned) + if (q->limits.misaligned) return -1; - if (q && q->limits.alignment_offset) - return q->limits.alignment_offset; - - return 0; + return q->limits.alignment_offset; } static inline int queue_sector_alignment_offset(struct request_queue *q, @@ -1109,6 +1121,19 @@ static inline int queue_sector_alignment_offset(struct request_queue *q, & (q->limits.io_min - 1); } +static inline int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + + if (bdev != bdev->bd_contains) + return bdev->bd_part->alignment_offset; + + return q->limits.alignment_offset; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/fs.h b/include/linux/fs.h index 2adaa2529f18..883eaacfd924 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -300,6 +300,10 @@ struct inodes_stat_t { #define BLKTRACESTOP _IO(0x12,117) #define BLKTRACETEARDOWN _IO(0x12,118) #define BLKDISCARD _IO(0x12,119) +#define BLKIOMIN _IO(0x12,120) +#define BLKIOOPT _IO(0x12,121) +#define BLKALIGNOFF _IO(0x12,122) +#define BLKPBSZGET _IO(0x12,123) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 0f78ab9899e9d6acb09d5465def618704255963b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 4 Oct 2009 21:04:38 +0200 Subject: Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe --- block/blk-core.c | 6 +++--- block/blk-merge.c | 2 +- block/genhd.c | 4 +--- drivers/md/dm.c | 16 ++++++---------- fs/partitions/check.c | 12 +----------- include/linux/genhd.h | 21 +++++++-------------- 6 files changed, 19 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index a8c7fbe52e24..81f34311659a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -70,7 +70,7 @@ static void drive_stat_acct(struct request *rq, int new_io) part_stat_inc(cpu, part, merges[rw]); else { part_round_stats(cpu, part); - part_inc_in_flight(part, rw); + part_inc_in_flight(part); } part_stat_unlock(); @@ -1032,7 +1032,7 @@ static void part_round_stats_single(int cpu, struct hd_struct *part, if (part->in_flight) { __part_stat_add(cpu, part, time_in_queue, - part_in_flight(part) * (now - part->stamp)); + part->in_flight * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); } part->stamp = now; @@ -1739,7 +1739,7 @@ static void blk_account_io_done(struct request *req) part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); part_round_stats(cpu, part); - part_dec_in_flight(part, rw); + part_dec_in_flight(part); part_stat_unlock(); } diff --git a/block/blk-merge.c b/block/blk-merge.c index 99cb5cf1f447..b0de8574fdc8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req) part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_round_stats(cpu, part); - part_dec_in_flight(part, rq_data_dir(req)); + part_dec_in_flight(part); part_stat_unlock(); } diff --git a/block/genhd.c b/block/genhd.c index 517e4332cb37..5a0861da324d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -869,7 +869,6 @@ static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); -static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -889,7 +888,6 @@ static struct attribute *disk_attrs[] = { &dev_attr_alignment_offset.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, - &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1055,7 +1053,7 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, merges[1]), (unsigned long long)part_stat_read(hd, sectors[1]), jiffies_to_msecs(part_stat_read(hd, ticks[1])), - part_in_flight(hd), + hd->in_flight, jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)) ); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 376f1ab48a24..23e76fe0d359 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -130,7 +130,7 @@ struct mapped_device { /* * A list of ios that arrived while we were suspended. */ - atomic_t pending[2]; + atomic_t pending; wait_queue_head_t wait; struct work_struct work; struct bio_list deferred; @@ -453,14 +453,13 @@ static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; int cpu; - int rw = bio_data_dir(io->bio); io->start_time = jiffies; cpu = part_stat_lock(); part_round_stats(cpu, &dm_disk(md)->part0); part_stat_unlock(); - dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]); + dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending); } static void end_io_acct(struct dm_io *io) @@ -480,9 +479,8 @@ static void end_io_acct(struct dm_io *io) * After this is decremented the bio must not be touched if it is * a barrier. */ - dm_disk(md)->part0.in_flight[rw] = pending = - atomic_dec_return(&md->pending[rw]); - pending += atomic_read(&md->pending[rw^0x1]); + dm_disk(md)->part0.in_flight = pending = + atomic_dec_return(&md->pending); /* nudge anyone waiting on suspend queue */ if (!pending) @@ -1787,8 +1785,7 @@ static struct mapped_device *alloc_dev(int minor) if (!md->disk) goto bad_disk; - atomic_set(&md->pending[0], 0); - atomic_set(&md->pending[1], 0); + atomic_set(&md->pending, 0); init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); init_waitqueue_head(&md->eventq); @@ -2091,8 +2088,7 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) break; } spin_unlock_irqrestore(q->queue_lock, flags); - } else if (!atomic_read(&md->pending[0]) && - !atomic_read(&md->pending[1])) + } else if (!atomic_read(&md->pending)) break; if (interruptible == TASK_INTERRUPTIBLE && diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 7b685e10cbad..f38fee0311a7 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -248,19 +248,11 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, merges[WRITE]), (unsigned long long)part_stat_read(p, sectors[WRITE]), jiffies_to_msecs(part_stat_read(p, ticks[WRITE])), - part_in_flight(p), + p->in_flight, jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue))); } -ssize_t part_inflight_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct hd_struct *p = dev_to_part(dev); - - return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]); -} - #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -289,7 +281,6 @@ static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); -static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -301,7 +292,6 @@ static struct attribute *part_attrs[] = { &dev_attr_size.attr, &dev_attr_alignment_offset.attr, &dev_attr_stat.attr, - &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 297df45ffd0a..7beaa21b3880 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -98,7 +98,7 @@ struct hd_struct { int make_it_fail; #endif unsigned long stamp; - int in_flight[2]; + int in_flight; #ifdef CONFIG_SMP struct disk_stats *dkstats; #else @@ -322,23 +322,18 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part, int rw) +static inline void part_inc_in_flight(struct hd_struct *part) { - part->in_flight[rw]++; + part->in_flight++; if (part->partno) - part_to_disk(part)->part0.in_flight[rw]++; + part_to_disk(part)->part0.in_flight++; } -static inline void part_dec_in_flight(struct hd_struct *part, int rw) +static inline void part_dec_in_flight(struct hd_struct *part) { - part->in_flight[rw]--; + part->in_flight--; if (part->partno) - part_to_disk(part)->part0.in_flight[rw]--; -} - -static inline int part_in_flight(struct hd_struct *part) -{ - return part->in_flight[0] + part->in_flight[1]; + part_to_disk(part)->part0.in_flight--; } /* block/blk-core.c */ @@ -551,8 +546,6 @@ extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); -extern ssize_t part_inflight_show(struct device *dev, - struct device_attribute *attr, char *buf); #ifdef CONFIG_FAIL_MAKE_REQUEST extern ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); -- cgit v1.2.3 From a99bbaf5ee6bad1aca0c88ea65ec6e5373e86184 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 4 Oct 2009 16:11:37 +0400 Subject: headers: remove sched.h from poll.h Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- drivers/char/dtlk.c | 1 + drivers/char/ipmi/ipmi_devintf.c | 1 + drivers/char/ipmi/ipmi_msghandler.c | 1 + drivers/firewire/core-cdev.c | 1 + drivers/hid/hidraw.c | 1 + drivers/infiniband/core/ucm.c | 1 + drivers/infiniband/core/user_mad.c | 1 + drivers/infiniband/core/uverbs_main.c | 1 + drivers/input/evdev.c | 1 + drivers/input/input.c | 1 + drivers/input/joydev.c | 1 + drivers/input/misc/uinput.c | 1 + drivers/input/mousedev.c | 1 + drivers/isdn/divert/divert_procfs.c | 1 + drivers/media/dvb/dvb-core/dmxdev.c | 1 + drivers/media/dvb/dvb-core/dvb_demux.c | 1 + drivers/media/radio/radio-cadet.c | 1 + drivers/media/video/cpia.c | 1 + drivers/mfd/ucb1400_core.c | 1 + drivers/usb/gadget/inode.c | 1 + drivers/xen/xenfs/xenbus.c | 1 + fs/anon_inodes.c | 2 ++ fs/coda/psdev.c | 1 + fs/select.c | 1 + include/linux/poll.h | 2 +- net/rfkill/core.c | 1 + 26 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c index 52e06589821d..045c930e6320 100644 --- a/drivers/char/dtlk.c +++ b/drivers/char/dtlk.c @@ -56,6 +56,7 @@ #include /* for -EBUSY */ #include /* for request_region */ #include /* for loops_per_jiffy */ +#include #include /* cycle_kernel_lock() */ #include /* for inb_p, outb_p, inb, outb, etc. */ #include /* for get_user, etc. */ diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index 41fc11dc921c..65545de3dbf4 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 09050797c76a..ec5e3f8df648 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index ced186d7e9a9..5089331544ed 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index 0c6639ea03dd..ba05275e5104 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 51bd9669cb1f..f504c9b00c1b 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 8c46f2257098..7de02969ed7d 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index d3fff9e008a3..aec0fbdfe7f0 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 1148140d08a1..dee6706038aa 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -13,6 +13,7 @@ #define EVDEV_BUFFER_SIZE 64 #include +#include #include #include #include diff --git a/drivers/input/input.c b/drivers/input/input.c index 16ec33f27c5d..c6f88ebb40c7 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index 901b2525993e..b1bd6dd32286 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index c5a49aba418f..d3f57245420a 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -30,6 +30,7 @@ * - first public version */ #include +#include #include #include #include diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index 966b8868f792..a13d80f7da17 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -13,6 +13,7 @@ #define MOUSEDEV_MINORS 32 #define MOUSEDEV_MIX 31 +#include #include #include #include diff --git a/drivers/isdn/divert/divert_procfs.c b/drivers/isdn/divert/divert_procfs.c index 8b256a617c8a..3697c409bec6 100644 --- a/drivers/isdn/divert/divert_procfs.c +++ b/drivers/isdn/divert/divert_procfs.c @@ -16,6 +16,7 @@ #else #include #endif +#include #include #include #include "isdn_divert.h" diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c index 516414983593..c37790ad92d0 100644 --- a/drivers/media/dvb/dvb-core/dmxdev.c +++ b/drivers/media/dvb/dvb-core/dmxdev.c @@ -20,6 +20,7 @@ * */ +#include #include #include #include diff --git a/drivers/media/dvb/dvb-core/dvb_demux.c b/drivers/media/dvb/dvb-core/dvb_demux.c index eef6d3616626..91c537bca8ad 100644 --- a/drivers/media/dvb/dvb-core/dvb_demux.c +++ b/drivers/media/dvb/dvb-core/dvb_demux.c @@ -21,6 +21,7 @@ * */ +#include #include #include #include diff --git a/drivers/media/radio/radio-cadet.c b/drivers/media/radio/radio-cadet.c index 8b1440136c45..482d0f3be5ff 100644 --- a/drivers/media/radio/radio-cadet.c +++ b/drivers/media/radio/radio-cadet.c @@ -38,6 +38,7 @@ #include /* V4L2 API defs */ #include #include +#include #include /* outb, outb_p */ #include #include diff --git a/drivers/media/video/cpia.c b/drivers/media/video/cpia.c index 43ab0adf3b61..2377313c041a 100644 --- a/drivers/media/video/cpia.c +++ b/drivers/media/video/cpia.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/mfd/ucb1400_core.c b/drivers/mfd/ucb1400_core.c index 2afc08006e6d..fa294b6d600a 100644 --- a/drivers/mfd/ucb1400_core.c +++ b/drivers/mfd/ucb1400_core.c @@ -21,6 +21,7 @@ */ #include +#include #include unsigned int ucb1400_adc_read(struct snd_ac97 *ac97, u16 adc_channel, diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index c44367fea185..bf0f6520c6df 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c index a9592d981b10..6c4269b836b7 100644 --- a/drivers/xen/xenfs/xenbus.c +++ b/drivers/xen/xenfs/xenbus.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index d11c51fc2a3f..2ca7a7cafdbf 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -8,8 +8,10 @@ * */ +#include #include #include +#include #include #include #include diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index 0376ac66c44a..be4392ca2098 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/select.c b/fs/select.c index a201fc370223..fd38ce2e32e3 100644 --- a/fs/select.c +++ b/fs/select.c @@ -15,6 +15,7 @@ */ #include +#include #include #include #include diff --git a/include/linux/poll.h b/include/linux/poll.h index fa287f25138d..6673743946f7 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -6,10 +6,10 @@ #ifdef __KERNEL__ #include +#include #include #include #include -#include #include /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating diff --git a/net/rfkill/core.c b/net/rfkill/core.c index dbeaf2983822..ba2efb960c60 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3