From 3a38bb98d9abdc3856f26b5ed4332803065cd7cf Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 10 Apr 2018 09:37:32 -0700 Subject: bpf/tracing: fix a deadlock in perf_event_detach_bpf_prog syzbot reported a possible deadlock in perf_event_detach_bpf_prog. The error details: ====================================================== WARNING: possible circular locking dependency detected 4.16.0-rc7+ #3 Not tainted ------------------------------------------------------ syz-executor7/24531 is trying to acquire lock: (bpf_event_mutex){+.+.}, at: [<000000008a849b07>] perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854 but task is already holding lock: (&mm->mmap_sem){++++}, at: [<0000000038768f87>] vm_mmap_pgoff+0x198/0x280 mm/util.c:353 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++}: __might_fault+0x13a/0x1d0 mm/memory.c:4571 _copy_to_user+0x2c/0xc0 lib/usercopy.c:25 copy_to_user include/linux/uaccess.h:155 [inline] bpf_prog_array_copy_info+0xf2/0x1c0 kernel/bpf/core.c:1694 perf_event_query_prog_array+0x1c7/0x2c0 kernel/trace/bpf_trace.c:891 _perf_ioctl kernel/events/core.c:4750 [inline] perf_ioctl+0x3e1/0x1480 kernel/events/core.c:4770 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686 SYSC_ioctl fs/ioctl.c:701 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 -> #0 (bpf_event_mutex){+.+.}: lock_acquire+0x1d5/0x580 kernel/locking/lockdep.c:3920 __mutex_lock_common kernel/locking/mutex.c:756 [inline] __mutex_lock+0x16f/0x1a80 kernel/locking/mutex.c:893 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:908 perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854 perf_event_free_bpf_prog kernel/events/core.c:8147 [inline] _free_event+0xbdb/0x10f0 kernel/events/core.c:4116 put_event+0x24/0x30 kernel/events/core.c:4204 perf_mmap_close+0x60d/0x1010 kernel/events/core.c:5172 remove_vma+0xb4/0x1b0 mm/mmap.c:172 remove_vma_list mm/mmap.c:2490 [inline] do_munmap+0x82a/0xdf0 mm/mmap.c:2731 mmap_region+0x59e/0x15a0 mm/mmap.c:1646 do_mmap+0x6c0/0xe00 mm/mmap.c:1483 do_mmap_pgoff include/linux/mm.h:2223 [inline] vm_mmap_pgoff+0x1de/0x280 mm/util.c:355 SYSC_mmap_pgoff mm/mmap.c:1533 [inline] SyS_mmap_pgoff+0x462/0x5f0 mm/mmap.c:1491 SYSC_mmap arch/x86/kernel/sys_x86_64.c:100 [inline] SyS_mmap+0x16/0x20 arch/x86/kernel/sys_x86_64.c:91 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(bpf_event_mutex); lock(&mm->mmap_sem); lock(bpf_event_mutex); *** DEADLOCK *** ====================================================== The bug is introduced by Commit f371b304f12e ("bpf/tracing: allow user space to query prog array on the same tp") where copy_to_user, which requires mm->mmap_sem, is called inside bpf_event_mutex lock. At the same time, during perf_event file descriptor close, mm->mmap_sem is held first and then subsequent perf_event_detach_bpf_prog needs bpf_event_mutex lock. Such a senario caused a deadlock. As suggested by Daniel, moving copy_to_user out of the bpf_event_mutex lock should fix the problem. Fixes: f371b304f12e ("bpf/tracing: allow user space to query prog array on the same tp") Reported-by: syzbot+dc5ca0e4c9bfafaf2bae@syzkaller.appspotmail.com Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 95a7abd0ee92..486e65e3db26 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -339,8 +339,8 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, struct bpf_prog *old_prog); int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, - __u32 __user *prog_ids, u32 request_cnt, - __u32 __user *prog_cnt); + u32 *prog_ids, u32 request_cnt, + u32 *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, -- cgit v1.3-18-gd494 From edf5c17d866eada03b8750368a12dc3def77d608 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 5 Apr 2018 16:15:55 +0200 Subject: staging: irda: remove remaining remants of irda code removal There were some documentation locations that irda was mentioned, as well as an old MAINTAINERS entry and the networking sysctl entries. Clean these all out as this stuff really is finally gone. Reported-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- Documentation/ioctl/ioctl-number.txt | 2 -- Documentation/networking/ip-sysctl.txt | 15 --------------- Documentation/process/magic-number.rst | 3 --- MAINTAINERS | 10 ---------- include/uapi/linux/sysctl.h | 18 ------------------ kernel/sysctl_binary.c | 20 +------------------- 6 files changed, 1 insertion(+), 67 deletions(-) (limited to 'include') diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 84bb74dcae12..7f7413e597f3 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -217,7 +217,6 @@ Code Seq#(hex) Include File Comments 'd' 02-40 pcmcia/ds.h conflict! 'd' F0-FF linux/digi1.h 'e' all linux/digi1.h conflict! -'e' 00-1F drivers/net/irda/irtty-sir.h conflict! 'f' 00-1F linux/ext2_fs.h conflict! 'f' 00-1F linux/ext3_fs.h conflict! 'f' 00-0F fs/jfs/jfs_dinode.h conflict! @@ -247,7 +246,6 @@ Code Seq#(hex) Include File Comments 'm' all linux/synclink.h conflict! 'm' 00-19 drivers/message/fusion/mptctl.h conflict! 'm' 00 drivers/scsi/megaraid/megaraid_ioctl.h conflict! -'m' 00-1F net/irda/irmod.h conflict! 'n' 00-7F linux/ncp_fs.h and fs/ncpfs/ioctl.c 'n' 80-8F uapi/linux/nilfs2_api.h NILFS2 'n' E0-FF linux/matroxfb.h matroxfb diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 5dc1a040a2f1..8725aa718b35 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -2126,18 +2126,3 @@ max_dgram_qlen - INTEGER Default: 10 - -UNDOCUMENTED: - -/proc/sys/net/irda/* - fast_poll_increase FIXME - warn_noreply_time FIXME - discovery_slots FIXME - slot_timeout FIXME - max_baud_rate FIXME - discovery_timeout FIXME - lap_keepalive_time FIXME - max_noreply_time FIXME - max_tx_data_size FIXME - max_tx_window FIXME - min_tx_turn_time FIXME diff --git a/Documentation/process/magic-number.rst b/Documentation/process/magic-number.rst index 00cecf1fcba9..633be1043690 100644 --- a/Documentation/process/magic-number.rst +++ b/Documentation/process/magic-number.rst @@ -157,8 +157,5 @@ memory management. See ``include/sound/sndmagic.h`` for complete list of them. M OSS sound drivers have their magic numbers constructed from the soundcard PCI ID - these are not listed here as well. -IrDA subsystem also uses large number of own magic numbers, see -``include/net/irda/irda.h`` for a complete list of them. - HFS is another larger user of magic numbers - you can find them in ``fs/hfs/hfs.h``. diff --git a/MAINTAINERS b/MAINTAINERS index 0a1410d5a621..c74c80e44879 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7396,16 +7396,6 @@ S: Obsolete F: include/uapi/linux/ipx.h F: drivers/staging/ipx/ -IRDA SUBSYSTEM -M: Samuel Ortiz -L: irda-users@lists.sourceforge.net (subscribers-only) -L: netdev@vger.kernel.org -W: http://irda.sourceforge.net/ -S: Obsolete -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sameo/irda-2.6.git -F: Documentation/networking/irda.txt -F: drivers/staging/irda/ - IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY) M: Marc Zyngier S: Maintained diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 0f272818a4d2..6b58371b1f0d 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -780,24 +780,6 @@ enum { NET_BRIDGE_NF_FILTER_PPPOE_TAGGED = 5, }; -/* proc/sys/net/irda */ -enum { - NET_IRDA_DISCOVERY=1, - NET_IRDA_DEVNAME=2, - NET_IRDA_DEBUG=3, - NET_IRDA_FAST_POLL=4, - NET_IRDA_DISCOVERY_SLOTS=5, - NET_IRDA_DISCOVERY_TIMEOUT=6, - NET_IRDA_SLOT_TIMEOUT=7, - NET_IRDA_MAX_BAUD_RATE=8, - NET_IRDA_MIN_TX_TURN_TIME=9, - NET_IRDA_MAX_TX_DATA_SIZE=10, - NET_IRDA_MAX_TX_WINDOW=11, - NET_IRDA_MAX_NOREPLY_TIME=12, - NET_IRDA_WARN_NOREPLY_TIME=13, - NET_IRDA_LAP_KEEPALIVE_TIME=14, -}; - /* CTL_FS names: */ enum diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index e8c0dab4fd65..07148b497451 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -704,24 +704,6 @@ static const struct bin_table bin_net_netfilter_table[] = { {} }; -static const struct bin_table bin_net_irda_table[] = { - { CTL_INT, NET_IRDA_DISCOVERY, "discovery" }, - { CTL_STR, NET_IRDA_DEVNAME, "devname" }, - { CTL_INT, NET_IRDA_DEBUG, "debug" }, - { CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" }, - { CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" }, - { CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" }, - { CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" }, - { CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" }, - { CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" }, - { CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" }, - { CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" }, - { CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" }, - { CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" }, - { CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" }, - {} -}; - static const struct bin_table bin_net_table[] = { { CTL_DIR, NET_CORE, "core", bin_net_core_table }, /* NET_ETHER not used */ @@ -743,7 +725,7 @@ static const struct bin_table bin_net_table[] = { { CTL_DIR, NET_LLC, "llc", bin_net_llc_table }, { CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table }, /* NET_DCCP "dccp" no longer used */ - { CTL_DIR, NET_IRDA, "irda", bin_net_irda_table }, + /* NET_IRDA "irda" no longer used */ { CTL_INT, 2089, "nf_conntrack_max" }, {} }; -- cgit v1.3-18-gd494 From 144345a4a8c3b497a3f60d3af9d6071a37660186 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 8 Apr 2018 11:05:15 +0200 Subject: soc: bcm2835: Make !RASPBERRYPI_FIRMWARE dummies return failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If CONFIG_RASPBERRYPI_FIRMWARE=n: drivers/gpio/gpio-raspberrypi-exp.c: In function ‘rpi_exp_gpio_get_polarity’: drivers/gpio/gpio-raspberrypi-exp.c:71: warning: ‘get.polarity’ is used uninitialized in this function drivers/gpio/gpio-raspberrypi-exp.c: In function ‘rpi_exp_gpio_get_direction’: drivers/gpio/gpio-raspberrypi-exp.c:150: warning: ‘get.direction’ is used uninitialized in this function The dummy firmware interface functions return 0, which means success, causing subsequent code to make use of the never initialized output parameter. Fix this by making the dummy functions return an error code (-ENOSYS) instead. Note that this assumes the firmware always fills in the requested data in the CONFIG_RASPBERRYPI_FIRMWARE=y case. Fixes: d45f1a563b92dac7 ("staging: vc04_services: fix up rpi firmware functions") Signed-off-by: Geert Uytterhoeven Reviewed-by: Eric Anholt Signed-off-by: Florian Fainelli --- include/soc/bcm2835/raspberrypi-firmware.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h index 50df5b28d2c9..8ee8991aa099 100644 --- a/include/soc/bcm2835/raspberrypi-firmware.h +++ b/include/soc/bcm2835/raspberrypi-firmware.h @@ -143,13 +143,13 @@ struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node); static inline int rpi_firmware_property(struct rpi_firmware *fw, u32 tag, void *data, size_t len) { - return 0; + return -ENOSYS; } static inline int rpi_firmware_property_list(struct rpi_firmware *fw, void *data, size_t tag_size) { - return 0; + return -ENOSYS; } static inline struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node) -- cgit v1.3-18-gd494 From 0ce9144471de9ee09306ca0127e7cd27521ccc3f Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 18 Apr 2018 14:08:27 +1000 Subject: block: add blk_queue_fua() helper function So we can check FUA support status from the iomap direct IO code. Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9af3e0f430bc..c362aadfe036 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -737,6 +737,7 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_preempt_only(q) \ test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags) +#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) extern int blk_set_preempt_only(struct request_queue *q); extern void blk_clear_preempt_only(struct request_queue *q); -- cgit v1.3-18-gd494 From 5692fceebeb7f11c07e2a990f7711a01ae437de2 Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Wed, 11 Apr 2018 16:15:43 -0500 Subject: ARM: OMAP2+: Fix build when using split object directories The sleep33xx and sleep43xx files should not depend on a header file generated in drivers/memory. Remove this dependency and instead allow both drivers/memory and arch/arm/mach-omap2 to generate all macros needed in headers local to their own paths. This fixes an issue where the build fail will when using O= to set a split object directory and arch/arm/mach-omap2 is built before drivers/memory with the following error: .../drivers/memory/emif-asm-offsets.c:1:0: fatal error: can't open drivers/memory/emif-asm-offsets.s for writing: No such file or directory compilation terminated. Fixes: 41d9d44d7258 ("ARM: OMAP2+: pm33xx-core: Add platform code needed for PM") Reviewed-by: Masahiro Yamada Signed-off-by: Dave Gerlach Acked-by: Santosh Shilimkar Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/Makefile | 6 +-- arch/arm/mach-omap2/pm-asm-offsets.c | 3 ++ arch/arm/mach-omap2/sleep33xx.S | 1 - arch/arm/mach-omap2/sleep43xx.S | 1 - drivers/memory/emif-asm-offsets.c | 72 +--------------------------------- include/linux/ti-emif-sram.h | 75 ++++++++++++++++++++++++++++++++++++ 6 files changed, 80 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index 4603c30fef73..0d9ce58bc464 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -243,8 +243,4 @@ arch/arm/mach-omap2/pm-asm-offsets.s: arch/arm/mach-omap2/pm-asm-offsets.c include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORCE $(call filechk,offsets,__TI_PM_ASM_OFFSETS_H__) -# For rule to generate ti-emif-asm-offsets.h dependency -include drivers/memory/Makefile.asm-offsets - -arch/arm/mach-omap2/sleep33xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h -arch/arm/mach-omap2/sleep43xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h +$(obj)/sleep33xx.o $(obj)/sleep43xx.o: include/generated/ti-pm-asm-offsets.h diff --git a/arch/arm/mach-omap2/pm-asm-offsets.c b/arch/arm/mach-omap2/pm-asm-offsets.c index 6d4392da7c11..b9846b19e5e2 100644 --- a/arch/arm/mach-omap2/pm-asm-offsets.c +++ b/arch/arm/mach-omap2/pm-asm-offsets.c @@ -7,9 +7,12 @@ #include #include +#include int main(void) { + ti_emif_asm_offsets(); + DEFINE(AMX3_PM_WFI_FLAGS_OFFSET, offsetof(struct am33xx_pm_sram_data, wfi_flags)); DEFINE(AMX3_PM_L2_AUX_CTRL_VAL_OFFSET, diff --git a/arch/arm/mach-omap2/sleep33xx.S b/arch/arm/mach-omap2/sleep33xx.S index 218d79930b04..322b3bb868b4 100644 --- a/arch/arm/mach-omap2/sleep33xx.S +++ b/arch/arm/mach-omap2/sleep33xx.S @@ -6,7 +6,6 @@ * Dave Gerlach, Vaibhav Bedia */ -#include #include #include #include diff --git a/arch/arm/mach-omap2/sleep43xx.S b/arch/arm/mach-omap2/sleep43xx.S index b24be624e8b9..8903814a6677 100644 --- a/arch/arm/mach-omap2/sleep43xx.S +++ b/arch/arm/mach-omap2/sleep43xx.S @@ -6,7 +6,6 @@ * Dave Gerlach, Vaibhav Bedia */ -#include #include #include #include diff --git a/drivers/memory/emif-asm-offsets.c b/drivers/memory/emif-asm-offsets.c index 71a89d5d3efd..db8043019ec6 100644 --- a/drivers/memory/emif-asm-offsets.c +++ b/drivers/memory/emif-asm-offsets.c @@ -16,77 +16,7 @@ int main(void) { - DEFINE(EMIF_SDCFG_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_sdcfg_val)); - DEFINE(EMIF_TIMING1_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_timing1_val)); - DEFINE(EMIF_TIMING2_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_timing2_val)); - DEFINE(EMIF_TIMING3_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_timing3_val)); - DEFINE(EMIF_REF_CTRL_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_ref_ctrl_val)); - DEFINE(EMIF_ZQCFG_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_zqcfg_val)); - DEFINE(EMIF_PMCR_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_pmcr_val)); - DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val)); - DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET, - offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl)); - DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET, - offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh)); - DEFINE(EMIF_COS_CONFIG_OFFSET, - offsetof(struct emif_regs_amx3, emif_cos_config)); - DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET, - offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping)); - DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET, - offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map)); - DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET, - offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map)); - DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_ocp_config_val)); - DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET, - offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim)); - DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET, - offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw)); - DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET, - offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val)); - DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET, - offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw)); - DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET, - offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1)); - DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET, - offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals)); - DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3)); - - BLANK(); - - DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET, - offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt)); - DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET, - offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys)); - DEFINE(EMIF_PM_CONFIG_OFFSET, - offsetof(struct ti_emif_pm_data, ti_emif_sram_config)); - DEFINE(EMIF_PM_REGS_VIRT_OFFSET, - offsetof(struct ti_emif_pm_data, regs_virt)); - DEFINE(EMIF_PM_REGS_PHYS_OFFSET, - offsetof(struct ti_emif_pm_data, regs_phys)); - DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data)); - - BLANK(); - - DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET, - offsetof(struct ti_emif_pm_functions, save_context)); - DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET, - offsetof(struct ti_emif_pm_functions, restore_context)); - DEFINE(EMIF_PM_ENTER_SR_OFFSET, - offsetof(struct ti_emif_pm_functions, enter_sr)); - DEFINE(EMIF_PM_EXIT_SR_OFFSET, - offsetof(struct ti_emif_pm_functions, exit_sr)); - DEFINE(EMIF_PM_ABORT_SR_OFFSET, - offsetof(struct ti_emif_pm_functions, abort_sr)); - DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions)); + ti_emif_asm_offsets(); return 0; } diff --git a/include/linux/ti-emif-sram.h b/include/linux/ti-emif-sram.h index 45bc6b376492..53604b087f2c 100644 --- a/include/linux/ti-emif-sram.h +++ b/include/linux/ti-emif-sram.h @@ -60,6 +60,81 @@ struct ti_emif_pm_functions { u32 abort_sr; } __packed __aligned(8); +static inline void ti_emif_asm_offsets(void) +{ + DEFINE(EMIF_SDCFG_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_sdcfg_val)); + DEFINE(EMIF_TIMING1_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_timing1_val)); + DEFINE(EMIF_TIMING2_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_timing2_val)); + DEFINE(EMIF_TIMING3_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_timing3_val)); + DEFINE(EMIF_REF_CTRL_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_ref_ctrl_val)); + DEFINE(EMIF_ZQCFG_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_zqcfg_val)); + DEFINE(EMIF_PMCR_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_pmcr_val)); + DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val)); + DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET, + offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl)); + DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET, + offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh)); + DEFINE(EMIF_COS_CONFIG_OFFSET, + offsetof(struct emif_regs_amx3, emif_cos_config)); + DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET, + offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping)); + DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET, + offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map)); + DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET, + offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map)); + DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_ocp_config_val)); + DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET, + offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim)); + DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET, + offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw)); + DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET, + offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val)); + DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET, + offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw)); + DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET, + offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1)); + DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET, + offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals)); + DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3)); + + BLANK(); + + DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET, + offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt)); + DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET, + offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys)); + DEFINE(EMIF_PM_CONFIG_OFFSET, + offsetof(struct ti_emif_pm_data, ti_emif_sram_config)); + DEFINE(EMIF_PM_REGS_VIRT_OFFSET, + offsetof(struct ti_emif_pm_data, regs_virt)); + DEFINE(EMIF_PM_REGS_PHYS_OFFSET, + offsetof(struct ti_emif_pm_data, regs_phys)); + DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data)); + + BLANK(); + + DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET, + offsetof(struct ti_emif_pm_functions, save_context)); + DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET, + offsetof(struct ti_emif_pm_functions, restore_context)); + DEFINE(EMIF_PM_ENTER_SR_OFFSET, + offsetof(struct ti_emif_pm_functions, enter_sr)); + DEFINE(EMIF_PM_EXIT_SR_OFFSET, + offsetof(struct ti_emif_pm_functions, exit_sr)); + DEFINE(EMIF_PM_ABORT_SR_OFFSET, + offsetof(struct ti_emif_pm_functions, abort_sr)); + DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions)); +} + struct gen_pool; int ti_emif_copy_pm_function_table(struct gen_pool *sram_pool, void *dst); -- cgit v1.3-18-gd494 From 4d79e7d0f0cfe22c05c21a1008fa000f153119aa Mon Sep 17 00:00:00 2001 From: John Pittman Date: Sat, 24 Mar 2018 09:30:48 -0400 Subject: scsi: core: remove reference to scsi_show_extd_sense() In commit 2104551969e8 ("scsi: use per-cpu buffer for formatting sense"), function scsi_show_extd_sense() was removed, switching use over to scsi_format_extd_sense(). Remove last reference to scsi_show_extd_sense() in include/scsi/scsi_dbg.h. Signed-off-by: John Pittman Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_dbg.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h index 04e0679767f6..e03bd9d41fa8 100644 --- a/include/scsi/scsi_dbg.h +++ b/include/scsi/scsi_dbg.h @@ -11,8 +11,6 @@ struct scsi_sense_hdr; extern void scsi_print_command(struct scsi_cmnd *); extern size_t __scsi_format_command(char *, size_t, const unsigned char *, size_t); -extern void scsi_show_extd_sense(const struct scsi_device *, const char *, - unsigned char, unsigned char); extern void scsi_print_sense_hdr(const struct scsi_device *, const char *, const struct scsi_sense_hdr *); extern void scsi_print_sense(const struct scsi_cmnd *); -- cgit v1.3-18-gd494 From 6667e6d91c88a788d5ab1b1e999d245473e84a90 Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Wed, 28 Mar 2018 12:42:18 +0300 Subject: scsi: ufs: add trace event for ufs upiu Add UFS Protocol Information Units(upiu) trace events for ufs driver, used to trace various ufs transaction types- command, task-management and device management. The trace-point format is generic and can be easily adapted to trace other upius if needed. Currently tracing ufs transaction of type 'device management', which this patch introduce, cannot be obtained from any other trace. Device management transactions are used for communication with the device such as reading and writing descriptor or attributes etc. Signed-off-by: Ohad Sharabi Reviewed-by: Stanislav Nijnikov Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/trace/events/ufs.h | 27 +++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) (limited to 'include') diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index c5b1bf1cadcb..00e79057f870 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -276,6 +276,35 @@ static inline void ufshcd_remove_non_printable(char *val) *val = ' '; } +static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag, + const char *str) +{ + struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr; + + trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->sc.cdb); +} + +static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag, + const char *str) +{ + struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr; + + trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->qr); +} + +static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag, + const char *str) +{ + struct utp_task_req_desc *descp; + struct utp_upiu_task_req *task_req; + int off = (int)tag - hba->nutrs; + + descp = &hba->utmrdl_base_addr[off]; + task_req = (struct utp_upiu_task_req *)descp->task_req_upiu; + trace_ufshcd_upiu(dev_name(hba->dev), str, &task_req->header, + &task_req->input_param1); +} + static void ufshcd_add_command_trace(struct ufs_hba *hba, unsigned int tag, const char *str) { @@ -285,6 +314,9 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, struct ufshcd_lrb *lrbp; int transfer_len = -1; + /* trace UPIU also */ + ufshcd_add_cmd_upiu_trace(hba, tag, str); + if (!trace_ufshcd_command_enabled()) return; @@ -2550,6 +2582,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba, hba->dev_cmd.complete = &wait; + ufshcd_add_query_upiu_trace(hba, tag, "query_send"); /* Make sure descriptors are ready before ringing the doorbell */ wmb(); spin_lock_irqsave(hba->host->host_lock, flags); @@ -2559,6 +2592,9 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba, err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout); + ufshcd_add_query_upiu_trace(hba, tag, + err ? "query_complete_err" : "query_complete"); + out_put_tag: ufshcd_put_dev_cmd_tag(hba, tag); wake_up(&hba->dev_cmd.tag_wq); @@ -5443,11 +5479,14 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id, spin_unlock_irqrestore(host->host_lock, flags); + ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_send"); + /* wait until the task management command is completed */ err = wait_event_timeout(hba->tm_wq, test_bit(free_slot, &hba->tm_condition), msecs_to_jiffies(TM_CMD_TIMEOUT)); if (!err) { + ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete_err"); dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n", __func__, tm_function); if (ufshcd_clear_tm_cmd(hba, free_slot)) @@ -5456,6 +5495,7 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id, err = -ETIMEDOUT; } else { err = ufshcd_task_req_compl(hba, free_slot, tm_response); + ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete"); } clear_bit(free_slot, &hba->tm_condition); diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h index bf6f82673492..f8260e5c79ad 100644 --- a/include/trace/events/ufs.h +++ b/include/trace/events/ufs.h @@ -257,6 +257,33 @@ TRACE_EVENT(ufshcd_command, ) ); +TRACE_EVENT(ufshcd_upiu, + TP_PROTO(const char *dev_name, const char *str, void *hdr, void *tsf), + + TP_ARGS(dev_name, str, hdr, tsf), + + TP_STRUCT__entry( + __string(dev_name, dev_name) + __string(str, str) + __array(unsigned char, hdr, 12) + __array(unsigned char, tsf, 16) + ), + + TP_fast_assign( + __assign_str(dev_name, dev_name); + __assign_str(str, str); + memcpy(__entry->hdr, hdr, sizeof(__entry->hdr)); + memcpy(__entry->tsf, tsf, sizeof(__entry->tsf)); + ), + + TP_printk( + "%s: %s: HDR:%s, CDB:%s", + __get_str(str), __get_str(dev_name), + __print_hex(__entry->hdr, sizeof(__entry->hdr)), + __print_hex(__entry->tsf, sizeof(__entry->tsf)) + ) +); + #endif /* if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ) */ /* This part must be outside protection */ -- cgit v1.3-18-gd494 From ccce20fc7968d546fb1e8e147bf5cdc8afc4278a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 16 Apr 2018 18:04:41 -0700 Subject: scsi: sd_zbc: Avoid that resetting a zone fails sporadically Since SCSI scanning occurs asynchronously, since sd_revalidate_disk() is called from sd_probe_async() and since sd_revalidate_disk() calls sd_zbc_read_zones() it can happen that sd_zbc_read_zones() is called concurrently with blkdev_report_zones() and/or blkdev_reset_zones(). That can cause these functions to fail with -EIO because sd_zbc_read_zones() e.g. sets q->nr_zones to zero before restoring it to the actual value, even if no drive characteristics have changed. Avoid that this can happen by making the following changes: - Protect the code that updates zone information with blk_queue_enter() and blk_queue_exit(). - Modify sd_zbc_setup_seq_zones_bitmap() and sd_zbc_setup() such that these functions do not modify struct scsi_disk before all zone information has been obtained. Note: since commit 055f6e18e08f ("block: Make q_usage_counter also track legacy requests"; kernel v4.15) the request queue freezing mechanism also affects legacy request queues. Fixes: 89d947561077 ("sd: Implement support for ZBC devices") Signed-off-by: Bart Van Assche Cc: Jens Axboe Cc: Damien Le Moal Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: stable@vger.kernel.org # v4.16 Reviewed-by: Damien Le Moal Signed-off-by: Martin K. Petersen --- drivers/scsi/sd_zbc.c | 140 +++++++++++++++++++++++++++++-------------------- include/linux/blkdev.h | 5 ++ 2 files changed, 87 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 41df75eea57b..210407cd2341 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -400,8 +400,10 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf) * * Check that all zones of the device are equal. The last zone can however * be smaller. The zone size must also be a power of two number of LBAs. + * + * Returns the zone size in bytes upon success or an error code upon failure. */ -static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) +static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) { u64 zone_blocks = 0; sector_t block = 0; @@ -412,8 +414,6 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) int ret; u8 same; - sdkp->zone_blocks = 0; - /* Get a buffer */ buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL); if (!buf) @@ -445,16 +445,17 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) /* Parse zone descriptors */ while (rec < buf + buf_len) { - zone_blocks = get_unaligned_be64(&rec[8]); - if (sdkp->zone_blocks == 0) { - sdkp->zone_blocks = zone_blocks; - } else if (zone_blocks != sdkp->zone_blocks && - (block + zone_blocks < sdkp->capacity - || zone_blocks > sdkp->zone_blocks)) { - zone_blocks = 0; + u64 this_zone_blocks = get_unaligned_be64(&rec[8]); + + if (zone_blocks == 0) { + zone_blocks = this_zone_blocks; + } else if (this_zone_blocks != zone_blocks && + (block + this_zone_blocks < sdkp->capacity + || this_zone_blocks > zone_blocks)) { + this_zone_blocks = 0; goto out; } - block += zone_blocks; + block += this_zone_blocks; rec += 64; } @@ -467,8 +468,6 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) } while (block < sdkp->capacity); - zone_blocks = sdkp->zone_blocks; - out: if (!zone_blocks) { if (sdkp->first_scan) @@ -488,8 +487,7 @@ out: "Zone size too large\n"); ret = -ENODEV; } else { - sdkp->zone_blocks = zone_blocks; - sdkp->zone_shift = ilog2(zone_blocks); + ret = zone_blocks; } out_free: @@ -500,15 +498,14 @@ out_free: /** * sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone). - * @sdkp: The disk of the bitmap + * @nr_zones: Number of zones to allocate space for. + * @numa_node: NUMA node to allocate the memory from. */ -static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp) +static inline unsigned long * +sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node) { - struct request_queue *q = sdkp->disk->queue; - - return kzalloc_node(BITS_TO_LONGS(sdkp->nr_zones) - * sizeof(unsigned long), - GFP_KERNEL, q->node); + return kzalloc_node(BITS_TO_LONGS(nr_zones) * sizeof(unsigned long), + GFP_KERNEL, numa_node); } /** @@ -516,6 +513,7 @@ static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp) * @sdkp: disk used * @buf: report reply buffer * @buflen: length of @buf + * @zone_shift: logarithm base 2 of the number of blocks in a zone * @seq_zones_bitmap: bitmap of sequential zones to set * * Parse reported zone descriptors in @buf to identify sequential zones and @@ -525,7 +523,7 @@ static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp) * Return the LBA after the last zone reported. */ static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf, - unsigned int buflen, + unsigned int buflen, u32 zone_shift, unsigned long *seq_zones_bitmap) { sector_t lba, next_lba = sdkp->capacity; @@ -544,7 +542,7 @@ static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf, if (type != ZBC_ZONE_TYPE_CONV && cond != ZBC_ZONE_COND_READONLY && cond != ZBC_ZONE_COND_OFFLINE) - set_bit(lba >> sdkp->zone_shift, seq_zones_bitmap); + set_bit(lba >> zone_shift, seq_zones_bitmap); next_lba = lba + get_unaligned_be64(&rec[8]); rec += 64; } @@ -553,12 +551,16 @@ static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf, } /** - * sd_zbc_setup_seq_zones_bitmap - Initialize the disk seq zone bitmap. + * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap. * @sdkp: target disk + * @zone_shift: logarithm base 2 of the number of blocks in a zone + * @nr_zones: number of zones to set up a seq zone bitmap for * * Allocate a zone bitmap and initialize it by identifying sequential zones. */ -static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp) +static unsigned long * +sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift, + u32 nr_zones) { struct request_queue *q = sdkp->disk->queue; unsigned long *seq_zones_bitmap; @@ -566,9 +568,9 @@ static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp) unsigned char *buf; int ret = -ENOMEM; - seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(sdkp); + seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node); if (!seq_zones_bitmap) - return -ENOMEM; + return ERR_PTR(-ENOMEM); buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL); if (!buf) @@ -579,7 +581,7 @@ static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp) if (ret) goto out; lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE, - seq_zones_bitmap); + zone_shift, seq_zones_bitmap); } if (lba != sdkp->capacity) { @@ -591,12 +593,9 @@ out: kfree(buf); if (ret) { kfree(seq_zones_bitmap); - return ret; + return ERR_PTR(ret); } - - q->seq_zones_bitmap = seq_zones_bitmap; - - return 0; + return seq_zones_bitmap; } static void sd_zbc_cleanup(struct scsi_disk *sdkp) @@ -612,44 +611,64 @@ static void sd_zbc_cleanup(struct scsi_disk *sdkp) q->nr_zones = 0; } -static int sd_zbc_setup(struct scsi_disk *sdkp) +static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks) { struct request_queue *q = sdkp->disk->queue; + u32 zone_shift = ilog2(zone_blocks); + u32 nr_zones; int ret; - /* READ16/WRITE16 is mandatory for ZBC disks */ - sdkp->device->use_16_for_rw = 1; - sdkp->device->use_10_for_rw = 0; - /* chunk_sectors indicates the zone size */ - blk_queue_chunk_sectors(sdkp->disk->queue, - logical_to_sectors(sdkp->device, sdkp->zone_blocks)); - sdkp->nr_zones = - round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift; + blk_queue_chunk_sectors(q, + logical_to_sectors(sdkp->device, zone_blocks)); + nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift; /* * Initialize the device request queue information if the number * of zones changed. */ - if (sdkp->nr_zones != q->nr_zones) { - - sd_zbc_cleanup(sdkp); - - q->nr_zones = sdkp->nr_zones; - if (sdkp->nr_zones) { - q->seq_zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp); - if (!q->seq_zones_wlock) { + if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) { + unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; + size_t zone_bitmap_size; + + if (nr_zones) { + seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones, + q->node); + if (!seq_zones_wlock) { ret = -ENOMEM; goto err; } - ret = sd_zbc_setup_seq_zones_bitmap(sdkp); - if (ret) { - sd_zbc_cleanup(sdkp); + seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp, + zone_shift, nr_zones); + if (IS_ERR(seq_zones_bitmap)) { + ret = PTR_ERR(seq_zones_bitmap); + kfree(seq_zones_wlock); goto err; } } - + zone_bitmap_size = BITS_TO_LONGS(nr_zones) * + sizeof(unsigned long); + blk_mq_freeze_queue(q); + if (q->nr_zones != nr_zones) { + /* READ16/WRITE16 is mandatory for ZBC disks */ + sdkp->device->use_16_for_rw = 1; + sdkp->device->use_10_for_rw = 0; + + sdkp->zone_blocks = zone_blocks; + sdkp->zone_shift = zone_shift; + sdkp->nr_zones = nr_zones; + q->nr_zones = nr_zones; + swap(q->seq_zones_wlock, seq_zones_wlock); + swap(q->seq_zones_bitmap, seq_zones_bitmap); + } else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap, + zone_bitmap_size) != 0) { + memcpy(q->seq_zones_bitmap, seq_zones_bitmap, + zone_bitmap_size); + } + blk_mq_unfreeze_queue(q); + kfree(seq_zones_wlock); + kfree(seq_zones_bitmap); } return 0; @@ -661,6 +680,7 @@ err: int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) { + int64_t zone_blocks; int ret; if (!sd_is_zoned(sdkp)) @@ -697,12 +717,16 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) * Check zone size: only devices with a constant zone size (except * an eventual last runt zone) that is a power of 2 are supported. */ - ret = sd_zbc_check_zone_size(sdkp); - if (ret) + zone_blocks = sd_zbc_check_zone_size(sdkp); + ret = -EFBIG; + if (zone_blocks != (u32)zone_blocks) + goto err; + ret = zone_blocks; + if (ret < 0) goto err; /* The drive satisfies the kernel restrictions: set it up */ - ret = sd_zbc_setup(sdkp); + ret = sd_zbc_setup(sdkp, zone_blocks); if (ret) goto err; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9af3e0f430bc..21e21f273a21 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -605,6 +605,11 @@ struct request_queue { * initialized by the low level device driver (e.g. scsi/sd.c). * Stacking drivers (device mappers) may or may not initialize * these fields. + * + * Reads of this information must be protected with blk_queue_enter() / + * blk_queue_exit(). Modifying this information is only allowed while + * no requests are being processed. See also blk_mq_freeze_queue() and + * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; unsigned long *seq_zones_bitmap; -- cgit v1.3-18-gd494 From ed4564babeeee4fb19fe4ec0beabe29754e380f9 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Sun, 8 Apr 2018 23:57:07 +0200 Subject: drivers: change struct device_driver::coredump() return type to void Upon submitting a patch for mwifiex [1] it was discussed whether this callback function could fail. To keep things simple there is no need for the error code so the driver can do the task synchronous or not without worries. Currently the device driver core already ignores the return value so changing it to void. [1] https://patchwork.kernel.org/patch/10231933/ Signed-off-by: Arend van Spriel Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 0059b99e1f25..477956990f5e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -256,7 +256,9 @@ enum probe_type { * automatically. * @pm: Power management operations of the device which matched * this driver. - * @coredump: Called through sysfs to initiate a device coredump. + * @coredump: Called when sysfs entry is written to. The device driver + * is expected to call the dev_coredump API resulting in a + * uevent. * @p: Driver core's private data, no one other than the driver * core can touch this. * @@ -288,7 +290,7 @@ struct device_driver { const struct attribute_group **groups; const struct dev_pm_ops *pm; - int (*coredump) (struct device *dev); + void (*coredump) (struct device *dev); struct driver_private *p; }; -- cgit v1.3-18-gd494 From 1cdae042fc63dd987f39ffb3258e54fdac8b9852 Mon Sep 17 00:00:00 2001 From: Ahbong Chang Date: Mon, 16 Apr 2018 10:36:25 +0800 Subject: tracing: Add missing forward declaration Without this forward declaration compile may fail if this header is included only for registering other probe event without struct pool_workqueue. Link: http://lkml.kernel.org/r/20180416023626.139915-1-cwahbong@google.com Reviewed-by: Todd Poynor Signed-off-by: Ahbong Chang Signed-off-by: Steven Rostedt (VMware) --- include/trace/events/workqueue.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 2f057a494d93..9a761bc6a251 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -25,6 +25,8 @@ DECLARE_EVENT_CLASS(workqueue_work, TP_printk("work struct %p", __entry->work) ); +struct pool_workqueue; + /** * workqueue_queue_work - called when a work gets queued * @req_cpu: the requested cpu -- cgit v1.3-18-gd494 From d90a10e2444ba5a351fa695917258ff4c5709fa5 Mon Sep 17 00:00:00 2001 From: Robert Kolchmeyer Date: Thu, 19 Apr 2018 10:44:33 -0700 Subject: fsnotify: Fix fsnotify_mark_connector race fsnotify() acquires a reference to a fsnotify_mark_connector through the SRCU-protected pointer to_tell->i_fsnotify_marks. However, it appears that no precautions are taken in fsnotify_put_mark() to ensure that fsnotify() drops its reference to this fsnotify_mark_connector before assigning a value to its 'destroy_next' field. This can result in fsnotify_put_mark() assigning a value to a connector's 'destroy_next' field right before fsnotify() tries to traverse the linked list referenced by the connector's 'list' field. Since these two fields are members of the same union, this behavior results in a kernel panic. This issue is resolved by moving the connector's 'destroy_next' field into the object pointer union. This should work since the object pointer access is protected by both a spinlock and the value of the 'flags' field, and the 'flags' field is cleared while holding the spinlock in fsnotify_put_mark() before 'destroy_next' is updated. It shouldn't be possible for another thread to accidentally read from the object pointer after the 'destroy_next' field is updated. The offending behavior here is extremely unlikely; since fsnotify_put_mark() removes references to a connector (specifically, it ensures that the connector is unreachable from the inode it was formerly attached to) before updating its 'destroy_next' field, a sizeable chunk of code in fsnotify_put_mark() has to execute in the short window between when fsnotify() acquires the connector reference and saves the value of its 'list' field. On the HEAD kernel, I've only been able to reproduce this by inserting a udelay(1) in fsnotify(). However, I've been able to reproduce this issue without inserting a udelay(1) anywhere on older unmodified release kernels, so I believe it's worth fixing at HEAD. References: https://bugzilla.kernel.org/show_bug.cgi?id=199437 Fixes: 08991e83b7286635167bab40927665a90fb00d81 CC: stable@vger.kernel.org Signed-off-by: Robert Kolchmeyer Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 9f1edb92c97e..a3d13d874fd1 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -217,12 +217,10 @@ struct fsnotify_mark_connector { union { /* Object pointer [lock] */ struct inode *inode; struct vfsmount *mnt; - }; - union { - struct hlist_head list; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; + struct hlist_head list; }; /* -- cgit v1.3-18-gd494 From 85bd0ba1ff9875798fad94218b627ea9f768f3c3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 21 Jan 2018 16:42:56 +0000 Subject: arm/arm64: KVM: Add PSCI version selection API Although we've implemented PSCI 0.1, 0.2 and 1.0, we expose either 0.1 or 1.0 to a guest, defaulting to the latest version of the PSCI implementation that is compatible with the requested version. This is no different from doing a firmware upgrade on KVM. But in order to give a chance to hypothetical badly implemented guests that would have a fit by discovering something other than PSCI 0.2, let's provide a new API that allows userspace to pick one particular version of the API. This is implemented as a new class of "firmware" registers, where we expose the PSCI version. This allows the PSCI version to be save/restored as part of a guest migration, and also set to any supported version if the guest requires it. Cc: stable@vger.kernel.org #4.16 Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- Documentation/virtual/kvm/api.txt | 9 ++++- Documentation/virtual/kvm/arm/psci.txt | 30 +++++++++++++++++ arch/arm/include/asm/kvm_host.h | 3 ++ arch/arm/include/uapi/asm/kvm.h | 6 ++++ arch/arm/kvm/guest.c | 13 ++++++++ arch/arm64/include/asm/kvm_host.h | 3 ++ arch/arm64/include/uapi/asm/kvm.h | 6 ++++ arch/arm64/kvm/guest.c | 14 +++++++- include/kvm/arm_psci.h | 16 +++++++-- virt/kvm/arm/psci.c | 60 ++++++++++++++++++++++++++++++++++ 10 files changed, 156 insertions(+), 4 deletions(-) create mode 100644 Documentation/virtual/kvm/arm/psci.txt (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 1c7958b57fe9..758bf403a169 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1960,6 +1960,9 @@ ARM 32-bit VFP control registers have the following id bit patterns: ARM 64-bit FP registers have the following id bit patterns: 0x4030 0000 0012 0 +ARM firmware pseudo-registers have the following bit pattern: + 0x4030 0000 0014 + arm64 registers are mapped using the lower 32 bits. The upper 16 of that is the register group type, or coprocessor number: @@ -1976,6 +1979,9 @@ arm64 CCSIDR registers are demultiplexed by CSSELR value: arm64 system registers have the following id bit patterns: 0x6030 0000 0013 +arm64 firmware pseudo-registers have the following bit pattern: + 0x6030 0000 0014 + MIPS registers are mapped using the lower 32 bits. The upper 16 of that is the register group type: @@ -2510,7 +2516,8 @@ Possible features: and execute guest code when KVM_RUN is called. - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode. Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only). - - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU. + - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision + backward compatible with v0.2) for the CPU. Depends on KVM_CAP_ARM_PSCI_0_2. - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU. Depends on KVM_CAP_ARM_PMU_V3. diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virtual/kvm/arm/psci.txt new file mode 100644 index 000000000000..aafdab887b04 --- /dev/null +++ b/Documentation/virtual/kvm/arm/psci.txt @@ -0,0 +1,30 @@ +KVM implements the PSCI (Power State Coordination Interface) +specification in order to provide services such as CPU on/off, reset +and power-off to the guest. + +The PSCI specification is regularly updated to provide new features, +and KVM implements these updates if they make sense from a virtualization +point of view. + +This means that a guest booted on two different versions of KVM can +observe two different "firmware" revisions. This could cause issues if +a given guest is tied to a particular PSCI revision (unlikely), or if +a migration causes a different PSCI version to be exposed out of the +blue to an unsuspecting guest. + +In order to remedy this situation, KVM exposes a set of "firmware +pseudo-registers" that can be manipulated using the GET/SET_ONE_REG +interface. These registers can be saved/restored by userspace, and set +to a convenient value if required. + +The following register is defined: + +* KVM_REG_ARM_PSCI_VERSION: + + - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set + (and thus has already been initialized) + - Returns the current PSCI version on GET_ONE_REG (defaulting to the + highest PSCI version implemented by KVM and compatible with v0.2) + - Allows any PSCI version implemented by KVM and compatible with + v0.2 to be set with SET_ONE_REG + - Affects the whole VM (even if the register view is per-vcpu) diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c6a749568dd6..c7c28c885a19 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -77,6 +77,9 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; int max_vcpus; + + /* Mandated version of PSCI */ + u32 psci_version; }; #define KVM_NR_MEM_OBJS 40 diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 2ba95d6fe852..caae4843cb70 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -195,6 +195,12 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_VFP_FPINST 0x1009 #define KVM_REG_ARM_VFP_FPINST2 0x100A +/* KVM-as-firmware specific pseudo-registers */ +#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW | ((r) & 0xffff)) +#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 1e0784ebbfd6..a18f33edc471 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -176,6 +177,7 @@ static unsigned long num_core_regs(void) unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) { return num_core_regs() + kvm_arm_num_coproc_regs(vcpu) + + kvm_arm_get_fw_num_regs(vcpu) + NUM_TIMER_REGS; } @@ -196,6 +198,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) uindices++; } + ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); + if (ret) + return ret; + uindices += kvm_arm_get_fw_num_regs(vcpu); + ret = copy_timer_indices(vcpu, uindices); if (ret) return ret; @@ -214,6 +221,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return get_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_get_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return get_timer_reg(vcpu, reg); @@ -230,6 +240,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return set_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_set_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return set_timer_reg(vcpu, reg); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index ab46bc70add6..469de8acd06f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -75,6 +75,9 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; + + /* Mandated version of PSCI */ + u32 psci_version; }; #define KVM_NR_MEM_OBJS 40 diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 9abbf3044654..04b3256f8e6d 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -206,6 +206,12 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +/* KVM-as-firmware specific pseudo-registers */ +#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW | ((r) & 0xffff)) +#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 959e50d2588c..56a0260ceb11 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -205,7 +206,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) { return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu) - + NUM_TIMER_REGS; + + kvm_arm_get_fw_num_regs(vcpu) + NUM_TIMER_REGS; } /** @@ -225,6 +226,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) uindices++; } + ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); + if (ret) + return ret; + uindices += kvm_arm_get_fw_num_regs(vcpu); + ret = copy_timer_indices(vcpu, uindices); if (ret) return ret; @@ -243,6 +249,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return get_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_get_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return get_timer_reg(vcpu, reg); @@ -259,6 +268,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return set_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_set_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return set_timer_reg(vcpu, reg); diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index e518e4e3dfb5..4b1548129fa2 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -37,10 +37,15 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm) * Our PSCI implementation stays the same across versions from * v0.2 onward, only adding the few mandatory functions (such * as FEATURES with 1.0) that are required by newer - * revisions. It is thus safe to return the latest. + * revisions. It is thus safe to return the latest, unless + * userspace has instructed us otherwise. */ - if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) + if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) { + if (vcpu->kvm->arch.psci_version) + return vcpu->kvm->arch.psci_version; + return KVM_ARM_PSCI_LATEST; + } return KVM_ARM_PSCI_0_1; } @@ -48,4 +53,11 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm) int kvm_hvc_call_handler(struct kvm_vcpu *vcpu); +struct kvm_one_reg; + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); + #endif /* __KVM_ARM_PSCI_H__ */ diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 6919352cbf15..c4762bef13c6 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -427,3 +428,62 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) smccc_set_retval(vcpu, val, 0, 0, 0); return 1; } + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) +{ + return 1; /* PSCI version */ +} + +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices)) + return -EFAULT; + + return 0; +} + +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + if (reg->id == KVM_REG_ARM_PSCI_VERSION) { + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + + val = kvm_psci_version(vcpu, vcpu->kvm); + if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; + } + + return -EINVAL; +} + +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + if (reg->id == KVM_REG_ARM_PSCI_VERSION) { + void __user *uaddr = (void __user *)(long)reg->addr; + bool wants_02; + u64 val; + + if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); + + switch (val) { + case KVM_ARM_PSCI_0_1: + if (wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + case KVM_ARM_PSCI_0_2: + case KVM_ARM_PSCI_1_0: + if (!wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + } + } + + return -EINVAL; +} -- cgit v1.3-18-gd494 From b905ef9ab90115d001c1658259af4b1c65088779 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 19 Apr 2018 12:25:38 -0700 Subject: llc: delete timers synchronously in llc_sk_free() The connection timers of an llc sock could be still flying after we delete them in llc_sk_free(), and even possibly after we free the sock. We could just wait synchronously here in case of troubles. Note, I leave other call paths as they are, since they may not have to wait, at least we can change them to synchronously when needed. Also, move the code to net/llc/llc_conn.c, which is apparently a better place. Reported-by: Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/llc_conn.h | 1 + net/llc/llc_c_ac.c | 9 +-------- net/llc/llc_conn.c | 22 +++++++++++++++++++++- 3 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index 5c40f118c0fa..df528a623548 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb) struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); +void llc_sk_stop_all_timers(struct sock *sk, bool sync); void llc_sk_free(struct sock *sk); void llc_sk_reset(struct sock *sk); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 163121192aca..4d78375f9872 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb) int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb) { - struct llc_sock *llc = llc_sk(sk); - - del_timer(&llc->pf_cycle_timer.timer); - del_timer(&llc->ack_timer.timer); - del_timer(&llc->rej_sent_timer.timer); - del_timer(&llc->busy_state_timer.timer); - llc->ack_must_be_send = 0; - llc->ack_pf = 0; + llc_sk_stop_all_timers(sk, false); return 0; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 110e32bcb399..c0ac522b48a1 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -961,6 +961,26 @@ out: return sk; } +void llc_sk_stop_all_timers(struct sock *sk, bool sync) +{ + struct llc_sock *llc = llc_sk(sk); + + if (sync) { + del_timer_sync(&llc->pf_cycle_timer.timer); + del_timer_sync(&llc->ack_timer.timer); + del_timer_sync(&llc->rej_sent_timer.timer); + del_timer_sync(&llc->busy_state_timer.timer); + } else { + del_timer(&llc->pf_cycle_timer.timer); + del_timer(&llc->ack_timer.timer); + del_timer(&llc->rej_sent_timer.timer); + del_timer(&llc->busy_state_timer.timer); + } + + llc->ack_must_be_send = 0; + llc->ack_pf = 0; +} + /** * llc_sk_free - Frees a LLC socket * @sk - socket to free @@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk) llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ - llc_conn_ac_stop_all_timers(sk, NULL); + llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), -- cgit v1.3-18-gd494 From cc74eddd0ff325d57373cea99f642b787d7f76f5 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 20 Apr 2018 15:15:04 -0400 Subject: net: sched: ife: handle malformed tlv length There is currently no handling to check on a invalid tlv length. This patch adds such handling to avoid killing the kernel with a malformed ife packet. Signed-off-by: Alexander Aring Reviewed-by: Yotam Gigi Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/ife.h | 3 ++- net/ife/ife.c | 35 +++++++++++++++++++++++++++++++++-- net/sched/act_ife.c | 7 ++++++- 3 files changed, 41 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ife.h b/include/net/ife.h index 44b9c00f7223..e117617e3c34 100644 --- a/include/net/ife.h +++ b/include/net/ife.h @@ -12,7 +12,8 @@ void *ife_encode(struct sk_buff *skb, u16 metalen); void *ife_decode(struct sk_buff *skb, u16 *metalen); -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen); +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen); int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval); diff --git a/net/ife/ife.c b/net/ife/ife.c index 7d1ec76e7f43..7fbe70a0af4b 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -92,12 +92,43 @@ struct meta_tlvhdr { __be16 len; }; +static bool __ife_tlv_meta_valid(const unsigned char *skbdata, + const unsigned char *ifehdr_end) +{ + const struct meta_tlvhdr *tlv; + u16 tlvlen; + + if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end)) + return false; + + tlv = (const struct meta_tlvhdr *)skbdata; + tlvlen = ntohs(tlv->len); + + /* tlv length field is inc header, check on minimum */ + if (tlvlen < NLA_HDRLEN) + return false; + + /* overflow by NLA_ALIGN check */ + if (NLA_ALIGN(tlvlen) < tlvlen) + return false; + + if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end)) + return false; + + return true; +} + /* Caller takes care of presenting data in network order */ -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen) +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen) { - struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + struct meta_tlvhdr *tlv; + + if (!__ife_tlv_meta_valid(skbdata, ifehdr_end)) + return NULL; + tlv = (struct meta_tlvhdr *)skbdata; *dlen = ntohs(tlv->len) - NLA_HDRLEN; *attrtype = ntohs(tlv->type); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 49b8ab551fbe..8527cfdc446d 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u16 mtype; u16 dlen; - curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); + curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, + &dlen, NULL); + if (!curr_data) { + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); + return TC_ACT_SHOT; + } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata -- cgit v1.3-18-gd494 From dd709e72cb934eefd44de8d9969097173fbf45dc Mon Sep 17 00:00:00 2001 From: Daniel Kurtz Date: Fri, 6 Apr 2018 17:21:53 -0600 Subject: earlycon: Use a pointer table to fix __earlycon_table stride Commit 99492c39f39f ("earlycon: Fix __earlycon_table stride") tried to fix __earlycon_table stride by forcing the earlycon_id struct alignment to 32 and asking the linker to 32-byte align the __earlycon_table symbol. This fix was based on commit 07fca0e57fca92 ("tracing: Properly align linker defined symbols") which tried a similar fix for the tracing subsystem. However, this fix doesn't quite work because there is no guarantee that gcc will place structures packed into an array format. In fact, gcc 4.9 chooses to 64-byte align these structs by inserting additional padding between the entries because it has no clue that they are supposed to be in an array. If we are unlucky, the linker will assign symbol "__earlycon_table" to a 32-byte aligned address which does not correspond to the 64-byte aligned contents of section "__earlycon_table". To address this same problem, the fix to the tracing system was subsequently re-implemented using a more robust table of pointers approach by commits: 3d56e331b653 ("tracing: Replace syscall_meta_data struct array with pointer array") 654986462939 ("tracepoints: Fix section alignment using pointer array") e4a9ea5ee7c8 ("tracing: Replace trace_event struct array with pointer array") Let's use this same "array of pointers to structs" approach for EARLYCON_TABLE. Fixes: 99492c39f39f ("earlycon: Fix __earlycon_table stride") Signed-off-by: Daniel Kurtz Suggested-by: Aaron Durbin Reviewed-by: Rob Herring Tested-by: Guenter Roeck Reviewed-by: Guenter Roeck Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/of/fdt.c | 7 +++++-- drivers/tty/serial/earlycon.c | 6 ++++-- include/asm-generic/vmlinux.lds.h | 2 +- include/linux/serial_core.h | 21 ++++++++++++++------- 4 files changed, 24 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 84aa9d676375..6da20b9688f7 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -942,7 +942,7 @@ int __init early_init_dt_scan_chosen_stdout(void) int offset; const char *p, *q, *options = NULL; int l; - const struct earlycon_id *match; + const struct earlycon_id **p_match; const void *fdt = initial_boot_params; offset = fdt_path_offset(fdt, "/chosen"); @@ -969,7 +969,10 @@ int __init early_init_dt_scan_chosen_stdout(void) return 0; } - for (match = __earlycon_table; match < __earlycon_table_end; match++) { + for (p_match = __earlycon_table; p_match < __earlycon_table_end; + p_match++) { + const struct earlycon_id *match = *p_match; + if (!match->compatible[0]) continue; diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c index a24278380fec..22683393a0f2 100644 --- a/drivers/tty/serial/earlycon.c +++ b/drivers/tty/serial/earlycon.c @@ -169,7 +169,7 @@ static int __init register_earlycon(char *buf, const struct earlycon_id *match) */ int __init setup_earlycon(char *buf) { - const struct earlycon_id *match; + const struct earlycon_id **p_match; if (!buf || !buf[0]) return -EINVAL; @@ -177,7 +177,9 @@ int __init setup_earlycon(char *buf) if (early_con.flags & CON_ENABLED) return -EALREADY; - for (match = __earlycon_table; match < __earlycon_table_end; match++) { + for (p_match = __earlycon_table; p_match < __earlycon_table_end; + p_match++) { + const struct earlycon_id *match = *p_match; size_t len = strlen(match->name); if (strncmp(buf, match->name, len)) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 278841c75b97..af240573e482 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -188,7 +188,7 @@ #endif #ifdef CONFIG_SERIAL_EARLYCON -#define EARLYCON_TABLE() STRUCT_ALIGN(); \ +#define EARLYCON_TABLE() . = ALIGN(8); \ VMLINUX_SYMBOL(__earlycon_table) = .; \ KEEP(*(__earlycon_table)) \ VMLINUX_SYMBOL(__earlycon_table_end) = .; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 1d356105f25a..b4c9fda9d833 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -351,10 +351,10 @@ struct earlycon_id { char name[16]; char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); -} __aligned(32); +}; -extern const struct earlycon_id __earlycon_table[]; -extern const struct earlycon_id __earlycon_table_end[]; +extern const struct earlycon_id *__earlycon_table[]; +extern const struct earlycon_id *__earlycon_table_end[]; #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE) #define EARLYCON_USED_OR_UNUSED __used @@ -362,12 +362,19 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_USED_OR_UNUSED __maybe_unused #endif -#define OF_EARLYCON_DECLARE(_name, compat, fn) \ - static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \ - EARLYCON_USED_OR_UNUSED __section(__earlycon_table) \ +#define _OF_EARLYCON_DECLARE(_name, compat, fn, unique_id) \ + static const struct earlycon_id unique_id \ + EARLYCON_USED_OR_UNUSED __initconst \ = { .name = __stringify(_name), \ .compatible = compat, \ - .setup = fn } + .setup = fn }; \ + static const struct earlycon_id EARLYCON_USED_OR_UNUSED \ + __section(__earlycon_table) \ + * const __PASTE(__p, unique_id) = &unique_id + +#define OF_EARLYCON_DECLARE(_name, compat, fn) \ + _OF_EARLYCON_DECLARE(_name, compat, fn, \ + __UNIQUE_ID(__earlycon_##_name)) #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) -- cgit v1.3-18-gd494 From 903f9db10f18f735e62ba447147b6c434b6af003 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 5 Apr 2018 19:40:16 +0900 Subject: tty: Don't call panic() at tty_ldisc_init() syzbot is reporting kernel panic [1] triggered by memory allocation failure at tty_ldisc_get() from tty_ldisc_init(). But since both tty_ldisc_get() and caller of tty_ldisc_init() can cleanly handle errors, tty_ldisc_init() does not need to call panic() when tty_ldisc_get() failed. [1] https://syzkaller.appspot.com/bug?id=883431818e036ae6a9981156a64b821110f39187 Signed-off-by: Tetsuo Handa Reported-by: syzbot Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 5 ++++- drivers/tty/tty_ldisc.c | 5 +++-- include/linux/tty.h | 2 +- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 63114ea35ec1..7c838b90a31d 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2816,7 +2816,10 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx) kref_init(&tty->kref); tty->magic = TTY_MAGIC; - tty_ldisc_init(tty); + if (tty_ldisc_init(tty)) { + kfree(tty); + return NULL; + } tty->session = NULL; tty->pgrp = NULL; mutex_init(&tty->legacy_mutex); diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index c1cf6cb83185..8a88a7787cfe 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -821,12 +821,13 @@ EXPORT_SYMBOL_GPL(tty_ldisc_release); * the tty structure is not completely set up when this call is made. */ -void tty_ldisc_init(struct tty_struct *tty) +int tty_ldisc_init(struct tty_struct *tty) { struct tty_ldisc *ld = tty_ldisc_get(tty, N_TTY); if (IS_ERR(ld)) - panic("n_tty: init_tty"); + return PTR_ERR(ld); tty->ldisc = ld; + return 0; } /** diff --git a/include/linux/tty.h b/include/linux/tty.h index 47f8af22f216..1dd587ba6d88 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -701,7 +701,7 @@ extern int tty_unregister_ldisc(int disc); extern int tty_set_ldisc(struct tty_struct *tty, int disc); extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty); extern void tty_ldisc_release(struct tty_struct *tty); -extern void tty_ldisc_init(struct tty_struct *tty); +extern int __must_check tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, char *f, int count); -- cgit v1.3-18-gd494 From 02cfde67df1f440c7c3c7038cc97992afb81804f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 18 Apr 2018 15:24:47 +0200 Subject: virt: vbox: Move declarations of vboxguest private functions to private header Move the declarations of functions from vboxguest_utils.c which are only meant for vboxguest internal use from include/linux/vbox_utils.h to drivers/virt/vboxguest/vboxguest_core.h. Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/virt/vboxguest/vboxguest_core.h | 8 ++++++++ include/linux/vbox_utils.h | 23 ----------------------- 2 files changed, 8 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h index 6c784bf4fa6d..39ed85cf9244 100644 --- a/drivers/virt/vboxguest/vboxguest_core.h +++ b/drivers/virt/vboxguest/vboxguest_core.h @@ -171,4 +171,12 @@ irqreturn_t vbg_core_isr(int irq, void *dev_id); void vbg_linux_mouse_event(struct vbg_dev *gdev); +/* Private (non exported) functions form vboxguest_utils.c */ +void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type); +int vbg_req_perform(struct vbg_dev *gdev, void *req); +int vbg_hgcm_call32( + struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms, + struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count, + int *vbox_status); + #endif diff --git a/include/linux/vbox_utils.h b/include/linux/vbox_utils.h index c71def6b310f..a240ed2a0372 100644 --- a/include/linux/vbox_utils.h +++ b/include/linux/vbox_utils.h @@ -24,24 +24,6 @@ __printf(1, 2) void vbg_debug(const char *fmt, ...); #define vbg_debug pr_debug #endif -/** - * Allocate memory for generic request and initialize the request header. - * - * Return: the allocated memory - * @len: Size of memory block required for the request. - * @req_type: The generic request type. - */ -void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type); - -/** - * Perform a generic request. - * - * Return: VBox status code - * @gdev: The Guest extension device. - * @req: Pointer to the request structure. - */ -int vbg_req_perform(struct vbg_dev *gdev, void *req); - int vbg_hgcm_connect(struct vbg_dev *gdev, struct vmmdev_hgcm_service_location *loc, u32 *client_id, int *vbox_status); @@ -52,11 +34,6 @@ int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms, u32 parm_count, int *vbox_status); -int vbg_hgcm_call32( - struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms, - struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count, - int *vbox_status); - /** * Convert a VirtualBox status code to a standard Linux kernel return value. * Return: 0 or negative errno value. -- cgit v1.3-18-gd494 From 6510bbc88e3258631831ade49033537081950605 Mon Sep 17 00:00:00 2001 From: Joakim Tjernlund Date: Thu, 1 Mar 2018 14:39:39 +0100 Subject: mtd: cfi: cmdset_0001: Do not allow read/write to suspend erase block. Currently it is possible to read and/or write to suspend EB's. Writing /dev/mtdX or /dev/mtdblockX from several processes may break the flash state machine. Signed-off-by: Joakim Tjernlund Cc: Reviewed-by: Richard Weinberger Signed-off-by: Boris Brezillon --- drivers/mtd/chips/cfi_cmdset_0001.c | 16 +++++++++++----- include/linux/mtd/flashchip.h | 1 + 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c index d4c07b85f18e..8833115fbc11 100644 --- a/drivers/mtd/chips/cfi_cmdset_0001.c +++ b/drivers/mtd/chips/cfi_cmdset_0001.c @@ -831,21 +831,25 @@ static int chip_ready (struct map_info *map, struct flchip *chip, unsigned long (mode == FL_WRITING && (cfip->SuspendCmdSupport & 1)))) goto sleep; + /* Do not allow suspend iff read/write to EB address */ + if ((adr & chip->in_progress_block_mask) == + chip->in_progress_block_addr) + goto sleep; /* Erase suspend */ - map_write(map, CMD(0xB0), adr); + map_write(map, CMD(0xB0), chip->in_progress_block_addr); /* If the flash has finished erasing, then 'erase suspend' * appears to make some (28F320) flash devices switch to * 'read' mode. Make sure that we switch to 'read status' * mode so we get the right data. --rmk */ - map_write(map, CMD(0x70), adr); + map_write(map, CMD(0x70), chip->in_progress_block_addr); chip->oldstate = FL_ERASING; chip->state = FL_ERASE_SUSPENDING; chip->erase_suspended = 1; for (;;) { - status = map_read(map, adr); + status = map_read(map, chip->in_progress_block_addr); if (map_word_andequal(map, status, status_OK, status_OK)) break; @@ -1041,8 +1045,8 @@ static void put_chip(struct map_info *map, struct flchip *chip, unsigned long ad sending the 0x70 (Read Status) command to an erasing chip and expecting it to be ignored, that's what we do. */ - map_write(map, CMD(0xd0), adr); - map_write(map, CMD(0x70), adr); + map_write(map, CMD(0xd0), chip->in_progress_block_addr); + map_write(map, CMD(0x70), chip->in_progress_block_addr); chip->oldstate = FL_READY; chip->state = FL_ERASING; break; @@ -1933,6 +1937,8 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip, map_write(map, CMD(0xD0), adr); chip->state = FL_ERASING; chip->erase_suspended = 0; + chip->in_progress_block_addr = adr; + chip->in_progress_block_mask = ~(len - 1); ret = INVAL_CACHE_AND_WAIT(map, chip, adr, adr, len, diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index b63fa457febd..3529683f691e 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -85,6 +85,7 @@ struct flchip { unsigned int write_suspended:1; unsigned int erase_suspended:1; unsigned long in_progress_block_addr; + unsigned long in_progress_block_mask; struct mutex mutex; wait_queue_head_t wq; /* Wait on here when we're waiting for the chip -- cgit v1.3-18-gd494 From d805c5209350ae725e3a1ee0204ba27d9e75ce3e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 23 Apr 2018 15:51:38 -0700 Subject: net: ethtool: Add missing kernel doc for FEC parameters While adding support for ethtool::get_fecparam and set_fecparam, kernel doc for these functions was missed, add those. Fixes: 1a5f3da20bd9 ("net: ethtool: add support for forward error correction modes") Signed-off-by: Florian Fainelli Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/ethtool.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index ebe41811ed34..b32cd2062f18 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -310,6 +310,8 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS * instead of the latter), any change to them will be overwritten * by kernel. Returns a negative error code or zero. + * @get_fecparam: Get the network device Forward Error Correction parameters. + * @set_fecparam: Set the network device Forward Error Correction parameters. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must -- cgit v1.3-18-gd494 From b40000325044433cd350725e2025214ae48b17fd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 13 Apr 2018 16:37:04 +0300 Subject: virtio_balloon: add array of stat names Jason Wang points out that it's very hard for users to build an array of stat names. The naive thing is to use VIRTIO_BALLOON_S_NR but that breaks if we add more stats - as done e.g. recently by commit 6c64fe7f2 ("virtio_balloon: export hugetlb page allocation counts"). Let's add an array of reasonably readable names. Fixes: 6c64fe7f2 ("virtio_balloon: export hugetlb page allocation counts") Cc: Jason Wang Signed-off-by: Michael S. Tsirkin Reviewed-by: Jonathan Helman --- include/uapi/linux/virtio_balloon.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index 40297a3181ed..13b8cb563892 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -57,6 +57,21 @@ struct virtio_balloon_config { #define VIRTIO_BALLOON_S_HTLB_PGFAIL 9 /* Hugetlb page allocation failures */ #define VIRTIO_BALLOON_S_NR 10 +#define VIRTIO_BALLOON_S_NAMES_WITH_PREFIX(VIRTIO_BALLOON_S_NAMES_prefix) { \ + VIRTIO_BALLOON_S_NAMES_prefix "swap-in", \ + VIRTIO_BALLOON_S_NAMES_prefix "swap-out", \ + VIRTIO_BALLOON_S_NAMES_prefix "major-faults", \ + VIRTIO_BALLOON_S_NAMES_prefix "minor-faults", \ + VIRTIO_BALLOON_S_NAMES_prefix "free-memory", \ + VIRTIO_BALLOON_S_NAMES_prefix "total-memory", \ + VIRTIO_BALLOON_S_NAMES_prefix "available-memory", \ + VIRTIO_BALLOON_S_NAMES_prefix "disk-caches", \ + VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-allocations", \ + VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures" \ +} + +#define VIRTIO_BALLOON_S_NAMES VIRTIO_BALLOON_S_NAMES_WITH_PREFIX("") + /* * Memory statistics structure. * Driver fills an array of these structures and passes to device. -- cgit v1.3-18-gd494 From 088e861edffb84879cf0c0d1b02eda078c3a0ffe Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 24 Apr 2018 07:45:56 +0200 Subject: ALSA: control: Hardening for potential Spectre v1 As recently Smatch suggested, a few places in ALSA control core codes may expand the array directly from the user-space value with speculation: sound/core/control.c:1003 snd_ctl_elem_lock() warn: potential spectre issue 'kctl->vd' sound/core/control.c:1031 snd_ctl_elem_unlock() warn: potential spectre issue 'kctl->vd' sound/core/control.c:844 snd_ctl_elem_info() warn: potential spectre issue 'kctl->vd' sound/core/control.c:891 snd_ctl_elem_read() warn: potential spectre issue 'kctl->vd' sound/core/control.c:939 snd_ctl_elem_write() warn: potential spectre issue 'kctl->vd' Although all these seem doing only the first load without further reference, we may want to stay in a safer side, so hardening with array_index_nospec() would still make sense. In this patch, we put array_index_nospec() to the common snd_ctl_get_ioff*() helpers instead of each caller. These helpers are also referred from some drivers, too, and basically all usages are to calculate the array index from the user-space value, hence it's better to cover there. BugLink: https://marc.info/?l=linux-kernel&m=152411496503418&w=2 Reported-by: Dan Carpenter Cc: Signed-off-by: Takashi Iwai --- include/sound/control.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/control.h b/include/sound/control.h index ca13a44ae9d4..6011a58d3e20 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -23,6 +23,7 @@ */ #include +#include #include #define snd_kcontrol_chip(kcontrol) ((kcontrol)->private_data) @@ -148,12 +149,14 @@ int snd_ctl_get_preferred_subdevice(struct snd_card *card, int type); static inline unsigned int snd_ctl_get_ioffnum(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id) { - return id->numid - kctl->id.numid; + unsigned int ioff = id->numid - kctl->id.numid; + return array_index_nospec(ioff, kctl->count); } static inline unsigned int snd_ctl_get_ioffidx(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id) { - return id->index - kctl->id.index; + unsigned int ioff = id->index - kctl->id.index; + return array_index_nospec(ioff, kctl->count); } static inline unsigned int snd_ctl_get_ioff(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id) -- cgit v1.3-18-gd494 From fe644072dfee069d97a66ea9a80f4bc461499e6a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 20 Apr 2018 10:29:51 +0200 Subject: block: mq: Add some minor doc for core structs As it came up in discussion on the mailing list that the semantic meaning of 'blk_mq_ctx' and 'blk_mq_hw_ctx' isn't completely obvious to everyone, let's add some minimal kerneldoc for a starter. Signed-off-by: Linus Walleij Signed-off-by: Jens Axboe --- block/blk-mq.h | 3 +++ include/linux/blk-mq.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/block/blk-mq.h b/block/blk-mq.h index 88c558f71819..89b5cd3a6c70 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -7,6 +7,9 @@ struct blk_mq_tag_set; +/** + * struct blk_mq_ctx - State for a software queue facing the submitting CPUs + */ struct blk_mq_ctx { struct { spinlock_t lock; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3986f4b3461..ebc34a5686dc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -9,6 +9,9 @@ struct blk_mq_tags; struct blk_flush_queue; +/** + * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device + */ struct blk_mq_hw_ctx { struct { spinlock_t lock; -- cgit v1.3-18-gd494 From 24a7e4d20783c0514850f24a5c41ede46ab058f0 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 20 Apr 2018 20:22:40 +0300 Subject: virtio: add ability to iterate over vqs For cleanup it's helpful to be able to simply scan all vqs and discard all data. Add an iterator to do that. Cc: stable@vger.kernel.org Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 988c7355bc22..fa1b5da2804e 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -157,6 +157,9 @@ int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif +#define virtio_device_for_each_vq(vdev, vq) \ + list_for_each_entry(vq, &vdev->vqs, list) + /** * virtio_driver - operations for a virtio I/O driver * @driver: underlying device driver (populate name and owner). -- cgit v1.3-18-gd494 From a3ed0e4393d6885b4af7ce84b437dc696490a530 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Apr 2018 15:33:38 +0200 Subject: Revert: Unify CLOCK_MONOTONIC and CLOCK_BOOTTIME Revert commits 92af4dcb4e1c ("tracing: Unify the "boot" and "mono" tracing clocks") 127bfa5f4342 ("hrtimer: Unify MONOTONIC and BOOTTIME clock behavior") 7250a4047aa6 ("posix-timers: Unify MONOTONIC and BOOTTIME clock behavior") d6c7270e913d ("timekeeping: Remove boot time specific code") f2d6fdbfd238 ("Input: Evdev - unify MONOTONIC and BOOTTIME clock behavior") d6ed449afdb3 ("timekeeping: Make the MONOTONIC clock behave like the BOOTTIME clock") 72199320d49d ("timekeeping: Add the new CLOCK_MONOTONIC_ACTIVE clock") As stated in the pull request for the unification of CLOCK_MONOTONIC and CLOCK_BOOTTIME, it was clear that we might have to revert the change. As reported by several folks systemd and other applications rely on the documented behaviour of CLOCK_MONOTONIC on Linux and break with the above changes. After resume daemons time out and other timeout related issues are observed. Rafael compiled this list: * systemd kills daemons on resume, after >WatchdogSec seconds of suspending (Genki Sky). [Verified that that's because systemd uses CLOCK_MONOTONIC and expects it to not include the suspend time.] * systemd-journald misbehaves after resume: systemd-journald[7266]: File /var/log/journal/016627c3c4784cd4812d4b7e96a34226/system.journal corrupted or uncleanly shut down, renaming and replacing. (Mike Galbraith). * NetworkManager reports "networking disabled" and networking is broken after resume 50% of the time (Pavel). [May be because of systemd.] * MATE desktop dims the display and starts the screensaver right after system resume (Pavel). * Full system hang during resume (me). [May be due to systemd or NM or both.] That happens on debian and open suse systems. It's sad, that these problems were neither catched in -next nor by those folks who expressed interest in this change. Reported-by: Rafael J. Wysocki Reported-by: Genki Sky , Reported-by: Pavel Machek Signed-off-by: Thomas Gleixner Cc: Dmitry Torokhov Cc: John Stultz Cc: Jonathan Corbet Cc: Kevin Easton Cc: Linus Torvalds Cc: Mark Salyzyn Cc: Michael Kerrisk Cc: Peter Zijlstra Cc: Petr Mladek Cc: Prarit Bhargava Cc: Sergey Senozhatsky Cc: Steven Rostedt --- Documentation/trace/ftrace.rst | 14 +++++-- drivers/input/evdev.c | 7 +++- include/linux/hrtimer.h | 2 + include/linux/timekeeper_internal.h | 2 - include/linux/timekeeping.h | 37 ++++++++++++------ include/uapi/linux/time.h | 1 - kernel/time/hrtimer.c | 16 +++++++- kernel/time/posix-stubs.c | 2 - kernel/time/posix-timers.c | 26 ++++++++----- kernel/time/tick-common.c | 15 ------- kernel/time/tick-internal.h | 6 --- kernel/time/tick-sched.c | 9 ----- kernel/time/timekeeping.c | 78 ++++++++++++++++++------------------- kernel/time/timekeeping.h | 1 + kernel/trace/trace.c | 2 +- 15 files changed, 114 insertions(+), 104 deletions(-) (limited to 'include') diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index e45f0786f3f9..67d9c38e95eb 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -461,9 +461,17 @@ of ftrace. Here is a list of some of the key files: and ticks at the same rate as the hardware clocksource. boot: - Same as mono. Used to be a separate clock which accounted - for the time spent in suspend while CLOCK_MONOTONIC did - not. + This is the boot clock (CLOCK_BOOTTIME) and is based on the + fast monotonic clock, but also accounts for time spent in + suspend. Since the clock access is designed for use in + tracing in the suspend path, some side effects are possible + if clock is accessed after the suspend time is accounted before + the fast mono clock is updated. In this case, the clock update + appears to happen slightly sooner than it normally would have. + Also on 32-bit systems, it's possible that the 64-bit boot offset + sees a partial update. These effects are rare and post + processing should be able to handle them. See comments in the + ktime_get_boot_fast_ns() function for more information. To set a clock, simply echo the clock name into this file:: diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 46115a392098..c81c79d01d93 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -31,6 +31,7 @@ enum evdev_clock_type { EV_CLK_REAL = 0, EV_CLK_MONO, + EV_CLK_BOOT, EV_CLK_MAX }; @@ -197,10 +198,12 @@ static int evdev_set_clk_type(struct evdev_client *client, unsigned int clkid) case CLOCK_REALTIME: clk_type = EV_CLK_REAL; break; - case CLOCK_BOOTTIME: case CLOCK_MONOTONIC: clk_type = EV_CLK_MONO; break; + case CLOCK_BOOTTIME: + clk_type = EV_CLK_BOOT; + break; default: return -EINVAL; } @@ -311,6 +314,8 @@ static void evdev_events(struct input_handle *handle, ev_time[EV_CLK_MONO] = ktime_get(); ev_time[EV_CLK_REAL] = ktime_mono_to_real(ev_time[EV_CLK_MONO]); + ev_time[EV_CLK_BOOT] = ktime_mono_to_any(ev_time[EV_CLK_MONO], + TK_OFFS_BOOT); rcu_read_lock(); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index a2656c3ebe81..3892e9c8b2de 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -161,9 +161,11 @@ struct hrtimer_clock_base { enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, HRTIMER_BASE_REALTIME, + HRTIMER_BASE_BOOTTIME, HRTIMER_BASE_TAI, HRTIMER_BASE_MONOTONIC_SOFT, HRTIMER_BASE_REALTIME_SOFT, + HRTIMER_BASE_BOOTTIME_SOFT, HRTIMER_BASE_TAI_SOFT, HRTIMER_MAX_CLOCK_BASES, }; diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 4b3dca173e89..7acb953298a7 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -52,7 +52,6 @@ struct tk_read_base { * @offs_real: Offset clock monotonic -> clock realtime * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai - * @time_suspended: Accumulated suspend time * @tai_offset: The current UTC to TAI offset in seconds * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events @@ -95,7 +94,6 @@ struct timekeeper { ktime_t offs_real; ktime_t offs_boot; ktime_t offs_tai; - ktime_t time_suspended; s32 tai_offset; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 9737fbec7019..588a0e4b1ab9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -33,25 +33,20 @@ extern void ktime_get_ts64(struct timespec64 *ts); extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); -extern void ktime_get_active_ts64(struct timespec64 *ts); extern int __getnstimeofday64(struct timespec64 *tv); extern void getnstimeofday64(struct timespec64 *tv); extern void getboottime64(struct timespec64 *ts); -#define ktime_get_real_ts64(ts) getnstimeofday64(ts) - -/* Clock BOOTTIME compatibility wrappers */ -static inline void get_monotonic_boottime64(struct timespec64 *ts) -{ - ktime_get_ts64(ts); -} +#define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* * ktime_t based interfaces */ + enum tk_offsets { TK_OFFS_REAL, + TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; @@ -62,10 +57,6 @@ extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); -/* Clock BOOTTIME compatibility wrappers */ -static inline ktime_t ktime_get_boottime(void) { return ktime_get(); } -static inline u64 ktime_get_boot_ns(void) { return ktime_get(); } - /** * ktime_get_real - get the real (wall-) time in ktime_t format */ @@ -74,6 +65,17 @@ static inline ktime_t ktime_get_real(void) return ktime_get_with_offset(TK_OFFS_REAL); } +/** + * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * + * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the + * time spent in suspend. + */ +static inline ktime_t ktime_get_boottime(void) +{ + return ktime_get_with_offset(TK_OFFS_BOOT); +} + /** * ktime_get_clocktai - Returns the TAI time of day in ktime_t format */ @@ -100,6 +102,11 @@ static inline u64 ktime_get_real_ns(void) return ktime_to_ns(ktime_get_real()); } +static inline u64 ktime_get_boot_ns(void) +{ + return ktime_to_ns(ktime_get_boottime()); +} + static inline u64 ktime_get_tai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); @@ -112,11 +119,17 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); +extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64 interfaces utilizing the ktime based ones */ +static inline void get_monotonic_boottime64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_boottime()); +} + static inline void timekeeping_clocktai64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 16a296612ba4..4c0338ea308a 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -73,7 +73,6 @@ struct __kernel_old_timeval { */ #define CLOCK_SGI_CYCLE 10 #define CLOCK_TAI 11 -#define CLOCK_MONOTONIC_ACTIVE 12 #define MAX_CLOCKS 16 #define CLOCKS_MASK (CLOCK_REALTIME | CLOCK_MONOTONIC) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index eda1210ce50f..14e858753d76 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -90,6 +90,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, @@ -105,6 +110,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME_SOFT, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, @@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, - [CLOCK_BOOTTIME] = HRTIMER_BASE_MONOTONIC, + [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; @@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, - offs_real, offs_tai); + offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; + base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index e0dbae98db9d..69a937c3cd81 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) case CLOCK_BOOTTIME: get_monotonic_boottime64(tp); break; - case CLOCK_MONOTONIC_ACTIVE: - ktime_get_active_ts64(tp); default: return -EINVAL; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index b6899b5060bd..10b7186d0638 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * return 0; } -static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) { - timekeeping_clocktai64(tp); + get_monotonic_boottime64(tp); return 0; } -static int posix_get_monotonic_active(clockid_t which_clock, - struct timespec64 *tp) +static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) { - ktime_get_active_ts64(tp); + timekeeping_clocktai64(tp); return 0; } @@ -1317,9 +1316,19 @@ static const struct k_clock clock_tai = { .timer_arm = common_hrtimer_arm, }; -static const struct k_clock clock_monotonic_active = { +static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_monotonic_active, + .clock_get = posix_get_boottime, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, }; static const struct k_clock * const posix_clocks[] = { @@ -1330,11 +1339,10 @@ static const struct k_clock * const posix_clocks[] = { [CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw, [CLOCK_REALTIME_COARSE] = &clock_realtime_coarse, [CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse, - [CLOCK_BOOTTIME] = &clock_monotonic, + [CLOCK_BOOTTIME] = &clock_boottime, [CLOCK_REALTIME_ALARM] = &alarm_clock, [CLOCK_BOOTTIME_ALARM] = &alarm_clock, [CLOCK_TAI] = &clock_tai, - [CLOCK_MONOTONIC_ACTIVE] = &clock_monotonic_active, }; static const struct k_clock *clockid_to_kclock(const clockid_t id) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 099572ca4a8f..49edc1c4f3e6 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -419,19 +419,6 @@ void tick_suspend_local(void) clockevents_shutdown(td->evtdev); } -static void tick_forward_next_period(void) -{ - ktime_t delta, now = ktime_get(); - u64 n; - - delta = ktime_sub(now, tick_next_period); - n = ktime_divns(delta, tick_period); - tick_next_period += n * tick_period; - if (tick_next_period < now) - tick_next_period += tick_period; - tick_sched_forward_next_period(); -} - /** * tick_resume_local - Resume the local tick device * @@ -444,8 +431,6 @@ void tick_resume_local(void) struct tick_device *td = this_cpu_ptr(&tick_cpu_device); bool broadcast = tick_resume_check_broadcast(); - tick_forward_next_period(); - clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 21efab7485ca..e277284c2831 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } #endif /* !(BROADCAST && ONESHOT) */ -#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) -extern void tick_sched_forward_next_period(void); -#else -static inline void tick_sched_forward_next_period(void) { } -#endif - /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d31bec177fa5..da9455a6b42b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -51,15 +51,6 @@ struct tick_sched *tick_get_tick_sched(int cpu) */ static ktime_t last_jiffies_update; -/* - * Called after resume. Make sure that jiffies are not fast forwarded due to - * clock monotonic being forwarded by the suspended time. - */ -void tick_sched_forward_next_period(void) -{ - last_jiffies_update = tick_next_period; -} - /* * Must be called with interrupts disabled ! */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index dcf7f20fcd12..49cbceef5deb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - /* Update both bases so mono and raw stay coupled. */ - tk->tkr_mono.base += delta; - tk->tkr_raw.base += delta; - - /* Accumulate time spent in suspend */ - tk->time_suspended += delta; + tk->offs_boot = ktime_add(tk->offs_boot, delta); } /* @@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); +/** + * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. + * + * To keep it NMI safe since we're accessing from tracing, we're not using a + * separate timekeeper with updates to monotonic clock and boot offset + * protected with seqlocks. This has the following minor side effects: + * + * (1) Its possible that a timestamp be taken after the boot offset is updated + * but before the timekeeper is updated. If this happens, the new boot offset + * is added to the old timekeeping making the clock appear to update slightly + * earlier: + * CPU 0 CPU 1 + * timekeeping_inject_sleeptime64() + * __timekeeping_inject_sleeptime(tk, delta); + * timestamp(); + * timekeeping_update(tk, TK_CLEAR_NTP...); + * + * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be + * partially updated. Since the tk->offs_boot update is a rare event, this + * should be a rare occurrence which postprocessing should be able to handle. + */ +u64 notrace ktime_get_boot_fast_ns(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); +} +EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); + + /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ @@ -764,6 +789,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; @@ -860,39 +886,6 @@ void ktime_get_ts64(struct timespec64 *ts) } EXPORT_SYMBOL_GPL(ktime_get_ts64); -/** - * ktime_get_active_ts64 - Get the active non-suspended monotonic clock - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime clock and - * the wall_to_monotonic offset, subtracts the accumulated suspend time and - * stores the result in normalized timespec64 format in the variable - * pointed to by @ts. - */ -void ktime_get_active_ts64(struct timespec64 *ts) -{ - struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 tomono, tsusp; - u64 nsec, nssusp; - unsigned int seq; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&tk_core.seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(&tk->tkr_mono); - tomono = tk->wall_to_monotonic; - nssusp = tk->time_suspended; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - ts->tv_sec += tomono.tv_sec; - ts->tv_nsec = 0; - timespec64_add_ns(ts, nsec + tomono.tv_nsec); - tsusp = ns_to_timespec64(nssusp); - *ts = timespec64_sub(*ts, tsusp); -} - /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * @@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, return; } tk_xtime_add(tk, delta); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } @@ -2125,7 +2119,7 @@ out: void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended); + ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } @@ -2188,6 +2182,7 @@ void do_timer(unsigned long ticks) * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the @@ -2197,7 +2192,7 @@ void do_timer(unsigned long ticks) * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, - ktime_t *offs_tai) + ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; @@ -2214,6 +2209,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 79b67f5e0343..7a9b4eb7a1d5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -6,6 +6,7 @@ */ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, + ktime_t *offs_boot, ktime_t *offs_tai); extern int timekeeping_valid_for_hres(void); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index dfbcf9ee1447..414d7210b2ec 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1165,7 +1165,7 @@ static struct { { trace_clock, "perf", 1 }, { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, - { ktime_get_mono_fast_ns, "boot", 1 }, + { ktime_get_boot_fast_ns, "boot", 1 }, ARCH_TRACE_CLOCKS }; -- cgit v1.3-18-gd494 From 5e62493f1a70e7f13059544daaee05e40e8548e2 Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Tue, 17 Apr 2018 06:43:58 +0200 Subject: x86/headers/UAPI: Move DISABLE_EXITS KVM capability bits to the UAPI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move DISABLE_EXITS KVM capability bits to the UAPI just like the rest of capabilities. Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: x86@kernel.org Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: KarimAllah Ahmed Signed-off-by: Radim Krčmář --- arch/x86/kvm/x86.h | 7 ------- include/uapi/linux/kvm.h | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7d35ce672989..c9492f764902 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -302,13 +302,6 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) __rem; \ }) -#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) -#define KVM_X86_DISABLE_EXITS_HTL (1 << 1) -#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) -#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ - KVM_X86_DISABLE_EXITS_HTL | \ - KVM_X86_DISABLE_EXITS_PAUSE) - static inline bool kvm_mwait_in_guest(struct kvm *kvm) { return kvm->arch.mwait_in_guest; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 1065006c9bf5..b02c41e53d56 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -676,6 +676,13 @@ struct kvm_ioeventfd { __u8 pad[36]; }; +#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) +#define KVM_X86_DISABLE_EXITS_HTL (1 << 1) +#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) +#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ + KVM_X86_DISABLE_EXITS_HTL | \ + KVM_X86_DISABLE_EXITS_PAUSE) + /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { /* in */ -- cgit v1.3-18-gd494 From 19b9ad67310ed2f685062a00aec602bec33835f0 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 5 Feb 2018 19:32:18 +0200 Subject: : fix end_name_hash() for 64bit long The comment claims that this helper will try not to loose bits, but for 64bit long it looses the high bits before hashing 64bit long into 32bit int. Use the helper hash_long() to do the right thing for 64bit long. For 32bit long, there is no change. All the callers of end_name_hash() either assign the result to qstr->hash, which is u32 or return the result as an int value (e.g. full_name_hash()). Change the helper return type to int to conform to its users. [ It took me a while to apply this, because my initial reaction to it was - incorrectly - that it could make for slower code. After having looked more at it, I take back all my complaints about the patch, Amir was right and I was mis-reading things or just being stupid. I also don't worry too much about the possible performance impact of this on 64-bit, since most architectures that actually care about performance end up not using this very much (the dcache code is the most performance-critical, but the word-at-a-time case uses its own hashing anyway). So this ends up being mostly used for filesystems that do their own degraded hashing (usually because they want a case-insensitive comparison function). A _tiny_ worry remains, in that not everybody uses DCACHE_WORD_ACCESS, and then this potentially makes things more expensive on 64-bit architectures with slow or lacking multipliers even for the normal case. That said, realistically the only such architecture I can think of is PA-RISC. Nobody really cares about performance on that, it's more of a "look ma, I've got warts^W an odd machine" platform. So the patch is fine, and all my initial worries were just misplaced from not looking at this properly. - Linus ] Signed-off-by: Amir Goldstein Signed-off-by: Linus Torvalds --- include/linux/stringhash.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h index e8f0f852968f..c0c5c5b73dc0 100644 --- a/include/linux/stringhash.h +++ b/include/linux/stringhash.h @@ -50,9 +50,9 @@ partial_name_hash(unsigned long c, unsigned long prevhash) * losing bits). This also has the property (wanted by the dcache) * that the msbits make a good hash table index. */ -static inline unsigned long end_name_hash(unsigned long hash) +static inline unsigned int end_name_hash(unsigned long hash) { - return __hash_32((unsigned int)hash); + return hash_long(hash, 32); } /* -- cgit v1.3-18-gd494