From ee8209fd026b074bb8eb75bece516a338a281b1b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 8 May 2013 11:55:48 +0300 Subject: dma: acpi-dma: parse CSRT to extract additional resources Since we have CSRT only to get additional DMA controller resources, let's get rid of drivers/acpi/csrt.c and move its logic inside ACPI DMA helpers code. Signed-off-by: Andy Shevchenko Signed-off-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Vinod Koul --- include/linux/acpi_dma.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h index d09deabc7bf6..fb0298082916 100644 --- a/include/linux/acpi_dma.h +++ b/include/linux/acpi_dma.h @@ -37,6 +37,8 @@ struct acpi_dma_spec { * @dev: struct device of this controller * @acpi_dma_xlate: callback function to find a suitable channel * @data: private data used by a callback function + * @base_request_line: first supported request line (CSRT) + * @end_request_line: last supported request line (CSRT) */ struct acpi_dma { struct list_head dma_controllers; @@ -44,6 +46,8 @@ struct acpi_dma { struct dma_chan *(*acpi_dma_xlate) (struct acpi_dma_spec *, struct acpi_dma *); void *data; + unsigned short base_request_line; + unsigned short end_request_line; }; /* Used with acpi_dma_simple_xlate() */ -- cgit v1.2.3 From b59cc200ac025aca597fb21862c1c9e667f2eff2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 8 May 2013 11:55:49 +0300 Subject: ACPI / LPSS: register clock device for Lynxpoint DMA properly The DMA controller in Lynxpoint is enumerated as a regular ACPI device now. To work properly it is using the LPSS root clock as a functional clock. That's why we have to register the clock device accordingly to the ACPI ID of the DMA controller. The acpi_lpss.c module is responsible to do the job. This patch also removes hardcoded name of the DMA device in clk-lpt.c and the name of the root clock in acpi_lpss.c. Signed-off-by: Rafael J. Wysocki Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- include/linux/platform_data/clk-lpss.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-lpss.h b/include/linux/platform_data/clk-lpss.h index 528e73ce46d2..23901992b9dd 100644 --- a/include/linux/platform_data/clk-lpss.h +++ b/include/linux/platform_data/clk-lpss.h @@ -13,6 +13,11 @@ #ifndef __CLK_LPSS_H #define __CLK_LPSS_H +struct lpss_clk_data { + const char *name; + struct clk *clk; +}; + extern int lpt_clk_init(void); #endif /* __CLK_LPSS_H */ -- cgit v1.2.3 From 7f18d05a1af75142d4856a91ffd2f1d8eb553c12 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 15 May 2013 20:18:41 +0530 Subject: SERIAL: OMAP: Remove the slave idle handling from the driver UART IP slave idle handling now taken care by runtime pm backend(hwmod layer) so remove the hackery from the driver. As discussed on the list, in future if dma mode needs to be brought back to this driver, UART sysc handling needs to be updated in framework such a way that no-idle/force idle profile can be supported. Given the broken dma mode for OMAP uarts, its very unlikely. Acked-by: Greg Kroah-Hartman Tested-by: Vaibhav Bedia Tested-by: Sourav Poddar Signed-off-by: Rajendra nayak Signed-off-by: Santosh Shilimkar Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman # OMAP4/Panda Signed-off-by: Paul Walmsley --- include/linux/platform_data/serial-omap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-omap.h b/include/linux/platform_data/serial-omap.h index ff9b0aab5281..c860c1b314c0 100644 --- a/include/linux/platform_data/serial-omap.h +++ b/include/linux/platform_data/serial-omap.h @@ -43,8 +43,6 @@ struct omap_uart_port_info { int DTR_present; int (*get_context_loss_count)(struct device *); - void (*set_forceidle)(struct device *); - void (*set_noidle)(struct device *); void (*enable_wakeup)(struct device *, bool); }; -- cgit v1.2.3 From 2a7851bffb008ff4882eee673da74718997b4265 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 May 2013 03:56:10 +0000 Subject: netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6 Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812: [ ip6tables -m addrtype ] When I tried to use in the nat/PREROUTING it messes up the routing cache even if the rule didn't matched at all. [..] If I remove the --limit-iface-in from the non-working scenario, so just use the -m addrtype --dst-type LOCAL it works! This happens when LOCAL type matching is requested with --limit-iface-in, and the default ipv6 route is via the interface the packet we test arrived on. Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation creates an unwanted cached entry, and the packet won't make it to the real/expected destination. Silently ignoring --limit-iface-in makes the routing work but it breaks rule matching (--dst-type LOCAL with limit-iface-in is supposed to only match if the dst address is configured on the incoming interface; without --limit-iface-in it will match if the address is reachable via lo). The test should call ipv6_chk_addr() instead. However, this would add a link-time dependency on ipv6. There are two possible solutions: 1) Revert the commit that moved ipt_addrtype to xt_addrtype, and put ipv6 specific code into ip6t_addrtype. 2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions. While the former might seem preferable, Pablo pointed out that there are more xt modules with link-time dependeny issues regarding ipv6, so lets go for 2). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 98ffb54988b6..2d4df6ce043e 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -17,6 +17,22 @@ extern __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, extern int ipv6_netfilter_init(void); extern void ipv6_netfilter_fini(void); + +/* + * Hook functions for ipv6 to allow xt_* modules to be built-in even + * if IPv6 is a module. + */ +struct nf_ipv6_ops { + int (*chk_addr)(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict); +}; + +extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops; +static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) +{ + return rcu_dereference(nf_ipv6_ops); +} + #else /* CONFIG_NETFILTER */ static inline int ipv6_netfilter_init(void) { return 0; } static inline void ipv6_netfilter_fini(void) { return; } -- cgit v1.2.3 From 7805d000db30a3787a4c969bab6ae4d8a5fd8ce6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 24 May 2013 10:50:24 +0900 Subject: cgroup: fix a subtle bug in descendant pre-order walk When cgroup_next_descendant_pre() initiates a walk, it checks whether the subtree root doesn't have any children and if not returns NULL. Later code assumes that the subtree isn't empty. This is broken because the subtree may become empty inbetween, which can lead to the traversal escaping the subtree by walking to the sibling of the subtree root. There's no reason to have the early exit path. Remove it along with the later assumption that the subtree isn't empty. This simplifies the code a bit and fixes the subtle bug. While at it, fix the comment of cgroup_for_each_descendant_pre() which was incorrectly referring to ->css_offline() instead of ->css_online(). Signed-off-by: Tejun Heo Reviewed-by: Michal Hocko Cc: stable@vger.kernel.org --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5047355b9a0f..8bda1294c035 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -707,7 +707,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * * If a subsystem synchronizes against the parent in its ->css_online() and * before starting iterating, and synchronizes against @pos on each - * iteration, any descendant cgroup which finished ->css_offline() is + * iteration, any descendant cgroup which finished ->css_online() is * guaranteed to be visible in the future iterations. * * In other words, the following guarantees that a descendant can't escape -- cgit v1.2.3 From a11650e11093ed57dca78bf16e7836517c599098 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Fri, 24 May 2013 15:55:05 -0700 Subject: rapidio: make enumeration/discovery configurable Systems that use RapidIO fabric may need to implement their own enumeration and discovery methods which are better suitable for needs of a target application. The following set of patches is intended to simplify process of introduction of new RapidIO fabric enumeration/discovery methods. The first patch offers ability to add new RapidIO enumeration/discovery methods using kernel configuration options. This new configuration option mechanism allows to select statically linked or modular enumeration/discovery method(s) from the list of existing methods or use external module(s). This patch also updates the currently existing enumeration/discovery code to be used as a statically linked or modular method. The corresponding configuration option is named "Basic enumeration/discovery" method. This is the only one configuration option available today but new methods are expected to be introduced after adoption of provided patches. The second patch address a long time complaint of RapidIO subsystem users regarding fabric enumeration/discovery start sequence. Existing implementation offers only a boot-time enumeration/discovery start which requires synchronized boot of all endpoints in RapidIO network. While it works for small closed configurations with limited number of endpoints, using this approach in systems with large number of endpoints is quite challenging. To eliminate requirement for synchronized start the second patch introduces RapidIO enumeration/discovery start from user space. For compatibility with the existing RapidIO subsystem implementation, automatic boot time enumeration/discovery start can be configured in by specifying "rio-scan.scan=1" command line parameter if statically linked basic enumeration method is selected. This patch: Rework to implement RapidIO enumeration/discovery method selection combined with ability to use enumeration/discovery as a kernel module. This patch adds ability to introduce new RapidIO enumeration/discovery methods using kernel configuration options. Configuration option mechanism allows to select statically linked or modular enumeration/discovery method from the list of existing methods or use external modules. If a modular enumeration/discovery is selected each RapidIO mport device can have its own method attached to it. The existing enumeration/discovery code was updated to be used as statically linked or modular method. This configuration option is named "Basic enumeration/discovery" method. Several common routines have been moved from rio-scan.c to make them available to other enumeration methods and reduce number of exported symbols. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Andre van Herk Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 13 ++++++++++++- include/linux/rio_drv.h | 1 + 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index a3e784278667..cd3796ee7410 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -83,7 +83,6 @@ extern struct bus_type rio_bus_type; extern struct device rio_bus; -extern struct list_head rio_devices; /* list of all devices */ struct rio_mport; struct rio_dev; @@ -237,6 +236,7 @@ enum rio_phy_type { * @name: Port name string * @priv: Master port private data * @dma: DMA device associated with mport + * @nscan: RapidIO network enumeration/discovery operations */ struct rio_mport { struct list_head dbells; /* list of doorbell events */ @@ -262,6 +262,7 @@ struct rio_mport { #ifdef CONFIG_RAPIDIO_DMA_ENGINE struct dma_device dma; #endif + struct rio_scan *nscan; }; struct rio_id_table { @@ -460,6 +461,16 @@ static inline struct rio_mport *dma_to_mport(struct dma_device *ddev) } #endif /* CONFIG_RAPIDIO_DMA_ENGINE */ +/** + * struct rio_scan - RIO enumeration and discovery operations + * @enumerate: Callback to perform RapidIO fabric enumeration. + * @discover: Callback to perform RapidIO fabric discovery. + */ +struct rio_scan { + int (*enumerate)(struct rio_mport *mport); + int (*discover)(struct rio_mport *mport); +}; + /* Architecture and hardware-specific functions */ extern int rio_register_mport(struct rio_mport *); extern int rio_open_inb_mbox(struct rio_mport *, void *, int, int); diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index b75c05920ab5..5059994fe297 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -433,5 +433,6 @@ extern u16 rio_local_get_device_id(struct rio_mport *port); extern struct rio_dev *rio_get_device(u16 vid, u16 did, struct rio_dev *from); extern struct rio_dev *rio_get_asm(u16 vid, u16 did, u16 asm_vid, u16 asm_did, struct rio_dev *from); +extern int rio_init_mports(void); #endif /* LINUX_RIO_DRV_H */ -- cgit v1.2.3 From bc8fcfea18249640f2728c46d70999dcb7e4dc49 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Fri, 24 May 2013 15:55:06 -0700 Subject: rapidio: add enumeration/discovery start from user space Add RapidIO enumeration/discovery start from user space. User space start allows to defer RapidIO fabric scan until the moment when all participating endpoints are initialized avoiding mandatory synchronized start of all endpoints (which may be challenging in systems with large number of RapidIO endpoints). Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Andre van Herk Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio.h b/include/linux/rio.h index cd3796ee7410..18e099342e6f 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -265,6 +265,11 @@ struct rio_mport { struct rio_scan *nscan; }; +/* + * Enumeration/discovery control flags + */ +#define RIO_SCAN_ENUM_NO_WAIT 0x00000001 /* Do not wait for enum completed */ + struct rio_id_table { u16 start; /* logical minimal id */ u32 max; /* max number of IDs in table */ @@ -467,8 +472,8 @@ static inline struct rio_mport *dma_to_mport(struct dma_device *ddev) * @discover: Callback to perform RapidIO fabric discovery. */ struct rio_scan { - int (*enumerate)(struct rio_mport *mport); - int (*discover)(struct rio_mport *mport); + int (*enumerate)(struct rio_mport *mport, u32 flags); + int (*discover)(struct rio_mport *mport, u32 flags); }; /* Architecture and hardware-specific functions */ -- cgit v1.2.3 From 4c663cfc523a88d97a8309b04a089c27dc57fd7e Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 24 May 2013 15:55:09 -0700 Subject: wait: fix false timeouts when using wait_event_timeout() Many callers of the wait_event_timeout() and wait_event_interruptible_timeout() expect that the return value will be positive if the specified condition becomes true before the timeout elapses. However, at the moment this isn't guaranteed. If the wake-up handler is delayed enough, the time remaining until timeout will be calculated as 0 - and passed back as a return value - even if the condition became true before the timeout has passed. Fix this by returning at least 1 if the condition becomes true. This semantic is in line with what wait_for_condition_timeout() does; see commit bb10ed09 ("sched: fix wait_for_completion_timeout() spurious failure under heavy load"). Daniel said "We have 3 instances of this bug in drm/i915. One case even where we switch between the interruptible and not interruptible wait_event_timeout variants, foolishly presuming they have the same semantics. I very much like this." One such bug is reported at https://bugs.freedesktop.org/show_bug.cgi?id=64133 Signed-off-by: Imre Deak Acked-by: Daniel Vetter Acked-by: David Howells Acked-by: Jens Axboe Cc: "Paul E. McKenney" Cc: Dave Jones Cc: Lukas Czerner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index ac38be2692d8..1133695eb067 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -217,6 +217,8 @@ do { \ if (!ret) \ break; \ } \ + if (!ret && (condition)) \ + ret = 1; \ finish_wait(&wq, &__wait); \ } while (0) @@ -233,8 +235,9 @@ do { \ * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * - * The function returns 0 if the @timeout elapsed, and the remaining - * jiffies if the condition evaluated to true before the timeout elapsed. + * The function returns 0 if the @timeout elapsed, or the remaining + * jiffies (at least 1) if the @condition evaluated to %true before + * the @timeout elapsed. */ #define wait_event_timeout(wq, condition, timeout) \ ({ \ @@ -302,6 +305,8 @@ do { \ ret = -ERESTARTSYS; \ break; \ } \ + if (!ret && (condition)) \ + ret = 1; \ finish_wait(&wq, &__wait); \ } while (0) @@ -318,9 +323,10 @@ do { \ * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * - * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it - * was interrupted by a signal, and the remaining jiffies otherwise - * if the condition evaluated to true before the timeout elapsed. + * Returns: + * 0 if the @timeout elapsed, -%ERESTARTSYS if it was interrupted by + * a signal, or the remaining jiffies (at least 1) if the @condition + * evaluated to %true before the @timeout elapsed. */ #define wait_event_interruptible_timeout(wq, condition, timeout) \ ({ \ -- cgit v1.2.3 From 7450231fb35492951e78a91b833fd935171f4e66 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 24 May 2013 15:55:20 -0700 Subject: linux/kernel.h: fix kernel-doc warning Fix kernel-doc warning in : Warning(include/linux/kernel.h:590): No description found for parameter 'ip' scripts/kernel-doc cannot handle macros, functions, or function prototypes between the function or macro that is being documented and its definition, so move these prototypes above the function that is being documented. Signed-off-by: Randy Dunlap Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e96329ceb28c..e9ef6d6b51d5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -562,6 +562,9 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) int __trace_printk(unsigned long ip, const char *fmt, ...); +extern int __trace_bputs(unsigned long ip, const char *str); +extern int __trace_puts(unsigned long ip, const char *str, int size); + /** * trace_puts - write a string into the ftrace buffer * @str: the string to record @@ -587,8 +590,6 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) */ -extern int __trace_bputs(unsigned long ip, const char *str); -extern int __trace_puts(unsigned long ip, const char *str, int size); #define trace_puts(str) ({ \ static const char *trace_printk_fmt \ __attribute__((section("__trace_printk_fmt"))) = \ -- cgit v1.2.3 From 37448adfc7ce0d6d5892b87aa8d57edde4126f49 Mon Sep 17 00:00:00 2001 From: Lance Ortiz Date: Thu, 30 May 2013 08:25:12 -0600 Subject: aerdrv: Move cper_print_aer() call out of interrupt context The following warning was seen on 3.9 when a corrected PCIe error was being handled by the AER subsystem. WARNING: at .../drivers/pci/search.c:214 pci_get_dev_by_id+0x8a/0x90() This occurred because a call to pci_get_domain_bus_and_slot() was added to cper_print_pcie() to setup for the call to cper_print_aer(). The warning showed up because cper_print_pcie() is called in an interrupt context and pci_get* functions are not supposed to be called in that context. The solution is to move the cper_print_aer() call out of the interrupt context and into aer_recover_work_func() to avoid any warnings when calling pci_get* functions. Signed-off-by: Lance Ortiz Acked-by: Borislav Petkov Acked-by: Rafael J. Wysocki Signed-off-by: Tony Luck --- include/linux/aer.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aer.h b/include/linux/aer.h index ec10e1b24c1c..737f90ab4b62 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -49,10 +49,11 @@ static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) } #endif -extern void cper_print_aer(const char *prefix, struct pci_dev *dev, +extern void cper_print_aer(struct pci_dev *dev, int cper_severity, struct aer_capability_regs *aer); extern int cper_severity_to_aer(int cper_severity); extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, - int severity); + int severity, + struct aer_capability_regs *aer_regs); #endif //_AER_H_ -- cgit v1.2.3 From 1e2bd517c108816220f262d7954b697af03b5f9c Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 30 May 2013 06:45:27 +0000 Subject: udp6: Fix udp fragmentation for tunnel traffic. udp6 over GRE tunnel does not work after to GRE tso changes. GRE tso handler passes inner packet but keeps track of outer header start in SKB_GSO_CB(skb)->mac_offset. udp6 fragment need to take care of outer header, which start at the mac_offset, while adding fragment header. This bug is introduced by commit 68c3316311 (GRE: Add TCP segmentation offload for GRE). Reported-by: Dmitry Kravkov Signed-off-by: Pravin B Shelar Tested-by: Dmitry Kravkov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2e0ced1af3b1..9c676eae3968 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2852,6 +2852,21 @@ static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) SKB_GSO_CB(inner_skb)->mac_offset; } +static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) +{ + int new_headroom, headroom; + int ret; + + headroom = skb_headroom(skb); + ret = pskb_expand_head(skb, extra, 0, GFP_ATOMIC); + if (ret) + return ret; + + new_headroom = skb_headroom(skb); + SKB_GSO_CB(skb)->mac_offset += (new_headroom - headroom); + return 0; +} + static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; -- cgit v1.2.3 From 6d7581e62f8be462440d7b22c6361f7c9fa4902b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 29 May 2013 05:02:56 +0000 Subject: list: introduce list_first_entry_or_null non-rcu variant of list_first_or_null_rcu Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/list.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 6a1f8df9144b..b83e5657365a 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -361,6 +361,17 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) +/** + * list_first_entry_or_null - get the first element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_struct within the struct. + * + * Note that if the list is empty, it returns NULL. + */ +#define list_first_entry_or_null(ptr, type, member) \ + (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL) + /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. -- cgit v1.2.3 From c87a124a5d5e8cf8e21c4363c3372bcaf53ea190 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 May 2013 09:06:27 +0000 Subject: net: force a reload of first item in hlist_nulls_for_each_entry_rcu Roman Gushchin discovered that udp4_lib_lookup2() was not reloading first item in the rcu protected list, in case the loop was restarted. This produced soft lockups as in https://lkml.org/lkml/2013/4/16/37 rcu_dereference(X)/ACCESS_ONCE(X) seem to not work as intended if X is ptr->field : In some cases, gcc caches the value or ptr->field in a register. Use a barrier() to disallow such caching, as documented in Documentation/atomic_ops.txt line 114 Thanks a lot to Roman for providing analysis and numerous patches. Diagnosed-by: Roman Gushchin Signed-off-by: Eric Dumazet Reported-by: Boris Zhmurov Signed-off-by: Roman Gushchin Acked-by: Paul E. McKenney Signed-off-by: David S. Miller --- include/linux/rculist_nulls.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 2ae13714828b..1c33dd7da4a7 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -105,9 +105,14 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, * @head: the head for your list. * @member: the name of the hlist_nulls_node within the struct. * + * The barrier() is needed to make sure compiler doesn't cache first element [1], + * as this loop can be restarted [2] + * [1] Documentation/atomic_ops.txt around line 114 + * [2] Documentation/RCU/rculist_nulls.txt around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ + for (({barrier();}), \ + pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) -- cgit v1.2.3