From aba428a0c612bb259891307da12e22efd0fab14c Mon Sep 17 00:00:00 2001 From: Chunguang Xu Date: Tue, 1 Dec 2020 17:52:31 +0800 Subject: timekeeping: Remove unused get_seconds() The get_seconds() cleanup seems to have been completed, now it is time to delete the legacy interface to avoid misuse later. Signed-off-by: Chunguang Xu Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/1606816351-26900-1-git-send-email-brookxu@tencent.com --- include/linux/ktime.h | 1 - include/linux/timekeeping32.h | 14 -------------- 2 files changed, 15 deletions(-) delete mode 100644 include/linux/timekeeping32.h (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index a12b5523cc18..73f20deb497d 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -230,6 +230,5 @@ static inline ktime_t ms_to_ktime(u64 ms) } # include -# include #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h deleted file mode 100644 index 266017fc9ee9..000000000000 --- a/include/linux/timekeeping32.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef _LINUX_TIMEKEEPING32_H -#define _LINUX_TIMEKEEPING32_H -/* - * These interfaces are all based on the old timespec type - * and should get replaced with the timespec64 based versions - * over time so we can remove the file here. - */ - -static inline unsigned long get_seconds(void) -{ - return ktime_get_real_seconds(); -} - -#endif -- cgit v1.2.3-71-gd317 From 5e6dca82bcaa49348f9e5fcb48df4881f6d6c4ae Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 12 Jan 2021 11:46:24 -0800 Subject: x86/entry: Emit a symbol for register restoring thunk Arnd found a randconfig that produces the warning: arch/x86/entry/thunk_64.o: warning: objtool: missing symbol for insn at offset 0x3e when building with LLVM_IAS=1 (Clang's integrated assembler). Josh notes: With the LLVM assembler not generating section symbols, objtool has no way to reference this code when it generates ORC unwinder entries, because this code is outside of any ELF function. The limitation now being imposed by objtool is that all code must be contained in an ELF symbol. And .L symbols don't create such symbols. So basically, you can use an .L symbol *inside* a function or a code segment, you just can't use the .L symbol to contain the code using a SYM_*_START/END annotation pair. Fangrui notes that this optimization is helpful for reducing image size when compiling with -ffunction-sections and -fdata-sections. I have observed on the order of tens of thousands of symbols for the kernel images built with those flags. A patch has been authored against GNU binutils to match this behavior of not generating unused section symbols ([1]), so this will also become a problem for users of GNU binutils once they upgrade to 2.36. Omit the .L prefix on a label so that the assembler will emit an entry into the symbol table for the label, with STB_LOCAL binding. This enables objtool to generate proper unwind info here with LLVM_IAS=1 or GNU binutils 2.36+. [ bp: Massage commit message. ] Reported-by: Arnd Bergmann Suggested-by: Josh Poimboeuf Suggested-by: Borislav Petkov Suggested-by: Mark Brown Signed-off-by: Nick Desaulniers Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20210112194625.4181814-1-ndesaulniers@google.com Link: https://github.com/ClangBuiltLinux/linux/issues/1209 Link: https://reviews.llvm.org/D93783 Link: https://sourceware.org/binutils/docs/as/Symbol-Names.html Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=d1bcae833b32f1408485ce69f844dcd7ded093a8 [1] --- Documentation/asm-annotations.rst | 5 +++++ arch/x86/entry/thunk_64.S | 8 ++++---- include/linux/linkage.h | 5 +++++ 3 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/asm-annotations.rst b/Documentation/asm-annotations.rst index 32ea57483378..76424e0431f4 100644 --- a/Documentation/asm-annotations.rst +++ b/Documentation/asm-annotations.rst @@ -100,6 +100,11 @@ Instruction Macros ~~~~~~~~~~~~~~~~~~ This section covers ``SYM_FUNC_*`` and ``SYM_CODE_*`` enumerated above. +``objtool`` requires that all code must be contained in an ELF symbol. Symbol +names that have a ``.L`` prefix do not emit symbol table entries. ``.L`` +prefixed symbols can be used within a code region, but should be avoided for +denoting a range of code via ``SYM_*_START/END`` annotations. + * ``SYM_FUNC_START`` and ``SYM_FUNC_START_LOCAL`` are supposed to be **the most frequent markings**. They are used for functions with standard calling conventions -- global and local. Like in C, they both align the functions to diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index ccd32877a3c4..c9a9fbf1655f 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -31,7 +31,7 @@ SYM_FUNC_START_NOALIGN(\name) .endif call \func - jmp .L_restore + jmp __thunk_restore SYM_FUNC_END(\name) _ASM_NOKPROBE(\name) .endm @@ -44,7 +44,7 @@ SYM_FUNC_END(\name) #endif #ifdef CONFIG_PREEMPTION -SYM_CODE_START_LOCAL_NOALIGN(.L_restore) +SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore) popq %r11 popq %r10 popq %r9 @@ -56,6 +56,6 @@ SYM_CODE_START_LOCAL_NOALIGN(.L_restore) popq %rdi popq %rbp ret - _ASM_NOKPROBE(.L_restore) -SYM_CODE_END(.L_restore) + _ASM_NOKPROBE(__thunk_restore) +SYM_CODE_END(__thunk_restore) #endif diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 5bcfbd972e97..dbf8506decca 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -178,6 +178,11 @@ * Objtool generates debug info for both FUNC & CODE, but needs special * annotations for each CODE's start (to describe the actual stack frame). * + * Objtool requires that all code must be contained in an ELF symbol. Symbol + * names that have a .L prefix do not emit symbol table entries. .L + * prefixed symbols can be used within a code region, but should be avoided for + * denoting a range of code via ``SYM_*_START/END`` annotations. + * * ALIAS -- does not generate debug info -- the aliased function will */ -- cgit v1.2.3-71-gd317 From 20d3bb92e84d417b0494a3b6867f0c86713db257 Mon Sep 17 00:00:00 2001 From: Klaus Jensen Date: Fri, 15 Jan 2021 07:30:46 +0100 Subject: nvme-pci: allow use of cmb on v1.4 controllers Since NVMe v1.4 the Controller Memory Buffer must be explicitly enabled by the host. Signed-off-by: Klaus Jensen [hch: avoid a local variable and add a comment] Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 14 ++++++++++++++ include/linux/nvme.h | 6 ++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 50d9a20568a2..25456d02eddb 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -1795,6 +1796,9 @@ static void nvme_map_cmb(struct nvme_dev *dev) if (dev->cmb_size) return; + if (NVME_CAP_CMBS(dev->ctrl.cap)) + writel(NVME_CMBMSC_CRE, dev->bar + NVME_REG_CMBMSC); + dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!dev->cmbsz) return; @@ -1808,6 +1812,16 @@ static void nvme_map_cmb(struct nvme_dev *dev) if (offset > bar_size) return; + /* + * Tell the controller about the host side address mapping the CMB, + * and enable CMB decoding for the NVMe 1.4+ scheme: + */ + if (NVME_CAP_CMBS(dev->ctrl.cap)) { + hi_lo_writeq(NVME_CMBMSC_CRE | NVME_CMBMSC_CMSE | + (pci_bus_address(pdev, bar) + offset), + dev->bar + NVME_REG_CMBMSC); + } + /* * Controllers may support a CMB size larger than their BAR, * for example, due to being behind a bridge. Reduce the CMB to diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d92535997687..bfed36e342cc 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -116,6 +116,9 @@ enum { NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer * Location */ + NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory + * Space Control + */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -135,6 +138,7 @@ enum { #define NVME_CAP_CSS(cap) (((cap) >> 37) & 0xff) #define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) #define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define NVME_CAP_CMBS(cap) (((cap) >> 57) & 0x1) #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) @@ -192,6 +196,8 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, + NVME_CMBMSC_CRE = 1 << 0, + NVME_CMBMSC_CMSE = 1 << 1, }; struct nvme_id_power_state { -- cgit v1.2.3-71-gd317 From 8eed01b5ca9c1deff329ad44f08e2041ca14842c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 18 Jan 2021 16:06:55 +0100 Subject: mdio-bitbang: Export mdiobb_{read,write}() Export mdiobb_read() and mdiobb_write(), so Ethernet controller drivers can call them from their MDIO read/write wrappers. Signed-off-by: Geert Uytterhoeven Tested-by: Wolfram Sang Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- drivers/net/mdio/mdio-bitbang.c | 6 ++++-- include/linux/mdio-bitbang.h | 3 +++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio/mdio-bitbang.c b/drivers/net/mdio/mdio-bitbang.c index 5136275c8e73..d3915f831854 100644 --- a/drivers/net/mdio/mdio-bitbang.c +++ b/drivers/net/mdio/mdio-bitbang.c @@ -149,7 +149,7 @@ static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr) return dev_addr; } -static int mdiobb_read(struct mii_bus *bus, int phy, int reg) +int mdiobb_read(struct mii_bus *bus, int phy, int reg) { struct mdiobb_ctrl *ctrl = bus->priv; int ret, i; @@ -180,8 +180,9 @@ static int mdiobb_read(struct mii_bus *bus, int phy, int reg) mdiobb_get_bit(ctrl); return ret; } +EXPORT_SYMBOL(mdiobb_read); -static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val) +int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val) { struct mdiobb_ctrl *ctrl = bus->priv; @@ -201,6 +202,7 @@ static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val) mdiobb_get_bit(ctrl); return 0; } +EXPORT_SYMBOL(mdiobb_write); struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl) { diff --git a/include/linux/mdio-bitbang.h b/include/linux/mdio-bitbang.h index 5d71e8a8500f..aca4dc037b70 100644 --- a/include/linux/mdio-bitbang.h +++ b/include/linux/mdio-bitbang.h @@ -35,6 +35,9 @@ struct mdiobb_ctrl { const struct mdiobb_ops *ops; }; +int mdiobb_read(struct mii_bus *bus, int phy, int reg); +int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val); + /* The returned bus is not yet registered with the phy layer. */ struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl); -- cgit v1.2.3-71-gd317 From de641d74fb00f5b32f054ee154e31fb037e0db88 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Sun, 17 Jan 2021 11:26:33 +0200 Subject: Revert "RDMA/mlx5: Fix devlink deadlock on net namespace deletion" This reverts commit fbdd0049d98d44914fc57d4b91f867f4996c787b. Due to commit in fixes tag, netdevice events were received only in one net namespace of mlx5_core_dev. Due to this when netdevice events arrive in net namespace other than net namespace of mlx5_core_dev, they are missed. This results in empty GID table due to RDMA device being detached from its net device. Hence, revert back to receive netdevice events in all net namespaces to restore back RDMA functionality in non init_net net namespace. The deadlock will have to be addressed in another patch. Fixes: fbdd0049d98d ("RDMA/mlx5: Fix devlink deadlock on net namespace deletion") Link: https://lore.kernel.org/r/20210117092633.10690-1-leon@kernel.org Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/main.c | 6 ++---- drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 5 +++++ include/linux/mlx5/driver.h | 18 ------------------ 3 files changed, 7 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index d26f3f3e0462..aabdc07e4753 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3311,8 +3311,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num) int err; dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event; - err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev), - &dev->port[port_num].roce.nb); + err = register_netdevice_notifier(&dev->port[port_num].roce.nb); if (err) { dev->port[port_num].roce.nb.notifier_call = NULL; return err; @@ -3324,8 +3323,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num) static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num) { if (dev->port[port_num].roce.nb.notifier_call) { - unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev), - &dev->port[port_num].roce.nb); + unregister_netdevice_notifier(&dev->port[port_num].roce.nb); dev->port[port_num].roce.nb.notifier_call = NULL; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 3a9fa629503f..d046db7bb047 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -90,4 +90,9 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, u32 key_type, u32 *p_key_id); void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id); +static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) +{ + return devlink_net(priv_to_devlink(dev)); +} + #endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..4672e12f1aa5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1209,22 +1209,4 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) return val.vbool; } -/** - * mlx5_core_net - Provide net namespace of the mlx5_core_dev - * @dev: mlx5 core device - * - * mlx5_core_net() returns the net namespace of mlx5 core device. - * This can be called only in below described limited context. - * (a) When a devlink instance for mlx5_core is registered and - * when devlink reload operation is disabled. - * or - * (b) during devlink reload reload_down() and reload_up callbacks - * where it is ensured that devlink instance's net namespace is - * stable. - */ -static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) -{ - return devlink_net(priv_to_devlink(dev)); -} - #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3-71-gd317 From de658a195ee23ca6aaffe197d1d2ea040beea0a2 Mon Sep 17 00:00:00 2001 From: Grant Grundler Date: Tue, 19 Jan 2021 17:12:08 -0800 Subject: net: usb: cdc_ncm: don't spew notifications RTL8156 sends notifications about every 32ms. Only display/log notifications when something changes. This issue has been reported by others: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1832472 https://lkml.org/lkml/2020/8/27/1083 ... [785962.779840] usb 1-1: new high-speed USB device number 5 using xhci_hcd [785962.929944] usb 1-1: New USB device found, idVendor=0bda, idProduct=8156, bcdDevice=30.00 [785962.929949] usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=6 [785962.929952] usb 1-1: Product: USB 10/100/1G/2.5G LAN [785962.929954] usb 1-1: Manufacturer: Realtek [785962.929956] usb 1-1: SerialNumber: 000000001 [785962.991755] usbcore: registered new interface driver cdc_ether [785963.017068] cdc_ncm 1-1:2.0: MAC-Address: 00:24:27:88:08:15 [785963.017072] cdc_ncm 1-1:2.0: setting rx_max = 16384 [785963.017169] cdc_ncm 1-1:2.0: setting tx_max = 16384 [785963.017682] cdc_ncm 1-1:2.0 usb0: register 'cdc_ncm' at usb-0000:00:14.0-1, CDC NCM, 00:24:27:88:08:15 [785963.019211] usbcore: registered new interface driver cdc_ncm [785963.023856] usbcore: registered new interface driver cdc_wdm [785963.025461] usbcore: registered new interface driver cdc_mbim [785963.038824] cdc_ncm 1-1:2.0 enx002427880815: renamed from usb0 [785963.089586] cdc_ncm 1-1:2.0 enx002427880815: network connection: disconnected [785963.121673] cdc_ncm 1-1:2.0 enx002427880815: network connection: disconnected [785963.153682] cdc_ncm 1-1:2.0 enx002427880815: network connection: disconnected ... This is about 2KB per second and will overwrite all contents of a 1MB dmesg buffer in under 10 minutes rendering them useless for debugging many kernel problems. This is also an extra 180 MB/day in /var/logs (or 1GB per week) rendering the majority of those logs useless too. When the link is up (expected state), spew amount is >2x higher: ... [786139.600992] cdc_ncm 2-1:2.0 enx002427880815: network connection: connected [786139.632997] cdc_ncm 2-1:2.0 enx002427880815: 2500 mbit/s downlink 2500 mbit/s uplink [786139.665097] cdc_ncm 2-1:2.0 enx002427880815: network connection: connected [786139.697100] cdc_ncm 2-1:2.0 enx002427880815: 2500 mbit/s downlink 2500 mbit/s uplink [786139.729094] cdc_ncm 2-1:2.0 enx002427880815: network connection: connected [786139.761108] cdc_ncm 2-1:2.0 enx002427880815: 2500 mbit/s downlink 2500 mbit/s uplink ... Chrome OS cannot support RTL8156 until this is fixed. Signed-off-by: Grant Grundler Reviewed-by: Hayes Wang Link: https://lore.kernel.org/r/20210120011208.3768105-1-grundler@chromium.org Signed-off-by: Jakub Kicinski --- drivers/net/usb/cdc_ncm.c | 12 +++++++++++- include/linux/usb/usbnet.h | 2 ++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 5a78848db93f..291e76d32abe 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1827,6 +1827,15 @@ cdc_ncm_speed_change(struct usbnet *dev, uint32_t rx_speed = le32_to_cpu(data->DLBitRRate); uint32_t tx_speed = le32_to_cpu(data->ULBitRate); + /* if the speed hasn't changed, don't report it. + * RTL8156 shipped before 2021 sends notification about every 32ms. + */ + if (dev->rx_speed == rx_speed && dev->tx_speed == tx_speed) + return; + + dev->rx_speed = rx_speed; + dev->tx_speed = tx_speed; + /* * Currently the USB-NET API does not support reporting the actual * device speed. Do print it instead. @@ -1867,7 +1876,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) * USB_CDC_NOTIFY_NETWORK_CONNECTION notification shall be * sent by device after USB_CDC_NOTIFY_SPEED_CHANGE. */ - usbnet_link_change(dev, !!event->wValue, 0); + if (netif_carrier_ok(dev->net) != !!event->wValue) + usbnet_link_change(dev, !!event->wValue, 0); break; case USB_CDC_NOTIFY_SPEED_CHANGE: diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 88a7673894d5..cfbfd6fe01df 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -81,6 +81,8 @@ struct usbnet { # define EVENT_LINK_CHANGE 11 # define EVENT_SET_RX_MODE 12 # define EVENT_NO_IP_ALIGN 13 + u32 rx_speed; /* in bps - NOT Mbps */ + u32 tx_speed; /* in bps - NOT Mbps */ }; static inline struct usb_driver *driver_of(struct usb_interface *intf) -- cgit v1.2.3-71-gd317 From 51dfb6ca3728bd0a0a3c23776a12d2a15a1d2457 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 20 Jan 2021 23:58:44 +0300 Subject: regulator: consumer: Add missing stubs to regulator/consumer.h Add missing stubs to regulator/consumer.h in order to fix COMPILE_TEST of the kernel. In particular this should fix compile-testing of OPP core because of a missing stub for regulator_sync_voltage(). Reported-by: kernel test robot Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20210120205844.12658-1-digetx@gmail.com Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 2024944fd2f7..20e84a84fb77 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -331,6 +331,12 @@ regulator_get_exclusive(struct device *dev, const char *id) return ERR_PTR(-ENODEV); } +static inline struct regulator *__must_check +devm_regulator_get_exclusive(struct device *dev, const char *id) +{ + return ERR_PTR(-ENODEV); +} + static inline struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id) { @@ -486,6 +492,11 @@ static inline int regulator_get_voltage(struct regulator *regulator) return -EINVAL; } +static inline int regulator_sync_voltage(struct regulator *regulator) +{ + return -EINVAL; +} + static inline int regulator_is_supported_voltage(struct regulator *regulator, int min_uV, int max_uV) { @@ -578,6 +589,25 @@ static inline int devm_regulator_unregister_notifier(struct regulator *regulator return 0; } +static inline int regulator_suspend_enable(struct regulator_dev *rdev, + suspend_state_t state) +{ + return -EINVAL; +} + +static inline int regulator_suspend_disable(struct regulator_dev *rdev, + suspend_state_t state) +{ + return -EINVAL; +} + +static inline int regulator_set_suspend_voltage(struct regulator *regulator, + int min_uV, int max_uV, + suspend_state_t state) +{ + return -EINVAL; +} + static inline void *regulator_get_drvdata(struct regulator *regulator) { return NULL; -- cgit v1.2.3-71-gd317 From e020ff611ba9be54e959e6b548038f8a020da1c9 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Sun, 10 Jan 2021 09:54:07 -0800 Subject: driver core: Fix device link device name collision The device link device's name was of the form: -- This can cause name collision as reported here [1] as device names are not globally unique. Since device names have to be unique within the bus/class, add the bus/class name as a prefix to the device names used to construct the device link device name. So the devuce link device's name will be of the form: :--: [1] - https://lore.kernel.org/lkml/20201229033440.32142-1-michael@walle.cc/ Fixes: 287905e68dd2 ("driver core: Expose device link details in sysfs") Cc: stable@vger.kernel.org Reported-by: Michael Walle Tested-by: Michael Walle Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210110175408.1465657-1-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-class-devlink | 4 ++-- Documentation/ABI/testing/sysfs-devices-consumer | 5 +++-- Documentation/ABI/testing/sysfs-devices-supplier | 5 +++-- drivers/base/core.c | 27 +++++++++++++----------- include/linux/device.h | 12 +++++++++++ 5 files changed, 35 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink index b662f747c83e..8a21ce515f61 100644 --- a/Documentation/ABI/testing/sysfs-class-devlink +++ b/Documentation/ABI/testing/sysfs-class-devlink @@ -5,8 +5,8 @@ Description: Provide a place in sysfs for the device link objects in the kernel at any given time. The name of a device link directory, denoted as ... above, is of the form -- - where is the supplier device name and is - the consumer device name. + where is the supplier bus:device name and + is the consumer bus:device name. What: /sys/class/devlink/.../auto_remove_on Date: May 2020 diff --git a/Documentation/ABI/testing/sysfs-devices-consumer b/Documentation/ABI/testing/sysfs-devices-consumer index 1f06d74d1c3c..0809fda092e6 100644 --- a/Documentation/ABI/testing/sysfs-devices-consumer +++ b/Documentation/ABI/testing/sysfs-devices-consumer @@ -4,5 +4,6 @@ Contact: Saravana Kannan Description: The /sys/devices/.../consumer: are symlinks to device links where this device is the supplier. denotes the - name of the consumer in that device link. There can be zero or - more of these symlinks for a given device. + name of the consumer in that device link and is of the form + bus:device name. There can be zero or more of these symlinks + for a given device. diff --git a/Documentation/ABI/testing/sysfs-devices-supplier b/Documentation/ABI/testing/sysfs-devices-supplier index a919e0db5e90..207f5972e98d 100644 --- a/Documentation/ABI/testing/sysfs-devices-supplier +++ b/Documentation/ABI/testing/sysfs-devices-supplier @@ -4,5 +4,6 @@ Contact: Saravana Kannan Description: The /sys/devices/.../supplier: are symlinks to device links where this device is the consumer. denotes the - name of the supplier in that device link. There can be zero or - more of these symlinks for a given device. + name of the supplier in that device link and is of the form + bus:device name. There can be zero or more of these symlinks + for a given device. diff --git a/drivers/base/core.c b/drivers/base/core.c index 3819fd012e27..78f6db169d47 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -471,7 +471,9 @@ static int devlink_add_symlinks(struct device *dev, struct device *con = link->consumer; char *buf; - len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), + strlen(dev_bus_name(con)) + strlen(dev_name(con))); + len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) @@ -485,12 +487,12 @@ static int devlink_add_symlinks(struct device *dev, if (ret) goto err_con; - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf); if (ret) goto err_con_dev; - snprintf(buf, len, "supplier:%s", dev_name(sup)); + snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf); if (ret) goto err_sup_dev; @@ -498,7 +500,7 @@ static int devlink_add_symlinks(struct device *dev, goto out; err_sup_dev: - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); err_con_dev: sysfs_remove_link(&link->link_dev.kobj, "consumer"); @@ -521,7 +523,9 @@ static void devlink_remove_symlinks(struct device *dev, sysfs_remove_link(&link->link_dev.kobj, "consumer"); sysfs_remove_link(&link->link_dev.kobj, "supplier"); - len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), + strlen(dev_bus_name(con)) + strlen(dev_name(con))); + len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) { @@ -529,9 +533,9 @@ static void devlink_remove_symlinks(struct device *dev, return; } - snprintf(buf, len, "supplier:%s", dev_name(sup)); + snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); sysfs_remove_link(&con->kobj, buf); - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); kfree(buf); } @@ -752,8 +756,9 @@ struct device_link *device_link_add(struct device *consumer, link->link_dev.class = &devlink_class; device_set_pm_not_required(&link->link_dev); - dev_set_name(&link->link_dev, "%s--%s", - dev_name(supplier), dev_name(consumer)); + dev_set_name(&link->link_dev, "%s:%s--%s:%s", + dev_bus_name(supplier), dev_name(supplier), + dev_bus_name(consumer), dev_name(consumer)); if (device_register(&link->link_dev)) { put_device(consumer); put_device(supplier); @@ -1823,9 +1828,7 @@ const char *dev_driver_string(const struct device *dev) * never change once they are set, so they don't need special care. */ drv = READ_ONCE(dev->driver); - return drv ? drv->name : - (dev->bus ? dev->bus->name : - (dev->class ? dev->class->name : "")); + return drv ? drv->name : dev_bus_name(dev); } EXPORT_SYMBOL(dev_driver_string); diff --git a/include/linux/device.h b/include/linux/device.h index 89bb8b84173e..1779f90eeb4c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -609,6 +609,18 @@ static inline const char *dev_name(const struct device *dev) return kobject_name(&dev->kobj); } +/** + * dev_bus_name - Return a device's bus/class name, if at all possible + * @dev: struct device to get the bus/class name of + * + * Will return the name of the bus/class the device is attached to. If it is + * not attached to a bus/class, an empty string will be returned. + */ +static inline const char *dev_bus_name(const struct device *dev) +{ + return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); +} + __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA -- cgit v1.2.3-71-gd317 From ac687e6e8c26181a33270efd1a2e2241377924b0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jan 2021 11:24:04 +0100 Subject: kthread: Extract KTHREAD_IS_PER_CPU There is a need to distinguish geniune per-cpu kthreads from kthreads that happen to have a single CPU affinity. Geniune per-cpu kthreads are kthreads that are CPU affine for correctness, these will obviously have PF_KTHREAD set, but must also have PF_NO_SETAFFINITY set, lest userspace modify their affinity and ruins things. However, these two things are not sufficient, PF_NO_SETAFFINITY is also set on other tasks that have their affinities controlled through other means, like for instance workqueues. Therefore another bit is needed; it turns out kthread_create_per_cpu() already has such a bit: KTHREAD_IS_PER_CPU, which is used to make kthread_park()/kthread_unpark() work correctly. Expose this flag and remove the implicit setting of it from kthread_create_on_cpu(); the io_uring usage of it seems dubious at best. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20210121103506.557620262@infradead.org --- include/linux/kthread.h | 3 +++ kernel/kthread.c | 27 ++++++++++++++++++++++++++- kernel/smpboot.c | 1 + 3 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 65b81e0c494d..2484ed97e72f 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,6 +33,9 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); +void kthread_set_per_cpu(struct task_struct *k, int cpu); +bool kthread_is_per_cpu(struct task_struct *k); + /** * kthread_run - create and wake a thread. * @threadfn: the function to run until signal_pending(current). diff --git a/kernel/kthread.c b/kernel/kthread.c index a5eceecd4513..e0e4a423f184 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -493,11 +493,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; } +void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *k) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2efe1e206167..f25208e8df83 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -188,6 +188,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + kthread_set_per_cpu(tsk, cpu); /* * Park the thread so that it could start right on the CPU * when it is available. -- cgit v1.2.3-71-gd317 From 9f12e37cae44a96132fc3031535a0b165486941a Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 25 Jan 2021 11:09:25 -0800 Subject: Commit 9bb48c82aced ("tty: implement write_iter") converted the tty layer to use write_iter. Fix the redirected_tty_write declaration also in n_tty and change the comparisons to use write_iter instead of write. [ Also moved the declaration of redirected_tty_write() to the proper location in a header file. The reason for the bug was the bogus extern declaration in n_tty.c silently not matching the changed definition in tty_io.c, and because it wasn't in a shared header file, there was no cross-checking of the declaration. Sami noticed because Clang's Control Flow Integrity checking ended up incidentally noticing the inconsistent declaration. - Linus ] Fixes: 9bb48c82aced ("tty: implement write_iter") Signed-off-by: Sami Tolvanen Signed-off-by: Linus Torvalds --- drivers/tty/n_tty.c | 7 ++----- drivers/tty/tty_io.c | 2 -- include/linux/tty.h | 1 + 3 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 319d68c8a5df..219e85756171 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2081,9 +2081,6 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, return 0; } -extern ssize_t redirected_tty_write(struct file *, const char __user *, - size_t, loff_t *); - /** * job_control - check job control * @tty: tty @@ -2105,7 +2102,7 @@ static int job_control(struct tty_struct *tty, struct file *file) /* NOTE: not yet done after every sleep pending a thorough check of the logic of this change. -- jlc */ /* don't stop on /dev/console */ - if (file->f_op->write == redirected_tty_write) + if (file->f_op->write_iter == redirected_tty_write) return 0; return __tty_check_change(tty, SIGTTIN); @@ -2309,7 +2306,7 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file, ssize_t retval = 0; /* Job control check -- must be done at start (POSIX.1 7.1.1.4). */ - if (L_TOSTOP(tty) && file->f_op->write != redirected_tty_write) { + if (L_TOSTOP(tty) && file->f_op->write_iter != redirected_tty_write) { retval = tty_check_change(tty); if (retval) return retval; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 4a208a95e921..48de20916ca7 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -144,10 +144,8 @@ DEFINE_MUTEX(tty_mutex); static ssize_t tty_read(struct file *, char __user *, size_t, loff_t *); static ssize_t tty_write(struct kiocb *, struct iov_iter *); -ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); static __poll_t tty_poll(struct file *, poll_table *); static int tty_open(struct inode *, struct file *); -long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT static long tty_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); diff --git a/include/linux/tty.h b/include/linux/tty.h index c873f475f0a7..37803f3e6d49 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -421,6 +421,7 @@ extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); extern int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); extern void tty_ldisc_unlock(struct tty_struct *tty); +extern ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); #else static inline void tty_kref_put(struct tty_struct *tty) { } -- cgit v1.2.3-71-gd317 From ba6dfce47c4d002d96cd02a304132fca76981172 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 21 Jan 2021 16:17:23 -0500 Subject: SUNRPC: Move simple_get_bytes and simple_get_netobj into private header Remove duplicated helper functions to parse opaque XDR objects and place inside new file net/sunrpc/auth_gss/auth_gss_internal.h. In the new file carry the license and copyright from the source file net/sunrpc/auth_gss/auth_gss.c. Finally, update the comment inside include/linux/sunrpc/xdr.h since lockd is not the only user of struct xdr_netobj. Signed-off-by: Dave Wysochanski Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 3 +-- net/sunrpc/auth_gss/auth_gss.c | 30 +---------------------- net/sunrpc/auth_gss/auth_gss_internal.h | 42 +++++++++++++++++++++++++++++++++ net/sunrpc/auth_gss/gss_krb5_mech.c | 31 ++---------------------- 4 files changed, 46 insertions(+), 60 deletions(-) create mode 100644 net/sunrpc/auth_gss/auth_gss_internal.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 19b6dea27367..b26213ae8c1a 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -25,8 +25,7 @@ struct rpc_rqst; #define XDR_QUADLEN(l) (((l) + 3) >> 2) /* - * Generic opaque `network object.' At the kernel level, this type - * is used only by lockd. + * Generic opaque `network object.' */ #define XDR_MAX_NETOBJ 1024 struct xdr_netobj { diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 4ecc2a959567..5f42aa5fc612 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -29,6 +29,7 @@ #include #include +#include "auth_gss_internal.h" #include "../netns.h" #include @@ -125,35 +126,6 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx) clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags); } -static const void * -simple_get_bytes(const void *p, const void *end, void *res, size_t len) -{ - const void *q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - memcpy(res, p, len); - return q; -} - -static inline const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) -{ - const void *q; - unsigned int len; - - p = simple_get_bytes(p, end, &len, sizeof(len)); - if (IS_ERR(p)) - return p; - q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - dest->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(dest->data == NULL)) - return ERR_PTR(-ENOMEM); - dest->len = len; - return q; -} - static struct gss_cl_ctx * gss_cred_get_ctx(struct rpc_cred *cred) { diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h new file mode 100644 index 000000000000..c5603242b54b --- /dev/null +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * linux/net/sunrpc/auth_gss/auth_gss_internal.h + * + * Internal definitions for RPCSEC_GSS client authentication + * + * Copyright (c) 2000 The Regents of the University of Michigan. + * All rights reserved. + * + */ +#include +#include +#include + +static inline const void * +simple_get_bytes(const void *p, const void *end, void *res, size_t len) +{ + const void *q = (const void *)((const char *)p + len); + if (unlikely(q > end || q < p)) + return ERR_PTR(-EFAULT); + memcpy(res, p, len); + return q; +} + +static inline const void * +simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) +{ + const void *q; + unsigned int len; + + p = simple_get_bytes(p, end, &len, sizeof(len)); + if (IS_ERR(p)) + return p; + q = (const void *)((const char *)p + len); + if (unlikely(q > end || q < p)) + return ERR_PTR(-EFAULT); + dest->data = kmemdup(p, len, GFP_NOFS); + if (unlikely(dest->data == NULL)) + return ERR_PTR(-ENOMEM); + dest->len = len; + return q; +} diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index ae9acf3a7389..1c092b05c2bb 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -21,6 +21,8 @@ #include #include +#include "auth_gss_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -143,35 +145,6 @@ get_gss_krb5_enctype(int etype) return NULL; } -static const void * -simple_get_bytes(const void *p, const void *end, void *res, int len) -{ - const void *q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - memcpy(res, p, len); - return q; -} - -static const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res) -{ - const void *q; - unsigned int len; - - p = simple_get_bytes(p, end, &len, sizeof(len)); - if (IS_ERR(p)) - return p; - q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - res->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(res->data == NULL)) - return ERR_PTR(-ENOMEM); - res->len = len; - return q; -} - static inline const void * get_key(const void *p, const void *end, struct krb5_ctx *ctx, struct crypto_sync_skcipher **res) -- cgit v1.2.3-71-gd317 From 97c753e62e6c31a404183898d950d8c08d752dbd Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 28 Jan 2021 00:37:51 +0900 Subject: tracing/kprobe: Fix to support kretprobe events on unloaded modules Fix kprobe_on_func_entry() returns error code instead of false so that register_kretprobe() can return an appropriate error code. append_trace_kprobe() expects the kprobe registration returns -ENOENT when the target symbol is not found, and it checks whether the target module is unloaded or not. If the target module doesn't exist, it defers to probe the target symbol until the module is loaded. However, since register_kretprobe() returns -EINVAL instead of -ENOENT in that case, it always fail on putting the kretprobe event on unloaded modules. e.g. Kprobe event: /sys/kernel/debug/tracing # echo p xfs:xfs_end_io >> kprobe_events [ 16.515574] trace_kprobe: This probe might be able to register after target module is loaded. Continue. Kretprobe event: (p -> r) /sys/kernel/debug/tracing # echo r xfs:xfs_end_io >> kprobe_events sh: write error: Invalid argument /sys/kernel/debug/tracing # cat error_log [ 41.122514] trace_kprobe: error: Failed to register probe event Command: r xfs:xfs_end_io ^ To fix this bug, change kprobe_on_func_entry() to detect symbol lookup failure and return -ENOENT in that case. Otherwise it returns -EINVAL or 0 (succeeded, given address is on the entry). Link: https://lkml.kernel.org/r/161176187132.1067016.8118042342894378981.stgit@devnote2 Cc: stable@vger.kernel.org Fixes: 59158ec4aef7 ("tracing/kprobes: Check the probe on unloaded module correctly") Reported-by: Jianlin Lv Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 2 +- kernel/kprobes.c | 34 +++++++++++++++++++++++++--------- kernel/trace/trace_kprobe.c | 10 ++++++---- 3 files changed, 32 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index b3a36b0cfc81..1883a4a9f16a 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -266,7 +266,7 @@ extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); extern bool arch_kprobe_on_func_entry(unsigned long offset); -extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); +extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); extern int kprobe_add_ksym_blacklist(unsigned long entry); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index f7fb5d135930..1a5bc321e0a5 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1954,29 +1954,45 @@ bool __weak arch_kprobe_on_func_entry(unsigned long offset) return !offset; } -bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) +/** + * kprobe_on_func_entry() -- check whether given address is function entry + * @addr: Target address + * @sym: Target symbol name + * @offset: The offset from the symbol or the address + * + * This checks whether the given @addr+@offset or @sym+@offset is on the + * function entry address or not. + * This returns 0 if it is the function entry, or -EINVAL if it is not. + * And also it returns -ENOENT if it fails the symbol or address lookup. + * Caller must pass @addr or @sym (either one must be NULL), or this + * returns -EINVAL. + */ +int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) { kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset); if (IS_ERR(kp_addr)) - return false; + return PTR_ERR(kp_addr); - if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) || - !arch_kprobe_on_func_entry(offset)) - return false; + if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset)) + return -ENOENT; - return true; + if (!arch_kprobe_on_func_entry(offset)) + return -EINVAL; + + return 0; } int register_kretprobe(struct kretprobe *rp) { - int ret = 0; + int ret; struct kretprobe_instance *inst; int i; void *addr; - if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset)) - return -EINVAL; + ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset); + if (ret) + return ret; if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index e6fba1798771..56c7fbff7bd7 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -221,9 +221,9 @@ bool trace_kprobe_on_func_entry(struct trace_event_call *call) { struct trace_kprobe *tk = trace_kprobe_primary_from_call(call); - return tk ? kprobe_on_func_entry(tk->rp.kp.addr, + return tk ? (kprobe_on_func_entry(tk->rp.kp.addr, tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name, - tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false; + tk->rp.kp.addr ? 0 : tk->rp.kp.offset) == 0) : false; } bool trace_kprobe_error_injectable(struct trace_event_call *call) @@ -828,9 +828,11 @@ static int trace_kprobe_create(int argc, const char *argv[]) } if (is_return) flags |= TPARG_FL_RETURN; - if (kprobe_on_func_entry(NULL, symbol, offset)) + ret = kprobe_on_func_entry(NULL, symbol, offset); + if (ret == 0) flags |= TPARG_FL_FENTRY; - if (offset && is_return && !(flags & TPARG_FL_FENTRY)) { + /* Defer the ENOENT case until register kprobe */ + if (ret == -EINVAL && is_return) { trace_probe_log_err(0, BAD_RETPROBE); goto parse_error; } -- cgit v1.2.3-71-gd317 From 4c457e8cb75eda91906a4f89fc39bde3f9a43922 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 23 Jan 2021 12:27:59 +0000 Subject: genirq/msi: Activate Multi-MSI early when MSI_FLAG_ACTIVATE_EARLY is set When MSI_FLAG_ACTIVATE_EARLY is set (which is the case for PCI), __msi_domain_alloc_irqs() performs the activation of the interrupt (which in the case of PCI results in the endpoint being programmed) as soon as the interrupt is allocated. But it appears that this is only done for the first vector, introducing an inconsistent behaviour for PCI Multi-MSI. Fix it by iterating over the number of vectors allocated to each MSI descriptor. This is easily achieved by introducing a new "for_each_msi_vector" iterator, together with a tiny bit of refactoring. Fixes: f3b0946d629c ("genirq/msi: Make sure PCI MSIs are activated early") Reported-by: Shameer Kolothum Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Tested-by: Shameer Kolothum Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210123122759.1781359-1-maz@kernel.org --- include/linux/msi.h | 6 ++++++ kernel/irq/msi.c | 44 ++++++++++++++++++++------------------------ 2 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 360a0a7e7341..aef35fd1cf11 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -178,6 +178,12 @@ struct msi_desc { list_for_each_entry((desc), dev_to_msi_list((dev)), list) #define for_each_msi_entry_safe(desc, tmp, dev) \ list_for_each_entry_safe((desc), (tmp), dev_to_msi_list((dev)), list) +#define for_each_msi_vector(desc, __irq, dev) \ + for_each_msi_entry((desc), (dev)) \ + if ((desc)->irq) \ + for (__irq = (desc)->irq; \ + __irq < ((desc)->irq + (desc)->nvec_used); \ + __irq++) #ifdef CONFIG_IRQ_MSI_IOMMU static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index dc0e2d7fbdfd..b338d622f26e 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -436,22 +436,22 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, can_reserve = msi_check_reservation_mode(domain, info, dev); - for_each_msi_entry(desc, dev) { - virq = desc->irq; - if (desc->nvec_used == 1) - dev_dbg(dev, "irq %d for MSI\n", virq); - else + /* + * This flag is set by the PCI layer as we need to activate + * the MSI entries before the PCI layer enables MSI in the + * card. Otherwise the card latches a random msi message. + */ + if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY)) + goto skip_activate; + + for_each_msi_vector(desc, i, dev) { + if (desc->irq == i) { + virq = desc->irq; dev_dbg(dev, "irq [%d-%d] for MSI\n", virq, virq + desc->nvec_used - 1); - /* - * This flag is set by the PCI layer as we need to activate - * the MSI entries before the PCI layer enables MSI in the - * card. Otherwise the card latches a random msi message. - */ - if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY)) - continue; + } - irq_data = irq_domain_get_irq_data(domain, desc->irq); + irq_data = irq_domain_get_irq_data(domain, i); if (!can_reserve) { irqd_clr_can_reserve(irq_data); if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) @@ -462,28 +462,24 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, goto cleanup; } +skip_activate: /* * If these interrupts use reservation mode, clear the activated bit * so request_irq() will assign the final vector. */ if (can_reserve) { - for_each_msi_entry(desc, dev) { - irq_data = irq_domain_get_irq_data(domain, desc->irq); + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); irqd_clr_activated(irq_data); } } return 0; cleanup: - for_each_msi_entry(desc, dev) { - struct irq_data *irqd; - - if (desc->irq == virq) - break; - - irqd = irq_domain_get_irq_data(domain, desc->irq); - if (irqd_is_activated(irqd)) - irq_domain_deactivate_irq(irqd); + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); + if (irqd_is_activated(irq_data)) + irq_domain_deactivate_irq(irq_data); } msi_domain_free_irqs(domain, dev); return ret; -- cgit v1.2.3-71-gd317 From c8b186a8d54d7e12d28e9f9686cb00ff18fc2ab2 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Tue, 2 Feb 2021 18:23:26 +1100 Subject: tracepoint: Fix race between tracing and removing tracepoint When executing a tracepoint, the tracepoint's func is dereferenced twice - in __DO_TRACE() (where the returned pointer is checked) and later on in __traceiter_##_name where the returned pointer is dereferenced without checking which leads to races against tracepoint_removal_sync() and crashes. This adds a check before referencing the pointer in tracepoint_ptr_deref. Link: https://lkml.kernel.org/r/20210202072326.120557-1-aik@ozlabs.ru Cc: stable@vger.kernel.org Fixes: d25e37d89dd2f ("tracepoint: Optimize using static_call()") Acked-by: Peter Zijlstra (Intel) Signed-off-by: Alexey Kardashevskiy Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 0f21617f1a66..966ed8980327 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -307,11 +307,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) \ it_func_ptr = \ rcu_dereference_raw((&__tracepoint_##_name)->funcs); \ - do { \ - it_func = (it_func_ptr)->func; \ - __data = (it_func_ptr)->data; \ - ((void(*)(void *, proto))(it_func))(__data, args); \ - } while ((++it_func_ptr)->func); \ + if (it_func_ptr) { \ + do { \ + it_func = (it_func_ptr)->func; \ + __data = (it_func_ptr)->data; \ + ((void(*)(void *, proto))(it_func))(__data, args); \ + } while ((++it_func_ptr)->func); \ + } \ return 0; \ } \ DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name); -- cgit v1.2.3-71-gd317 From 4c9fb5d9140802db4db9f66c23887f43174e113c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 2 Feb 2021 15:54:19 +0100 Subject: iommu: Check dev->iommu in dev_iommu_priv_get() before dereferencing it The dev_iommu_priv_get() needs a similar check to dev_iommu_fwspec_get() to make sure no NULL-ptr is dereferenced. Fixes: 05a0542b456e1 ("iommu/amd: Store dev_data as device iommu private data") Cc: stable@vger.kernel.org # v5.8+ Link: https://lore.kernel.org/r/20210202145419.29143-1-joro@8bytes.org Reference: https://bugzilla.kernel.org/show_bug.cgi?id=211241 Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index b3f0e2018c62..efa96263b81b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -616,7 +616,10 @@ static inline void dev_iommu_fwspec_set(struct device *dev, static inline void *dev_iommu_priv_get(struct device *dev) { - return dev->iommu->priv; + if (dev->iommu) + return dev->iommu->priv; + else + return NULL; } static inline void dev_iommu_priv_set(struct device *dev, void *priv) -- cgit v1.2.3-71-gd317 From 5ae4a4b45d4396aa7f7c008c4ae9eca981d43f8c Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 2 Feb 2021 10:25:11 +0530 Subject: cpufreq: Remove CPUFREQ_STICKY flag During cpufreq driver's registration, if the ->init() callback for all the CPUs fail then there is not much point in keeping the driver around as it will only account for more of unnecessary noise, for example cpufreq core will try to suspend/resume the driver which never got registered properly. The removal of such a driver is avoided if the driver carries the CPUFREQ_STICKY flag. This was added way back [1] in 2004 and perhaps no one should ever need it now. A lot of drivers do set this flag, probably because they just copied it from other drivers. This was added earlier for some platforms [2] because their cpufreq drivers were getting registered before the CPUs were registered with subsys framework. And hence they used to fail. The same isn't true anymore though. The current code flow in the kernel is: start_kernel() -> kernel_init() -> kernel_init_freeable() -> do_basic_setup() -> driver_init() -> cpu_dev_init() -> subsys_system_register() //For CPUs -> do_initcalls() -> cpufreq_register_driver() Clearly, the CPUs will always get registered with subsys framework before any cpufreq driver can get probed. Remove the flag and update the relevant drivers. Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/include/linux/cpufreq.h?id=7cc9f0d9a1ab04cedc60d64fd8dcf7df224a3b4d # [1] Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/arch/arm/mach-sa1100/cpu-sa1100.c?id=f59d3bbe35f6268d729f51be82af8325d62f20f5 # [2] Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq-dt.c | 2 +- drivers/cpufreq/cpufreq.c | 3 +-- drivers/cpufreq/davinci-cpufreq.c | 2 +- drivers/cpufreq/loongson1-cpufreq.c | 2 +- drivers/cpufreq/mediatek-cpufreq.c | 2 +- drivers/cpufreq/omap-cpufreq.c | 2 +- drivers/cpufreq/qcom-cpufreq-hw.c | 2 +- drivers/cpufreq/s3c24xx-cpufreq.c | 2 +- drivers/cpufreq/s5pv210-cpufreq.c | 2 +- drivers/cpufreq/sa1100-cpufreq.c | 2 +- drivers/cpufreq/sa1110-cpufreq.c | 2 +- drivers/cpufreq/scmi-cpufreq.c | 2 +- drivers/cpufreq/scpi-cpufreq.c | 2 +- drivers/cpufreq/spear-cpufreq.c | 2 +- drivers/cpufreq/tegra186-cpufreq.c | 2 +- drivers/cpufreq/tegra194-cpufreq.c | 3 +-- drivers/cpufreq/vexpress-spc-cpufreq.c | 3 +-- include/linux/cpufreq.h | 17 +++++++---------- 18 files changed, 24 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index ad4234518ef6..b1e1bdc63b01 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -175,7 +175,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy) } static struct cpufreq_driver dt_cpufreq_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .target_index = set_target, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index d0a3525ce27f..7d0ae968def7 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2810,8 +2810,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (ret) goto err_boost_unreg; - if (!(cpufreq_driver->flags & CPUFREQ_STICKY) && - list_empty(&cpufreq_policy_list)) { + if (unlikely(list_empty(&cpufreq_policy_list))) { /* if all ->init() calls failed, unregister */ ret = -ENODEV; pr_debug("%s: No CPU initialized for driver %s\n", __func__, diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c index 91f477a6cbc4..9e97f60f8199 100644 --- a/drivers/cpufreq/davinci-cpufreq.c +++ b/drivers/cpufreq/davinci-cpufreq.c @@ -95,7 +95,7 @@ static int davinci_cpu_init(struct cpufreq_policy *policy) } static struct cpufreq_driver davinci_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = davinci_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/loongson1-cpufreq.c b/drivers/cpufreq/loongson1-cpufreq.c index 86f612593e49..fb72d709db56 100644 --- a/drivers/cpufreq/loongson1-cpufreq.c +++ b/drivers/cpufreq/loongson1-cpufreq.c @@ -116,7 +116,7 @@ static int ls1x_cpufreq_exit(struct cpufreq_policy *policy) static struct cpufreq_driver ls1x_cpufreq_driver = { .name = "cpufreq-ls1x", - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = ls1x_cpufreq_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index 022e3e966e71..f2e491b25b07 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -463,7 +463,7 @@ static int mtk_cpufreq_exit(struct cpufreq_policy *policy) } static struct cpufreq_driver mtk_cpufreq_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c index 3694bb030df3..e035ee216b0f 100644 --- a/drivers/cpufreq/omap-cpufreq.c +++ b/drivers/cpufreq/omap-cpufreq.c @@ -144,7 +144,7 @@ static int omap_cpu_exit(struct cpufreq_policy *policy) } static struct cpufreq_driver omap_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = omap_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 9ed5341dc515..2a3b4f44488b 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -374,7 +374,7 @@ static struct freq_attr *qcom_cpufreq_hw_attr[] = { }; static struct cpufreq_driver cpufreq_qcom_hw_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c index 37efc0dc3f91..7380c32b238e 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -420,7 +420,7 @@ static int s3c_cpufreq_resume(struct cpufreq_policy *policy) #endif static struct cpufreq_driver s3c24xx_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .target = s3c_cpufreq_target, .get = cpufreq_generic_get, .init = s3c_cpufreq_init, diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index bed496cf8d24..69786e5bbf05 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -574,7 +574,7 @@ static int s5pv210_cpufreq_reboot_notifier_event(struct notifier_block *this, } static struct cpufreq_driver s5pv210_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = s5pv210_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/sa1100-cpufreq.c b/drivers/cpufreq/sa1100-cpufreq.c index 5c075ef6adc0..252b9fc26124 100644 --- a/drivers/cpufreq/sa1100-cpufreq.c +++ b/drivers/cpufreq/sa1100-cpufreq.c @@ -186,7 +186,7 @@ static int __init sa1100_cpu_init(struct cpufreq_policy *policy) } static struct cpufreq_driver sa1100_driver __refdata = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, .verify = cpufreq_generic_frequency_table_verify, .target_index = sa1100_target, diff --git a/drivers/cpufreq/sa1110-cpufreq.c b/drivers/cpufreq/sa1110-cpufreq.c index d9d04d935b3a..1a83c8678a63 100644 --- a/drivers/cpufreq/sa1110-cpufreq.c +++ b/drivers/cpufreq/sa1110-cpufreq.c @@ -310,7 +310,7 @@ static int __init sa1110_cpu_init(struct cpufreq_policy *policy) /* sa1110_driver needs __refdata because it must remain after init registers * it with cpufreq_register_driver() */ static struct cpufreq_driver sa1110_driver __refdata = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, .verify = cpufreq_generic_frequency_table_verify, .target_index = sa1110_target, diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 491a0a24fb1e..5bd03b59887f 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -217,7 +217,7 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy) static struct cpufreq_driver scmi_cpufreq_driver = { .name = "scmi", - .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index e5140ad63db8..d6a698a1b5d1 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -191,7 +191,7 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy) static struct cpufreq_driver scpi_cpufreq_driver = { .name = "scpi-cpufreq", - .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c index 73bd8dc47074..7d0d62a06bf3 100644 --- a/drivers/cpufreq/spear-cpufreq.c +++ b/drivers/cpufreq/spear-cpufreq.c @@ -160,7 +160,7 @@ static int spear_cpufreq_init(struct cpufreq_policy *policy) static struct cpufreq_driver spear_cpufreq_driver = { .name = "cpufreq-spear", - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = spear_cpufreq_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index e566ea298b59..5d1943e787b0 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -117,7 +117,7 @@ static unsigned int tegra186_cpufreq_get(unsigned int cpu) static struct cpufreq_driver tegra186_cpufreq_driver = { .name = "tegra186", - .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, .get = tegra186_cpufreq_get, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index 6a67f36f3b80..a9620e4489ae 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -272,8 +272,7 @@ static int tegra194_cpufreq_set_target(struct cpufreq_policy *policy, static struct cpufreq_driver tegra194_cpufreq_driver = { .name = "tegra194", - .flags = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS | - CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = tegra194_cpufreq_set_target, .get = tegra194_get_speed, diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index f711d8eaea6a..51dfa9ae6cf5 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -486,8 +486,7 @@ static void ve_spc_cpufreq_ready(struct cpufreq_policy *policy) static struct cpufreq_driver ve_spc_cpufreq_driver = { .name = "vexpress-spc", - .flags = CPUFREQ_STICKY | - CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = ve_spc_cpufreq_set_target, diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9c8b7437b6cd..c8e40e91fe9b 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -387,8 +387,13 @@ struct cpufreq_driver { /* flags */ -/* driver isn't removed even if all ->init() calls failed */ -#define CPUFREQ_STICKY BIT(0) +/* + * Set by drivers that need to update internale upper and lower boundaries along + * with the target frequency and so the core and governors should also invoke + * the diver if the target frequency does not change, but the policy min or max + * may have changed. + */ +#define CPUFREQ_NEED_UPDATE_LIMITS BIT(0) /* loops_per_jiffy or other kernel "constants" aren't affected by frequency transitions */ #define CPUFREQ_CONST_LOOPS BIT(1) @@ -432,14 +437,6 @@ struct cpufreq_driver { */ #define CPUFREQ_IS_COOLING_DEV BIT(7) -/* - * Set by drivers that need to update internale upper and lower boundaries along - * with the target frequency and so the core and governors should also invoke - * the diver if the target frequency does not change, but the policy min or max - * may have changed. - */ -#define CPUFREQ_NEED_UPDATE_LIMITS BIT(8) - int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3-71-gd317 From 2f0531869fd22182e769b10dd6cf151861ede791 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 2 Feb 2021 11:11:55 +0530 Subject: cpufreq: Remove unused flag CPUFREQ_PM_NO_WARN This flag is set by one of the drivers but it isn't used in the code otherwise. Remove the unused flag and update the driver. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/pmac32-cpufreq.c | 3 +-- include/linux/cpufreq.h | 13 +++++-------- 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index 73621bc11976..4f20c6a9108d 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -439,8 +439,7 @@ static struct cpufreq_driver pmac_cpufreq_driver = { .init = pmac_cpufreq_cpu_init, .suspend = pmac_cpufreq_suspend, .resume = pmac_cpufreq_resume, - .flags = CPUFREQ_PM_NO_WARN | - CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, + .flags = CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, .attr = cpufreq_generic_attr, .name = "powermac", }; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c8e40e91fe9b..353969c7acd3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -398,8 +398,11 @@ struct cpufreq_driver { /* loops_per_jiffy or other kernel "constants" aren't affected by frequency transitions */ #define CPUFREQ_CONST_LOOPS BIT(1) -/* don't warn on suspend/resume speed mismatches */ -#define CPUFREQ_PM_NO_WARN BIT(2) +/* + * Set by drivers that want the core to automatically register the cpufreq + * driver as a thermal cooling device. + */ +#define CPUFREQ_IS_COOLING_DEV BIT(2) /* * This should be set by platforms having multiple clock-domains, i.e. @@ -431,12 +434,6 @@ struct cpufreq_driver { */ #define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING BIT(6) -/* - * Set by drivers that want the core to automatically register the cpufreq - * driver as a thermal cooling device. - */ -#define CPUFREQ_IS_COOLING_DEV BIT(7) - int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3-71-gd317 From 585fc0d2871c9318c949fbf45b1f081edd489e96 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 4 Feb 2021 18:32:03 -0800 Subject: mm: hugetlbfs: fix cannot migrate the fallocated HugeTLB page If a new hugetlb page is allocated during fallocate it will not be marked as active (set_page_huge_active) which will result in a later isolate_huge_page failure when the page migration code would like to move that page. Such a failure would be unexpected and wrong. Only export set_page_huge_active, just leave clear_page_huge_active as static. Because there are no external users. Link: https://lkml.kernel.org/r/20210115124942.46403-3-songmuchun@bytedance.com Fixes: 70c3547e36f5 (hugetlbfs: add hugetlbfs_fallocate()) Signed-off-by: Muchun Song Acked-by: Michal Hocko Reviewed-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Yang Shi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 3 ++- include/linux/hugetlb.h | 2 ++ mm/hugetlb.c | 2 +- 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b5c109703daa..21c20fd5f9ee 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -735,9 +735,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_unlock(&hugetlb_fault_mutex_table[hash]); + set_page_huge_active(page); /* * unlock_page because locked by add_to_page_cache() - * page_put due to reference from alloc_huge_page() + * put_page() due to reference from alloc_huge_page() */ unlock_page(page); put_page(page); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ebca2ef02212..b5807f23caf8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -770,6 +770,8 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif +void set_page_huge_active(struct page *page); + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 18f6ee317900..6f0e242d38ca 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1349,7 +1349,7 @@ bool page_huge_active(struct page *page) } /* never called for tail page */ -static void set_page_huge_active(struct page *page) +void set_page_huge_active(struct page *page) { VM_BUG_ON_PAGE(!PageHeadHuge(page), page); SetPagePrivate(&page[1]); -- cgit v1.2.3-71-gd317 From 4f6ec8602341e97b364e4e0d41a1ed08148f5e98 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 4 Feb 2021 18:32:24 -0800 Subject: mm/vmalloc: separate put pages and flush VM flags When VM_MAP_PUT_PAGES was added, it was defined with the same value as VM_FLUSH_RESET_PERMS. This doesn't seem like it will cause any big functional problems other than some excess flushing for VM_MAP_PUT_PAGES allocations. Redefine VM_MAP_PUT_PAGES to have its own value. Also, rearrange things so flags are less likely to be missed in the future. Link: https://lkml.kernel.org/r/20210122233706.9304-1-rick.p.edgecombe@intel.com Fixes: b944afc9d64d ("mm: add a VM_MAP_PUT_PAGES flag for vmap") Signed-off-by: Rick Edgecombe Suggested-by: Matthew Wilcox Cc: Miaohe Lin Cc: Christoph Hellwig Cc: Daniel Axtens Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 80c0181c411d..cedcda6593f6 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -24,7 +24,8 @@ struct notifier_block; /* in notifier.h */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ -#define VM_MAP_PUT_PAGES 0x00000100 /* put pages and free array in vfree */ +#define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ +#define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ /* * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC. @@ -37,12 +38,6 @@ struct notifier_block; /* in notifier.h */ * determine which allocations need the module shadow freed. */ -/* - * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with - * vfree_atomic(). - */ -#define VM_FLUSH_RESET_PERMS 0x00000100 /* Reset direct map and flush TLB on unmap */ - /* bits [20..32] reserved for arch specific ioremap internals */ /* -- cgit v1.2.3-71-gd317 From 49c6631d3b4f61a7b5bb0453a885a12bfa06ffd8 Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Thu, 4 Feb 2021 18:32:49 -0800 Subject: kasan: add explicit preconditions to kasan_report() Patch series "kasan: Fix metadata detection for KASAN_HW_TAGS", v5. With the introduction of KASAN_HW_TAGS, kasan_report() currently assumes that every location in memory has valid metadata associated. This is due to the fact that addr_has_metadata() returns always true. As a consequence of this, an invalid address (e.g. NULL pointer address) passed to kasan_report() when KASAN_HW_TAGS is enabled, leads to a kernel panic. Example below, based on arm64: BUG: KASAN: invalid-access in 0x0 Read at addr 0000000000000000 by task swapper/0/1 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Mem abort info: ESR = 0x96000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 ... Call trace: mte_get_mem_tag+0x24/0x40 kasan_report+0x1a4/0x410 alsa_sound_last_init+0x8c/0xa4 do_one_initcall+0x50/0x1b0 kernel_init_freeable+0x1d4/0x23c kernel_init+0x14/0x118 ret_from_fork+0x10/0x34 Code: d65f03c0 9000f021 f9428021 b6cfff61 (d9600000) ---[ end trace 377c8bb45bdd3a1a ]--- hrtimer: interrupt took 48694256 ns note: swapper/0[1] exited with preempt_count 1 Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b SMP: stopping secondary CPUs Kernel Offset: 0x35abaf140000 from 0xffff800010000000 PHYS_OFFSET: 0x40000000 CPU features: 0x0a7e0152,61c0a030 Memory Limit: none ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]--- This series fixes the behavior of addr_has_metadata() that now returns true only when the address is valid. This patch (of 2): With the introduction of KASAN_HW_TAGS, kasan_report() accesses the metadata only when addr_has_metadata() succeeds. Add a comment to make sure that the preconditions to the function are explicitly clarified. Link: https://lkml.kernel.org/r/20210126134409.47894-1-vincenzo.frascino@arm.com Link: https://lkml.kernel.org/r/20210126134409.47894-2-vincenzo.frascino@arm.com Signed-off-by: Vincenzo Frascino Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Leon Romanovsky Cc: Andrey Konovalov Cc: Catalin Marinas Cc: Will Deacon Cc: Mark Rutland Cc: "Paul E . McKenney" Cc: Naresh Kamboju Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index fe1ae73ff8b5..0aea9e2a2a01 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -333,6 +333,13 @@ static inline void *kasan_reset_tag(const void *addr) return (void *)arch_kasan_reset_tag(addr); } +/** + * kasan_report - print a report about a bad memory access detected by KASAN + * @addr: address of the bad access + * @size: size of the bad access + * @is_write: whether the bad access is a write or a read + * @ip: instruction pointer for the accessibility check or the bad access itself + */ bool kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); -- cgit v1.2.3-71-gd317 From 4c7bcb51ae25f79e3733982e5d0cd8ce8640ddfc Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 21 Dec 2020 19:56:47 +0100 Subject: genirq: Prevent [devm_]irq_alloc_desc from returning irq 0 Since commit a85a6c86c25b ("driver core: platform: Clarify that IRQ 0 is invalid"), having a linux-irq with number 0 will trigger a WARN() when calling platform_get_irq*() to retrieve that linux-irq. Since [devm_]irq_alloc_desc allocs a single irq and since irq 0 is not used on some systems, it can return 0, triggering that WARN(). This happens e.g. on Intel Bay Trail and Cherry Trail devices using the LPE audio engine for HDMI audio: 0 is an invalid IRQ number WARNING: CPU: 3 PID: 472 at drivers/base/platform.c:238 platform_get_irq_optional+0x108/0x180 Modules linked in: snd_hdmi_lpe_audio(+) ... Call Trace: platform_get_irq+0x17/0x30 hdmi_lpe_audio_probe+0x4a/0x6c0 [snd_hdmi_lpe_audio] ---[ end trace ceece38854223a0b ]--- Change the 'from' parameter passed to __[devm_]irq_alloc_descs() by the [devm_]irq_alloc_desc macros from 0 to 1, so that these macros will no longer return 0. Fixes: a85a6c86c25b ("driver core: platform: Clarify that IRQ 0 is invalid") Signed-off-by: Hans de Goede Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20201221185647.226146-1-hdegoede@redhat.com --- include/linux/irq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 4aeb1c4c7e07..2efde6a79b7e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -928,7 +928,7 @@ int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from, __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL) #define irq_alloc_desc(node) \ - irq_alloc_descs(-1, 0, 1, node) + irq_alloc_descs(-1, 1, 1, node) #define irq_alloc_desc_at(at, node) \ irq_alloc_descs(at, at, 1, node) @@ -943,7 +943,7 @@ int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from, __devm_irq_alloc_descs(dev, irq, from, cnt, node, THIS_MODULE, NULL) #define devm_irq_alloc_desc(dev, node) \ - devm_irq_alloc_descs(dev, -1, 0, 1, node) + devm_irq_alloc_descs(dev, -1, 1, 1, node) #define devm_irq_alloc_desc_at(dev, at, node) \ devm_irq_alloc_descs(dev, at, at, 1, node) -- cgit v1.2.3-71-gd317 From 6342adcaa683c2b705c24ed201dc11b35854c88d Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Wed, 3 Feb 2021 13:00:48 -0500 Subject: entry: Ensure trap after single-step on system call return Commit 299155244770 ("entry: Drop usage of TIF flags in the generic syscall code") introduced a bug on architectures using the generic syscall entry code, in which processes stopped by PTRACE_SYSCALL do not trap on syscall return after receiving a TIF_SINGLESTEP. The reason is that the meaning of TIF_SINGLESTEP flag is overloaded to cause the trap after a system call is executed, but since the above commit, the syscall call handler only checks for the SYSCALL_WORK flags on the exit work. Split the meaning of TIF_SINGLESTEP such that it only means single-step mode, and create a new type of SYSCALL_WORK to request a trap immediately after a syscall in single-step mode. In the current implementation, the SYSCALL_WORK flag shadows the TIF_SINGLESTEP flag for simplicity. Update x86 to flip this bit when a tracer enables single stepping. Fixes: 299155244770 ("entry: Drop usage of TIF flags in the generic syscall code") Suggested-by: Linus Torvalds Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Tested-by: Kyle Huey Link: https://lore.kernel.org/r/87h7mtc9pr.fsf_-_@collabora.com --- arch/x86/include/asm/entry-common.h | 2 -- arch/x86/kernel/step.c | 10 ++++++++-- include/linux/entry-common.h | 1 + include/linux/thread_info.h | 2 ++ kernel/entry/common.c | 12 ++---------- 5 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 6fe54b2813c1..2b87b191b3b8 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -43,8 +43,6 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) } #define arch_check_user_regs arch_check_user_regs -#define ARCH_SYSCALL_EXIT_WORK (_TIF_SINGLESTEP) - static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, unsigned long ti_work) { diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 60d2c3798ba2..0f3c307b37b3 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -127,12 +127,17 @@ static int enable_single_step(struct task_struct *child) regs->flags |= X86_EFLAGS_TF; /* - * Always set TIF_SINGLESTEP - this guarantees that - * we single-step system calls etc.. This will also + * Always set TIF_SINGLESTEP. This will also * cause us to set TF when returning to user mode. */ set_tsk_thread_flag(child, TIF_SINGLESTEP); + /* + * Ensure that a trap is triggered once stepping out of a system + * call prior to executing any user instruction. + */ + set_task_syscall_work(child, SYSCALL_EXIT_TRAP); + oflags = regs->flags; /* Set TF on the kernel stack.. */ @@ -230,6 +235,7 @@ void user_disable_single_step(struct task_struct *child) /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); + clear_task_syscall_work(child, SYSCALL_EXIT_TRAP); /* But touch TF only if it was set by us.. */ if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF)) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index ca86a00abe86..a104b298019a 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -46,6 +46,7 @@ SYSCALL_WORK_SYSCALL_TRACE | \ SYSCALL_WORK_SYSCALL_AUDIT | \ SYSCALL_WORK_SYSCALL_USER_DISPATCH | \ + SYSCALL_WORK_SYSCALL_EXIT_TRAP | \ ARCH_SYSCALL_WORK_EXIT) /* diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index c8a974cead73..9b2158c69275 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -43,6 +43,7 @@ enum syscall_work_bit { SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, + SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) @@ -51,6 +52,7 @@ enum syscall_work_bit { #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) +#define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 6dd82be60df8..f9d491b17b78 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -209,15 +209,9 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs) lockdep_sys_exit(); } -#ifndef _TIF_SINGLESTEP -static inline bool report_single_step(unsigned long work) -{ - return false; -} -#else /* * If SYSCALL_EMU is set, then the only reason to report is when - * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall + * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall * instruction has been already reported in syscall_enter_from_user_mode(). */ static inline bool report_single_step(unsigned long work) @@ -225,10 +219,8 @@ static inline bool report_single_step(unsigned long work) if (work & SYSCALL_WORK_SYSCALL_EMU) return false; - return !!(current_thread_info()->flags & _TIF_SINGLESTEP); + return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP; } -#endif - static void syscall_exit_work(struct pt_regs *regs, unsigned long work) { -- cgit v1.2.3-71-gd317