From df3ed932394488e57e72dd0e73c224d1804fdc8f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 11 May 2017 10:15:10 -0500 Subject: Partially Revert "of: fix sparse warnings in fdt, irq, reserved mem, and resolver code" A change to function pointers that was meant to address a sparse warning turned out to cause hundreds of new gcc-7 warnings: include/linux/of_irq.h:11:13: error: type qualifiers ignored on function return type [-Werror=ignored-qualifiers] drivers/of/of_reserved_mem.c: In function '__reserved_mem_init_node': drivers/of/of_reserved_mem.c:200:7: error: type qualifiers ignored on function return type [-Werror=ignored-qualifiers] int const (*initfn)(struct reserved_mem *rmem) = i->data; Turns out the sparse warnings were spurious and have been fixed in upstream sparse since 0.5.0 in commit "sparse: treat function pointers as pointers to const data". This partially reverts commit 17a70355ea576843a7ac851f1db26872a50b2850. Fixes: 17a70355ea57 ("of: fix sparse warnings in fdt, irq, reserved mem, and resolver code") Reported-by: Arnd Bergmann Signed-off-by: Rob Herring --- include/linux/of_irq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index ec6b11deb773..1e0deb8e8494 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -8,7 +8,7 @@ #include #include -typedef int const (*of_irq_init_cb_t)(struct device_node *, struct device_node *); +typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *); /* * Workarounds only applied to 32bit powermac machines -- cgit v1.2.3 From d1174416747d790d750742d0514915deeed93acf Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 10 May 2017 11:22:52 -0700 Subject: bpf: Track alignment of register values in the verifier. Currently if we add only constant values to pointers we can fully validate the alignment, and properly check if we need to reject the program on !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS architectures. However, once an unknown value is introduced we only allow byte sized memory accesses which is too restrictive. Add logic to track the known minimum alignment of register values, and propagate this state into registers containing pointers. The most common paradigm that makes use of this new logic is computing the transport header using the IP header length field. For example: struct ethhdr *ep = skb->data; struct iphdr *iph = (struct iphdr *) (ep + 1); struct tcphdr *th; ... n = iph->ihl; th = ((void *)iph + (n * 4)); port = th->dest; The existing code will reject the load of th->dest because it cannot validate that the alignment is at least 2 once "n * 4" is added the the packet pointer. In the new code, the register holding "n * 4" will have a reg->min_align value of 4, because any value multiplied by 4 will be at least 4 byte aligned. (actually, the eBPF code emitted by the compiler in this case is most likely to use a shift left by 2, but the end result is identical) At the critical addition: th = ((void *)iph + (n * 4)); The register holding 'th' will start with reg->off value of 14. The pointer addition will transform that reg into something that looks like: reg->aux_off = 14 reg->aux_off_align = 4 Next, the verifier will look at the th->dest load, and it will see a load offset of 2, and first check: if (reg->aux_off_align % size) which will pass because aux_off_align is 4. reg_off will be computed: reg_off = reg->off; ... reg_off += reg->aux_off; plus we have off==2, and it will thus check: if ((NET_IP_ALIGN + reg_off + off) % size != 0) which evaluates to: if ((NET_IP_ALIGN + 14 + 2) % size != 0) On strict alignment architectures, NET_IP_ALIGN is 2, thus: if ((2 + 14 + 2) % size != 0) which passes. These pointer transformations and checks work regardless of whether the constant offset or the variable with known alignment is added first to the pointer register. Signed-off-by: David S. Miller Acked-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5efb4db44e1e..7c6a51924afc 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -40,6 +40,9 @@ struct bpf_reg_state { */ s64 min_value; u64 max_value; + u32 min_align; + u32 aux_off; + u32 aux_off_align; }; enum bpf_stack_slot_type { -- cgit v1.2.3 From e07b98d9bffe410019dfcf62c3428d4a96c56a2c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 10 May 2017 11:38:07 -0700 Subject: bpf: Add strict alignment flag for BPF_PROG_LOAD. Add a new field, "prog_flags", and an initial flag value BPF_F_STRICT_ALIGNMENT. When set, the verifier will enforce strict pointer alignment regardless of the setting of CONFIG_EFFICIENT_UNALIGNED_ACCESS. The verifier, in this mode, will also use a fixed value of "2" in place of NET_IP_ALIGN. This facilitates test cases that will exercise and validate this part of the verifier even when run on architectures where alignment doesn't matter. Signed-off-by: David S. Miller Acked-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7c6a51924afc..d5093b52b485 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -90,6 +90,7 @@ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ + bool strict_alignment; /* perform strict pointer alignment checks */ struct bpf_verifier_state cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ -- cgit v1.2.3 From d67b9cd28c1d7f82c2e5e727731ea7c89b23a0a8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 12 May 2017 01:04:46 +0200 Subject: xdp: refine xdp api with regards to generic xdp While working on the iproute2 generic XDP frontend, I noticed that as of right now it's possible to have native *and* generic XDP programs loaded both at the same time for the case when a driver supports native XDP. The intended model for generic XDP from b5cdae3291f7 ("net: Generic XDP") is, however, that only one out of the two can be present at once which is also indicated as such in the XDP netlink dump part. The main rationale for generic XDP is to ease accessibility (in case a driver does not yet have XDP support) and to generically provide a semantical model as an example for driver developers wanting to add XDP support. The generic XDP option for an XDP aware driver can still be useful for comparing and testing both implementations. However, it is not intended to have a second XDP processing stage or layer with exactly the same functionality of the first native stage. Only reason could be to have a partial fallback for future XDP features that are not supported yet in the native implementation and we probably also shouldn't strive for such fallback and instead encourage native feature support in the first place. Given there's currently no such fallback issue or use case, lets not go there yet if we don't need to. Therefore, change semantics for loading XDP and bail out if the user tries to load a generic XDP program when a native one is present and vice versa. Another alternative to bailing out would be to handle the transition from one flavor to another gracefully, but that would require to bring the device down, exchange both types of programs, and bring it up again in order to avoid a tiny window where a packet could hit both hooks. Given this complicates the logic for just a debugging feature in the native case, I went with the simpler variant. For the dump, remove IFLA_XDP_FLAGS that was added with b5cdae3291f7 and reuse IFLA_XDP_ATTACHED for indicating the mode. Dumping all or just a subset of flags that were used for loading the XDP prog is suboptimal in the long run since not all flags are useful for dumping and if we start to reuse the same flag definitions for load and dump, then we'll waste bit space. What we really just want is to dump the mode for now. Current IFLA_XDP_ATTACHED semantics are: nothing was installed (0), a program is running at the native driver layer (1). Thus, add a mode that says that a program is running at generic XDP layer (2). Applications will handle this fine in that older binaries will just indicate that something is attached at XDP layer, effectively this is similar to IFLA_XDP_FLAGS attr that we would have had modulo the redundancy. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9c23bd2efb56..3f39d27decf4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3296,11 +3296,15 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); + +typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, u32 flags); +bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, -- cgit v1.2.3 From f5705aa8cfed142d980ecac12bee0d81b756479e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 13 May 2017 16:31:05 -0700 Subject: dax, xfs, ext4: compile out iomap-dax paths in the FS_DAX=n case Tetsuo reports: fs/built-in.o: In function `xfs_file_iomap_end': xfs_iomap.c:(.text+0xe0ef9): undefined reference to `put_dax' fs/built-in.o: In function `xfs_file_iomap_begin': xfs_iomap.c:(.text+0xe1a7f): undefined reference to `dax_get_by_host' make: *** [vmlinux] Error 1 $ grep DAX .config CONFIG_DAX=m # CONFIG_DEV_DAX is not set # CONFIG_FS_DAX is not set When FS_DAX=n we can/must throw away the dax code in filesystems. Implement 'fs_' versions of dax_get_by_host() and put_dax() that are nops in the FS_DAX=n case. Cc: Cc: Cc: Jan Kara Cc: "Theodore Ts'o" Cc: "Darrick J. Wong" Cc: Ross Zwisler Tested-by: Tony Luck Fixes: ef51042472f5 ("block, dax: move 'select DAX' from BLOCK to FS_DAX") Reported-by: Tetsuo Handa Signed-off-by: Dan Williams --- include/linux/dax.h | 34 +++++++++++++++++++++++++++------- 1 file changed, 27 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 00ebac854bb7..5ec1f6c47716 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -18,6 +18,20 @@ struct dax_operations { void **, pfn_t *); }; +#if IS_ENABLED(CONFIG_DAX) +struct dax_device *dax_get_by_host(const char *host); +void put_dax(struct dax_device *dax_dev); +#else +static inline struct dax_device *dax_get_by_host(const char *host) +{ + return NULL; +} + +static inline void put_dax(struct dax_device *dax_dev) +{ +} +#endif + int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) int __bdev_dax_supported(struct super_block *sb, int blocksize); @@ -25,23 +39,29 @@ static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { return __bdev_dax_supported(sb, blocksize); } + +static inline struct dax_device *fs_dax_get_by_host(const char *host) +{ + return dax_get_by_host(host); +} + +static inline void fs_put_dax(struct dax_device *dax_dev) +{ + put_dax(dax_dev); +} + #else static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { return -EOPNOTSUPP; } -#endif -#if IS_ENABLED(CONFIG_DAX) -struct dax_device *dax_get_by_host(const char *host); -void put_dax(struct dax_device *dax_dev); -#else -static inline struct dax_device *dax_get_by_host(const char *host) +static inline struct dax_device *fs_dax_get_by_host(const char *host) { return NULL; } -static inline void put_dax(struct dax_device *dax_dev) +static inline void fs_put_dax(struct dax_device *dax_dev) { } #endif -- cgit v1.2.3 From 508541146af18e43072e41a31aa62fac2b01aac1 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 25 Apr 2017 10:39:57 +0300 Subject: net/mlx5: Use underlay QPN from the root name space Root flow table is dynamically changed by the underlying flow steering layer, and IPoIB/ULPs have no idea what will be the root flow table in the future, hence we need a dynamic infrastructure to move Underlay QPs with the root flow table. Fixes: b3ba51498bdd ("net/mlx5: Refactor create flow table method to accept underlay QP") Signed-off-by: Erez Shitrit Signed-off-by: Maor Gottlieb Signed-off-by: Yishai Hadas Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1b166d2e19c5..b25e7baa273e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -109,7 +109,6 @@ struct mlx5_flow_table_attr { int max_fte; u32 level; u32 flags; - u32 underlay_qpn; }; struct mlx5_flow_table * @@ -167,4 +166,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); +int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); +int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); + #endif -- cgit v1.2.3 From 30e7d894c1478c88d50ce94ddcdbd7f9763d9cdd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 17 May 2017 10:19:49 +0200 Subject: tracing/kprobes: Enforce kprobes teardown after testing Enabling the tracer selftest triggers occasionally the warning in text_poke(), which warns when the to be modified page is not marked reserved. The reason is that the tracer selftest installs kprobes on functions marked __init for testing. These probes are removed after the tests, but that removal schedules the delayed kprobes_optimizer work, which will do the actual text poke. If the work is executed after the init text is freed, then the warning triggers. The bug can be reproduced reliably when the work delay is increased. Flush the optimizer work and wait for the optimizing/unoptimizing lists to become empty before returning from the kprobes tracer selftest. That ensures that all operations which were queued due to the probes removal have completed. Link: http://lkml.kernel.org/r/20170516094802.76a468bb@gandalf.local.home Signed-off-by: Thomas Gleixner Acked-by: Masami Hiramatsu Cc: stable@vger.kernel.org Fixes: 6274de498 ("kprobes: Support delayed unoptimizing") Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 30f90c1a0aaf..541df0b5b815 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -349,6 +349,9 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif +extern void wait_for_kprobe_optimizer(void); +#else +static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, -- cgit v1.2.3 From 6a29beef9d1b16c762e469d77e28c3de3f5c3dbb Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 17 May 2017 18:32:02 +0300 Subject: usb: host: xhci-ring: don't need to clear interrupt pending for MSI enabled hcd According to xHCI spec Figure 30: Interrupt Throttle Flow Diagram If PCI Message Signaled Interrupts (MSI or MSI-X) are enabled, then the assertion of the Interrupt Pending (IP) flag in Figure 30 generates a PCI Dword write. The IP flag is automatically cleared by the completion of the PCI write. the MSI enabled HCs don't need to clear interrupt pending bit, but hcd->irq = 0 doesn't equal to MSI enabled HCD. At some Dual-role controller software designs, it sets hcd->irq as 0 to avoid HCD requesting interrupt, and they want to decide when to call usb_hcd_irq by software. Signed-off-by: Peter Chen Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index a469999a106d..50398b69ca44 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -148,6 +148,7 @@ struct usb_hcd { unsigned rh_registered:1;/* is root hub registered? */ unsigned rh_pollable:1; /* may we poll the root hub? */ unsigned msix_enabled:1; /* driver has MSI-X enabled? */ + unsigned msi_enabled:1; /* driver has MSI enabled? */ unsigned remove_phy:1; /* auto-remove USB phy */ /* The next flag is a stopgap, to be removed when all the HCDs -- cgit v1.2.3 From 4123109050a869a8871e58a50f28f383d41e49ad Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 5 May 2017 16:13:02 -0700 Subject: nvme-fc: correct port role bits FC Port roles is a bit mask, not individual values. Correct nvme definitions to unique bits. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc-driver.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 0db37158a61d..12e344b5b77f 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -27,8 +27,8 @@ /* FC Port role bitmask - can merge with FC Port Roles in fc transport */ #define FC_PORT_ROLE_NVME_INITIATOR 0x10 -#define FC_PORT_ROLE_NVME_TARGET 0x11 -#define FC_PORT_ROLE_NVME_DISCOVERY 0x12 +#define FC_PORT_ROLE_NVME_TARGET 0x20 +#define FC_PORT_ROLE_NVME_DISCOVERY 0x40 /** -- cgit v1.2.3 From 4b8ba5fa525bc8bdaaed2a5c5433f0f2008d7bc5 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 25 Apr 2017 16:23:09 -0700 Subject: nvmet-fc: remove target cpu scheduling flag Remove NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED. It's unnecessary. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc-driver.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 12e344b5b77f..6c8c5d8041b7 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -642,15 +642,7 @@ enum { * sequence in one LLDD operation. Errors during Data * sequence transmit must not allow RSP sequence to be sent. */ - NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED = (1 << 1), - /* Bit 1: When 0, the LLDD will deliver FCP CMD - * on the CPU it should be affinitized to. Thus work will - * be scheduled on the cpu received on. When 1, the LLDD - * may not deliver the CMD on the CPU it should be worked - * on. The transport should pick a cpu to schedule the work - * on. - */ - NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 2), + NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 1), /* Bit 2: When 0, the LLDD is calling the cmd rcv handler * in a non-isr context, allowing the transport to finish * op completion in the calling context. When 1, the LLDD @@ -658,7 +650,7 @@ enum { * requiring the transport to transition to a workqueue * for op completion. */ - NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 3), + NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 2), /* Bit 3: When 0, the LLDD is calling the op done handler * in a non-isr context, allowing the transport to finish * op completion in the calling context. When 1, the LLDD -- cgit v1.2.3