diff options
107 files changed, 1695 insertions, 1411 deletions
diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt index 98a8dd5ee385..1a0f2ac02eb6 100644 --- a/Documentation/block/bfq-iosched.txt +++ b/Documentation/block/bfq-iosched.txt @@ -20,13 +20,26 @@ for that device, by setting low_latency to 0. See Section 3 for details on how to configure BFQ for the desired tradeoff between latency and throughput, or on how to maximize throughput. -BFQ has a non-null overhead, which limits the maximum IOPS that a CPU -can process for a device scheduled with BFQ. To give an idea of the -limits on slow or average CPUs, here are, first, the limits of BFQ for -three different CPUs, on, respectively, an average laptop, an old -desktop, and a cheap embedded system, in case full hierarchical -support is enabled (i.e., CONFIG_BFQ_GROUP_IOSCHED is set), but -CONFIG_DEBUG_BLK_CGROUP is not set (Section 4-2): +As every I/O scheduler, BFQ adds some overhead to per-I/O-request +processing. To give an idea of this overhead, the total, +single-lock-protected, per-request processing time of BFQ---i.e., the +sum of the execution times of the request insertion, dispatch and +completion hooks---is, e.g., 1.9 us on an Intel Core i7-2760QM@2.40GHz +(dated CPU for notebooks; time measured with simple code +instrumentation, and using the throughput-sync.sh script of the S +suite [1], in performance-profiling mode). To put this result into +context, the total, single-lock-protected, per-request execution time +of the lightest I/O scheduler available in blk-mq, mq-deadline, is 0.7 +us (mq-deadline is ~800 LOC, against ~10500 LOC for BFQ). + +Scheduling overhead further limits the maximum IOPS that a CPU can +process (already limited by the execution of the rest of the I/O +stack). To give an idea of the limits with BFQ, on slow or average +CPUs, here are, first, the limits of BFQ for three different CPUs, on, +respectively, an average laptop, an old desktop, and a cheap embedded +system, in case full hierarchical support is enabled (i.e., +CONFIG_BFQ_GROUP_IOSCHED is set), but CONFIG_DEBUG_BLK_CGROUP is not +set (Section 4-2): - Intel i7-4850HQ: 400 KIOPS - AMD A8-3850: 250 KIOPS - ARM CortexTM-A53 Octa-core: 80 KIOPS @@ -566,3 +579,5 @@ applications. Unset this tunable if you need/want to control weights. Slightly extended version: http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite- results.pdf + +[3] https://github.com/Algodev-github/S diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt index 4cad1024fff7..41f0a3d33bbd 100644 --- a/Documentation/block/null_blk.txt +++ b/Documentation/block/null_blk.txt @@ -93,3 +93,7 @@ zoned=[0/1]: Default: 0 zone_size=[MB]: Default: 256 Per zone size when exposed as a zoned block device. Must be a power of two. + +zone_nr_conv=[nr_conv]: Default: 0 + The number of conventional zones to create when block device is zoned. If + zone_nr_conv >= nr_zones, it will be reduced to nr_zones - 1. diff --git a/Documentation/process/submit-checklist.rst b/Documentation/process/submit-checklist.rst index 367353c54949..c88867b173d9 100644 --- a/Documentation/process/submit-checklist.rst +++ b/Documentation/process/submit-checklist.rst @@ -72,47 +72,44 @@ and elsewhere regarding submitting Linux kernel patches. 13) Has been build- and runtime tested with and without ``CONFIG_SMP`` and ``CONFIG_PREEMPT.`` -14) If the patch affects IO/Disk, etc: has been tested with and without - ``CONFIG_LBDAF.`` +16) All codepaths have been exercised with all lockdep features enabled. -15) All codepaths have been exercised with all lockdep features enabled. +17) All new ``/proc`` entries are documented under ``Documentation/`` -16) All new ``/proc`` entries are documented under ``Documentation/`` - -17) All new kernel boot parameters are documented in +18) All new kernel boot parameters are documented in ``Documentation/admin-guide/kernel-parameters.rst``. -18) All new module parameters are documented with ``MODULE_PARM_DESC()`` +19) All new module parameters are documented with ``MODULE_PARM_DESC()`` -19) All new userspace interfaces are documented in ``Documentation/ABI/``. +20) All new userspace interfaces are documented in ``Documentation/ABI/``. See ``Documentation/ABI/README`` for more information. Patches that change userspace interfaces should be CCed to linux-api@vger.kernel.org. -20) Check that it all passes ``make headers_check``. +21) Check that it all passes ``make headers_check``. -21) Has been checked with injection of at least slab and page-allocation +22) Has been checked with injection of at least slab and page-allocation failures. See ``Documentation/fault-injection/``. If the new code is substantial, addition of subsystem-specific fault injection might be appropriate. -22) Newly-added code has been compiled with ``gcc -W`` (use +23) Newly-added code has been compiled with ``gcc -W`` (use ``make EXTRA_CFLAGS=-W``). This will generate lots of noise, but is good for finding bugs like "warning: comparison between signed and unsigned". -23) Tested after it has been merged into the -mm patchset to make sure +24) Tested after it has been merged into the -mm patchset to make sure that it still works with all of the other queued patches and various changes in the VM, VFS, and other subsystems. -24) All memory barriers {e.g., ``barrier()``, ``rmb()``, ``wmb()``} need a +25) All memory barriers {e.g., ``barrier()``, ``rmb()``, ``wmb()``} need a comment in the source code that explains the logic of what they are doing and why. -25) If any ioctl's are added by the patch, then also update +26) If any ioctl's are added by the patch, then also update ``Documentation/ioctl/ioctl-number.txt``. -26) If your modified source code depends on or uses any of the kernel +27) If your modified source code depends on or uses any of the kernel APIs or features that are related to the following ``Kconfig`` symbols, then test multiple builds with the related ``Kconfig`` symbols disabled and/or ``=m`` (if that option is available) [not all of these at the diff --git a/Documentation/translations/ja_JP/SubmitChecklist b/Documentation/translations/ja_JP/SubmitChecklist index 60c7c35ac517..b42220d3d46c 100644 --- a/Documentation/translations/ja_JP/SubmitChecklist +++ b/Documentation/translations/ja_JP/SubmitChecklist @@ -74,38 +74,34 @@ Linux カーネルパッチ投稿者向けチェックリスト 13: CONFIG_SMP, CONFIG_PREEMPT を有効にした場合と無効にした場合の両方で ビルドした上、動作確認を行ってください。 -14: もしパッチがディスクのI/O性能などに影響を与えるようであれば、 - 'CONFIG_LBDAF'オプションを有効にした場合と無効にした場合の両方で - テストを実施してみてください。 +14: lockdepの機能を全て有効にした上で、全てのコードパスを評価してください。 -15: lockdepの機能を全て有効にした上で、全てのコードパスを評価してください。 - -16: /proc に新しいエントリを追加した場合には、Documentation/ 配下に +15: /proc に新しいエントリを追加した場合には、Documentation/ 配下に 必ずドキュメントを追加してください。 -17: 新しいブートパラメータを追加した場合には、 +16: 新しいブートパラメータを追加した場合には、 必ずDocumentation/admin-guide/kernel-parameters.rst に説明を追加してください。 -18: 新しくmoduleにパラメータを追加した場合には、MODULE_PARM_DESC()を +17: 新しくmoduleにパラメータを追加した場合には、MODULE_PARM_DESC()を 利用して必ずその説明を記述してください。 -19: 新しいuserspaceインタフェースを作成した場合には、Documentation/ABI/ に +18: 新しいuserspaceインタフェースを作成した場合には、Documentation/ABI/ に Documentation/ABI/README を参考にして必ずドキュメントを追加してください。 -20: 'make headers_check'を実行して全く問題がないことを確認してください。 +19: 'make headers_check'を実行して全く問題がないことを確認してください。 -21: 少なくともslabアロケーションとpageアロケーションに失敗した場合の +20: 少なくともslabアロケーションとpageアロケーションに失敗した場合の 挙動について、fault-injectionを利用して確認してください。 Documentation/fault-injection/ を参照してください。 追加したコードがかなりの量であったならば、サブシステム特有の fault-injectionを追加したほうが良いかもしれません。 -22: 新たに追加したコードは、`gcc -W'でコンパイルしてください。 +21: 新たに追加したコードは、`gcc -W'でコンパイルしてください。 このオプションは大量の不要なメッセージを出力しますが、 "warning: comparison between signed and unsigned" のようなメッセージは、 バグを見つけるのに役に立ちます。 -23: 投稿したパッチが -mm パッチセットにマージされた後、全ての既存のパッチや +22: 投稿したパッチが -mm パッチセットにマージされた後、全ての既存のパッチや VM, VFS およびその他のサブシステムに関する様々な変更と、現時点でも共存 できることを確認するテストを行ってください。 diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index f56cc2070c11..b117e6c16d41 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -15,7 +15,6 @@ CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index b6f2482c7e74..33a787c375e2 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -17,7 +17,6 @@ CONFIG_PERF_EVENTS=y CONFIG_SLAB=y CONFIG_KPROBES=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 318e4cd29629..de398c7b10b3 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -18,7 +18,6 @@ CONFIG_PERF_EVENTS=y CONFIG_ISA_ARCOMPACT=y CONFIG_KPROBES=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index c15807b0e0c1..2dbd34a9ff07 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -20,7 +20,6 @@ CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 65e983fd942b..c7135f1e2583 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -18,7 +18,6 @@ CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 08c5b99ac341..385a71d3c478 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -18,7 +18,6 @@ CONFIG_PERF_EVENTS=y CONFIG_ISA_ARCOMPACT=y CONFIG_KPROBES=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 5b5e26d67955..248a2c3bdc12 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -17,7 +17,6 @@ CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 26af9b2f7fcb..1a4bc7b660fb 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -12,7 +12,6 @@ CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig index 1446262921b4..bdbade6af9c7 100644 --- a/arch/arm/configs/aspeed_g4_defconfig +++ b/arch/arm/configs/aspeed_g4_defconfig @@ -23,7 +23,6 @@ CONFIG_SLAB_FREELIST_RANDOM=y CONFIG_JUMP_LABEL=y CONFIG_STRICT_KERNEL_RWX=y CONFIG_GCC_PLUGINS=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_BLK_DEBUG_FS is not set # CONFIG_IOSCHED_DEADLINE is not set diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig index 02fa3a41add5..4bde84eae4eb 100644 --- a/arch/arm/configs/aspeed_g5_defconfig +++ b/arch/arm/configs/aspeed_g5_defconfig @@ -23,7 +23,6 @@ CONFIG_SLAB_FREELIST_RANDOM=y CONFIG_JUMP_LABEL=y CONFIG_STRICT_KERNEL_RWX=y CONFIG_GCC_PLUGINS=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_BLK_DEBUG_FS is not set # CONFIG_IOSCHED_DEADLINE is not set diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig index e4b1be66b3f5..b7752929975c 100644 --- a/arch/arm/configs/at91_dt_defconfig +++ b/arch/arm/configs/at91_dt_defconfig @@ -9,7 +9,6 @@ CONFIG_EMBEDDED=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arm/configs/clps711x_defconfig b/arch/arm/configs/clps711x_defconfig index fc105c9178cc..09ae750164e0 100644 --- a/arch/arm/configs/clps711x_defconfig +++ b/arch/arm/configs/clps711x_defconfig @@ -6,7 +6,6 @@ CONFIG_RD_LZMA=y CONFIG_EMBEDDED=y CONFIG_SLOB=y CONFIG_JUMP_LABEL=y -# CONFIG_LBDAF is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_CLPS711X=y diff --git a/arch/arm/configs/efm32_defconfig b/arch/arm/configs/efm32_defconfig index ee42158f41ec..10ea92513a69 100644 --- a/arch/arm/configs/efm32_defconfig +++ b/arch/arm/configs/efm32_defconfig @@ -11,7 +11,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig index 484e51fbd4a6..e3afca5bd9d6 100644 --- a/arch/arm/configs/ezx_defconfig +++ b/arch/arm/configs/ezx_defconfig @@ -13,7 +13,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y diff --git a/arch/arm/configs/h3600_defconfig b/arch/arm/configs/h3600_defconfig index ebeca11faa48..175881b7da7c 100644 --- a/arch/arm/configs/h3600_defconfig +++ b/arch/arm/configs/h3600_defconfig @@ -4,7 +4,6 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig index f204017c26b9..9b779e13e05d 100644 --- a/arch/arm/configs/imote2_defconfig +++ b/arch/arm/configs/imote2_defconfig @@ -12,7 +12,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_PXA=y diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig index 078228a19339..6a11669fa536 100644 --- a/arch/arm/configs/moxart_defconfig +++ b/arch/arm/configs/moxart_defconfig @@ -15,7 +15,6 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set CONFIG_ARCH_MULTI_V4=y diff --git a/arch/arm/configs/multi_v4t_defconfig b/arch/arm/configs/multi_v4t_defconfig index 9a6390c172d6..eeea0c41138b 100644 --- a/arch/arm/configs/multi_v4t_defconfig +++ b/arch/arm/configs/multi_v4t_defconfig @@ -5,7 +5,6 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EMBEDDED=y CONFIG_SLOB=y CONFIG_JUMP_LABEL=y -# CONFIG_LBDAF is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_MULTI_V4T=y diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig index cfc00b0961ec..8448a7f407a4 100644 --- a/arch/arm/configs/omap1_defconfig +++ b/arch/arm/configs/omap1_defconfig @@ -17,7 +17,6 @@ CONFIG_OPROFILE=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig index 0258ba891376..152321d2893e 100644 --- a/arch/arm/configs/stm32_defconfig +++ b/arch/arm/configs/stm32_defconfig @@ -13,7 +13,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arm/configs/u300_defconfig b/arch/arm/configs/u300_defconfig index 36d77406e31b..831ba6a9ee8b 100644 --- a/arch/arm/configs/u300_defconfig +++ b/arch/arm/configs/u300_defconfig @@ -9,7 +9,6 @@ CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig index 392ed3b3613c..484d77a7f589 100644 --- a/arch/arm/configs/vexpress_defconfig +++ b/arch/arm/configs/vexpress_defconfig @@ -14,7 +14,6 @@ CONFIG_PROFILING=y CONFIG_OPROFILE=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/m68k/configs/amcore_defconfig b/arch/m68k/configs/amcore_defconfig index 0857cdbfde0c..d5e683dd885d 100644 --- a/arch/m68k/configs/amcore_defconfig +++ b/arch/m68k/configs/amcore_defconfig @@ -12,7 +12,6 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_CFQ is not set # CONFIG_MMU is not set diff --git a/arch/m68k/configs/m5475evb_defconfig b/arch/m68k/configs/m5475evb_defconfig index 4f4ccd13c11b..434bd3750966 100644 --- a/arch/m68k/configs/m5475evb_defconfig +++ b/arch/m68k/configs/m5475evb_defconfig @@ -11,7 +11,6 @@ CONFIG_SYSCTL_SYSCALL=y # CONFIG_AIO is not set CONFIG_EMBEDDED=y CONFIG_MODULES=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig index 69f23c7b0497..27fa9465d19d 100644 --- a/arch/m68k/configs/stmark2_defconfig +++ b/arch/m68k/configs/stmark2_defconfig @@ -17,7 +17,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_BLK_CMDLINE_PARSER=y # CONFIG_MMU is not set diff --git a/arch/mips/configs/ar7_defconfig b/arch/mips/configs/ar7_defconfig index 9fbfb6e5c7d2..c83fdf649327 100644 --- a/arch/mips/configs/ar7_defconfig +++ b/arch/mips/configs/ar7_defconfig @@ -18,7 +18,6 @@ CONFIG_KEXEC=y # CONFIG_SECCOMP is not set CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_BSD_DISKLABEL=y diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig index 0c86ed86266a..30a6eafdb1d0 100644 --- a/arch/mips/configs/decstation_defconfig +++ b/arch/mips/configs/decstation_defconfig @@ -17,7 +17,6 @@ CONFIG_TC=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_SRCVERSION_ALL=y -# CONFIG_LBDAF is not set CONFIG_PARTITION_ADVANCED=y CONFIG_OSF_PARTITION=y # CONFIG_EFI_PARTITION is not set diff --git a/arch/mips/configs/decstation_r4k_defconfig b/arch/mips/configs/decstation_r4k_defconfig index 0e54ab2680ce..e2b58dbf4aa9 100644 --- a/arch/mips/configs/decstation_r4k_defconfig +++ b/arch/mips/configs/decstation_r4k_defconfig @@ -16,7 +16,6 @@ CONFIG_TC=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_SRCVERSION_ALL=y -# CONFIG_LBDAF is not set CONFIG_PARTITION_ADVANCED=y CONFIG_OSF_PARTITION=y # CONFIG_EFI_PARTITION is not set diff --git a/arch/mips/configs/loongson1b_defconfig b/arch/mips/configs/loongson1b_defconfig index b064d68a5424..aa7e98c5f5fc 100644 --- a/arch/mips/configs/loongson1b_defconfig +++ b/arch/mips/configs/loongson1b_defconfig @@ -19,7 +19,6 @@ CONFIG_MACH_LOONGSON32=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_NET=y diff --git a/arch/mips/configs/loongson1c_defconfig b/arch/mips/configs/loongson1c_defconfig index 5d76559b56cd..520e7ef35383 100644 --- a/arch/mips/configs/loongson1c_defconfig +++ b/arch/mips/configs/loongson1c_defconfig @@ -20,7 +20,6 @@ CONFIG_LOONGSON1_LS1C=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_NET=y diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig index 7befe05fd813..ed1038f62a2c 100644 --- a/arch/mips/configs/rb532_defconfig +++ b/arch/mips/configs/rb532_defconfig @@ -19,7 +19,6 @@ CONFIG_PCI=y # CONFIG_PCI_QUIRKS is not set CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_MAC_PARTITION=y diff --git a/arch/mips/configs/rbtx49xx_defconfig b/arch/mips/configs/rbtx49xx_defconfig index 50a2c9ad583f..b0f0c5f9ad9d 100644 --- a/arch/mips/configs/rbtx49xx_defconfig +++ b/arch/mips/configs/rbtx49xx_defconfig @@ -17,7 +17,6 @@ CONFIG_TOSHIBA_RBTX4938_MPLEX_KEEP=y CONFIG_PCI=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index 37ae4b57c001..a8f9bbef0975 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -14,7 +14,6 @@ CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_PA7100LC=y CONFIG_SMP=y diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig index 825c641726c4..d0d9ebc7165b 100644 --- a/arch/sh/configs/apsh4ad0a_defconfig +++ b/arch/sh/configs/apsh4ad0a_defconfig @@ -19,7 +19,6 @@ CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_CPU_SUBTYPE_SH7786=y diff --git a/arch/sh/configs/ecovec24-romimage_defconfig b/arch/sh/configs/ecovec24-romimage_defconfig index 0c5dfccbfe37..bdb61d1d0127 100644 --- a/arch/sh/configs/ecovec24-romimage_defconfig +++ b/arch/sh/configs/ecovec24-romimage_defconfig @@ -7,7 +7,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_KALLSYMS is not set CONFIG_SLAB=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_CPU_SUBTYPE_SH7724=y CONFIG_MEMORY_SIZE=0x10000000 diff --git a/arch/sh/configs/rsk7264_defconfig b/arch/sh/configs/rsk7264_defconfig index 2b9b731fc86b..ad003ee469ea 100644 --- a/arch/sh/configs/rsk7264_defconfig +++ b/arch/sh/configs/rsk7264_defconfig @@ -16,7 +16,6 @@ CONFIG_PERF_COUNTERS=y CONFIG_SLAB=y CONFIG_MMAP_ALLOW_UNINITIALIZED=y CONFIG_PROFILING=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_DEADLINE is not set diff --git a/arch/sh/configs/rsk7269_defconfig b/arch/sh/configs/rsk7269_defconfig index d041f7bcb84c..27fc01d58cf8 100644 --- a/arch/sh/configs/rsk7269_defconfig +++ b/arch/sh/configs/rsk7269_defconfig @@ -3,7 +3,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set CONFIG_SLAB=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig index 2ddf5ca7094e..a89ccc15af23 100644 --- a/arch/sh/configs/sh7785lcr_32bit_defconfig +++ b/arch/sh/configs/sh7785lcr_32bit_defconfig @@ -11,7 +11,6 @@ CONFIG_PROFILING=y CONFIG_GCOV_KERNEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set CONFIG_CPU_SUBTYPE_SH7785=y CONFIG_MEMORY_START=0x40000000 diff --git a/block/Kconfig b/block/Kconfig index 028bc085dac8..1b220101a9cb 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -26,30 +26,6 @@ menuconfig BLOCK if BLOCK -config LBDAF - bool "Support for large (2TB+) block devices and files" - depends on !64BIT - default y - help - Enable block devices or files of size 2TB and larger. - - This option is required to support the full capacity of large - (2TB+) block devices, including RAID, disk, Network Block Device, - Logical Volume Manager (LVM) and loopback. - - This option also enables support for single files larger than - 2TB. - - The ext4 filesystem requires that this feature be enabled in - order to support filesystems that have the huge_file feature - enabled. Otherwise, it will refuse to mount in the read-write - mode any filesystems that use the huge_file feature, which is - enabled by default by mke2fs.ext4. - - The GFS2 filesystem also requires this feature. - - If unsure, say Y. - config BLK_SCSI_REQUEST bool diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index c6113af31960..793c027ca60e 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -578,7 +578,8 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfqg_and_blkg_get(bfqg); if (bfq_bfqq_busy(bfqq)) { - bfq_pos_tree_add_move(bfqd, bfqq); + if (unlikely(!bfqd->nonrot_with_queueing)) + bfq_pos_tree_add_move(bfqd, bfqq); bfq_activate_bfqq(bfqd, bfqq); } @@ -1102,7 +1103,7 @@ struct cftype bfq_blkcg_legacy_files[] = { }, #endif /* CONFIG_DEBUG_BLK_CGROUP */ - /* the same statictics which cover the bfqg and its descendants */ + /* the same statistics which cover the bfqg and its descendants */ { .name = "bfq.io_service_bytes_recursive", .private = (unsigned long)&blkcg_policy_bfq, diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 5ba1e0d841b4..b85a4ab8b9db 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -189,7 +189,7 @@ static const int bfq_default_max_budget = 16 * 1024; /* * When a sync request is dispatched, the queue that contains that * request, and all the ancestor entities of that queue, are charged - * with the number of sectors of the request. In constrast, if the + * with the number of sectors of the request. In contrast, if the * request is async, then the queue and its ancestor entities are * charged with the number of sectors of the request, multiplied by * the factor below. This throttles the bandwidth for async I/O, @@ -217,7 +217,7 @@ const int bfq_timeout = HZ / 8; * queue merging. * * As can be deduced from the low time limit below, queue merging, if - * successful, happens at the very beggining of the I/O of the involved + * successful, happens at the very beginning of the I/O of the involved * cooperating processes, as a consequence of the arrival of the very * first requests from each cooperator. After that, there is very * little chance to find cooperators. @@ -242,6 +242,14 @@ static struct kmem_cache *bfq_pool; blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT)) #define BFQQ_CLOSE_THR (sector_t)(8 * 1024) #define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 19) +/* + * Sync random I/O is likely to be confused with soft real-time I/O, + * because it is characterized by limited throughput and apparently + * isochronous arrival pattern. To avoid false positives, queues + * containing only random (seeky) I/O are prevented from being tagged + * as soft real-time. + */ +#define BFQQ_TOTALLY_SEEKY(bfqq) (bfqq->seek_history & -1) /* Min number of samples required to perform peak-rate update */ #define BFQ_RATE_MIN_SAMPLES 32 @@ -433,7 +441,7 @@ void bfq_schedule_dispatch(struct bfq_data *bfqd) /* * Lifted from AS - choose which of rq1 and rq2 that is best served now. - * We choose the request that is closesr to the head right now. Distance + * We choose the request that is closer to the head right now. Distance * behind the head is penalized and only allowed to a certain extent. */ static struct request *bfq_choose_req(struct bfq_data *bfqd, @@ -595,7 +603,16 @@ static bool bfq_too_late_for_merging(struct bfq_queue *bfqq) bfq_merge_time_limit); } -void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) +/* + * The following function is not marked as __cold because it is + * actually cold, but for the same performance goal described in the + * comments on the likely() at the beginning of + * bfq_setup_cooperator(). Unexpectedly, to reach an even lower + * execution time for the case where this function is not invoked, we + * had to add an unlikely() in each involved if(). + */ +void __cold +bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) { struct rb_node **p, *parent; struct bfq_queue *__bfqq; @@ -629,12 +646,19 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) } /* - * The following function returns true if every queue must receive the - * same share of the throughput (this condition is used when deciding - * whether idling may be disabled, see the comments in the function - * bfq_better_to_idle()). + * The following function returns false either if every active queue + * must receive the same share of the throughput (symmetric scenario), + * or, as a special case, if bfqq must receive a share of the + * throughput lower than or equal to the share that every other active + * queue must receive. If bfqq does sync I/O, then these are the only + * two cases where bfqq happens to be guaranteed its share of the + * throughput even if I/O dispatching is not plugged when bfqq remains + * temporarily empty (for more details, see the comments in the + * function bfq_better_to_idle()). For this reason, the return value + * of this function is used to check whether I/O-dispatch plugging can + * be avoided. * - * Such a scenario occurs when: + * The above first case (symmetric scenario) occurs when: * 1) all active queues have the same weight, * 2) all active queues belong to the same I/O-priority class, * 3) all active groups at the same level in the groups tree have the same @@ -654,30 +678,36 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) * support or the cgroups interface are not enabled, thus no state * needs to be maintained in this case. */ -static bool bfq_symmetric_scenario(struct bfq_data *bfqd) +static bool bfq_asymmetric_scenario(struct bfq_data *bfqd, + struct bfq_queue *bfqq) { + bool smallest_weight = bfqq && + bfqq->weight_counter && + bfqq->weight_counter == + container_of( + rb_first_cached(&bfqd->queue_weights_tree), + struct bfq_weight_counter, + weights_node); + /* * For queue weights to differ, queue_weights_tree must contain * at least two nodes. */ - bool varied_queue_weights = !RB_EMPTY_ROOT(&bfqd->queue_weights_tree) && - (bfqd->queue_weights_tree.rb_node->rb_left || - bfqd->queue_weights_tree.rb_node->rb_right); + bool varied_queue_weights = !smallest_weight && + !RB_EMPTY_ROOT(&bfqd->queue_weights_tree.rb_root) && + (bfqd->queue_weights_tree.rb_root.rb_node->rb_left || + bfqd->queue_weights_tree.rb_root.rb_node->rb_right); bool multiple_classes_busy = (bfqd->busy_queues[0] && bfqd->busy_queues[1]) || (bfqd->busy_queues[0] && bfqd->busy_queues[2]) || (bfqd->busy_queues[1] && bfqd->busy_queues[2]); - /* - * For queue weights to differ, queue_weights_tree must contain - * at least two nodes. - */ - return !(varied_queue_weights || multiple_classes_busy + return varied_queue_weights || multiple_classes_busy #ifdef CONFIG_BFQ_GROUP_IOSCHED || bfqd->num_groups_with_pending_reqs > 0 #endif - ); + ; } /* @@ -694,10 +724,11 @@ static bool bfq_symmetric_scenario(struct bfq_data *bfqd) * should be low too. */ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq, - struct rb_root *root) + struct rb_root_cached *root) { struct bfq_entity *entity = &bfqq->entity; - struct rb_node **new = &(root->rb_node), *parent = NULL; + struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL; + bool leftmost = true; /* * Do not insert if the queue is already associated with a @@ -726,8 +757,10 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq, } if (entity->weight < __counter->weight) new = &((*new)->rb_left); - else + else { new = &((*new)->rb_right); + leftmost = false; + } } bfqq->weight_counter = kzalloc(sizeof(struct bfq_weight_counter), @@ -736,7 +769,7 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq, /* * In the unlucky event of an allocation failure, we just * exit. This will cause the weight of queue to not be - * considered in bfq_symmetric_scenario, which, in its turn, + * considered in bfq_asymmetric_scenario, which, in its turn, * causes the scenario to be deemed wrongly symmetric in case * bfqq's weight would have been the only weight making the * scenario asymmetric. On the bright side, no unbalance will @@ -750,7 +783,8 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfqq->weight_counter->weight = entity->weight; rb_link_node(&bfqq->weight_counter->weights_node, parent, new); - rb_insert_color(&bfqq->weight_counter->weights_node, root); + rb_insert_color_cached(&bfqq->weight_counter->weights_node, root, + leftmost); inc_counter: bfqq->weight_counter->num_active++; @@ -765,7 +799,7 @@ inc_counter: */ void __bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_queue *bfqq, - struct rb_root *root) + struct rb_root_cached *root) { if (!bfqq->weight_counter) return; @@ -774,7 +808,7 @@ void __bfq_weights_tree_remove(struct bfq_data *bfqd, if (bfqq->weight_counter->num_active > 0) goto reset_entity_pointer; - rb_erase(&bfqq->weight_counter->weights_node, root); + rb_erase_cached(&bfqq->weight_counter->weights_node, root); kfree(bfqq->weight_counter); reset_entity_pointer: @@ -889,7 +923,7 @@ static unsigned long bfq_serv_to_charge(struct request *rq, struct bfq_queue *bfqq) { if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1 || - !bfq_symmetric_scenario(bfqq->bfqd)) + bfq_asymmetric_scenario(bfqq->bfqd, bfqq)) return blk_rq_sectors(rq); return blk_rq_sectors(rq) * bfq_async_charge_factor; @@ -955,7 +989,7 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd) * of several files * mplayer took 23 seconds to start, if constantly weight-raised. * - * As for higher values than that accomodating the above bad + * As for higher values than that accommodating the above bad * scenario, tests show that higher values would often yield * the opposite of the desired result, i.e., would worsen * responsiveness by allowing non-interactive applications to @@ -994,6 +1028,7 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd, else bfq_clear_bfqq_IO_bound(bfqq); + bfqq->entity.new_weight = bic->saved_weight; bfqq->ttime = bic->saved_ttime; bfqq->wr_coeff = bic->saved_wr_coeff; bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt; @@ -1041,8 +1076,18 @@ static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq) hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node) hlist_del_init(&item->burst_list_node); - hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list); - bfqd->burst_size = 1; + + /* + * Start the creation of a new burst list only if there is no + * active queue. See comments on the conditional invocation of + * bfq_handle_burst(). + */ + if (bfq_tot_busy_queues(bfqd) == 0) { + hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list); + bfqd->burst_size = 1; + } else + bfqd->burst_size = 0; + bfqd->burst_parent_entity = bfqq->entity.parent; } @@ -1098,7 +1143,8 @@ static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq) * many parallel threads/processes. Examples are systemd during boot, * or git grep. To help these processes get their job done as soon as * possible, it is usually better to not grant either weight-raising - * or device idling to their queues. + * or device idling to their queues, unless these queues must be + * protected from the I/O flowing through other active queues. * * In this comment we describe, firstly, the reasons why this fact * holds, and, secondly, the next function, which implements the main @@ -1110,7 +1156,10 @@ static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq) * cumulatively served, the sooner the target job of these queues gets * completed. As a consequence, weight-raising any of these queues, * which also implies idling the device for it, is almost always - * counterproductive. In most cases it just lowers throughput. + * counterproductive, unless there are other active queues to isolate + * these new queues from. If there no other active queues, then + * weight-raising these new queues just lowers throughput in most + * cases. * * On the other hand, a burst of queue creations may be caused also by * the start of an application that does not consist of a lot of @@ -1144,14 +1193,16 @@ static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq) * are very rare. They typically occur if some service happens to * start doing I/O exactly when the interactive task starts. * - * Turning back to the next function, it implements all the steps - * needed to detect the occurrence of a large burst and to properly - * mark all the queues belonging to it (so that they can then be - * treated in a different way). This goal is achieved by maintaining a - * "burst list" that holds, temporarily, the queues that belong to the - * burst in progress. The list is then used to mark these queues as - * belonging to a large burst if the burst does become large. The main - * steps are the following. + * Turning back to the next function, it is invoked only if there are + * no active queues (apart from active queues that would belong to the + * same, possible burst bfqq would belong to), and it implements all + * the steps needed to detect the occurrence of a large burst and to + * properly mark all the queues belonging to it (so that they can then + * be treated in a different way). This goal is achieved by + * maintaining a "burst list" that holds, temporarily, the queues that + * belong to the burst in progress. The list is then used to mark + * these queues as belonging to a large burst if the burst does become + * large. The main steps are the following. * * . when the very first queue is created, the queue is inserted into the * list (as it could be the first queue in a possible burst) @@ -1596,6 +1647,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, */ in_burst = bfq_bfqq_in_large_burst(bfqq); soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 && + !BFQQ_TOTALLY_SEEKY(bfqq) && !in_burst && time_is_before_jiffies(bfqq->soft_rt_next_start) && bfqq->dispatched == 0; @@ -1704,6 +1756,123 @@ static void bfq_add_request(struct request *rq) bfqq->queued[rq_is_sync(rq)]++; bfqd->queued++; + if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) { + /* + * Periodically reset inject limit, to make sure that + * the latter eventually drops in case workload + * changes, see step (3) in the comments on + * bfq_update_inject_limit(). + */ + if (time_is_before_eq_jiffies(bfqq->decrease_time_jif + + msecs_to_jiffies(1000))) { + /* invalidate baseline total service time */ + bfqq->last_serv_time_ns = 0; + + /* + * Reset pointer in case we are waiting for + * some request completion. + */ + bfqd->waited_rq = NULL; + + /* + * If bfqq has a short think time, then start + * by setting the inject limit to 0 + * prudentially, because the service time of + * an injected I/O request may be higher than + * the think time of bfqq, and therefore, if + * one request was injected when bfqq remains + * empty, this injected request might delay + * the service of the next I/O request for + * bfqq significantly. In case bfqq can + * actually tolerate some injection, then the + * adaptive update will however raise the + * limit soon. This lucky circumstance holds + * exactly because bfqq has a short think + * time, and thus, after remaining empty, is + * likely to get new I/O enqueued---and then + * completed---before being expired. This is + * the very pattern that gives the + * limit-update algorithm the chance to + * measure the effect of injection on request + * service times, and then to update the limit + * accordingly. + * + * On the opposite end, if bfqq has a long + * think time, then start directly by 1, + * because: + * a) on the bright side, keeping at most one + * request in service in the drive is unlikely + * to cause any harm to the latency of bfqq's + * requests, as the service time of a single + * request is likely to be lower than the + * think time of bfqq; + * b) on the downside, after becoming empty, + * bfqq is likely to expire before getting its + * next request. With this request arrival + * pattern, it is very hard to sample total + * service times and update the inject limit + * accordingly (see comments on + * bfq_update_inject_limit()). So the limit is + * likely to be never, or at least seldom, + * updated. As a consequence, by setting the + * limit to 1, we avoid that no injection ever + * occurs with bfqq. On the downside, this + * proactive step further reduces chances to + * actually compute the baseline total service + * time. Thus it reduces chances to execute the + * limit-update algorithm and possibly raise the + * limit to more than 1. + */ + if (bfq_bfqq_has_short_ttime(bfqq)) + bfqq->inject_limit = 0; + else + bfqq->inject_limit = 1; + bfqq->decrease_time_jif = jiffies; + } + + /* + * The following conditions must hold to setup a new + * sampling of total service time, and then a new + * update of the inject limit: + * - bfqq is in service, because the total service + * time is evaluated only for the I/O requests of + * the queues in service; + * - this is the right occasion to compute or to + * lower the baseline total service time, because + * there are actually no requests in the drive, + * or + * the baseline total service time is available, and + * this is the right occasion to compute the other + * quantity needed to update the inject limit, i.e., + * the total service time caused by the amount of + * injection allowed by the current value of the + * limit. It is the right occasion because injection + * has actually been performed during the service + * hole, and there are still in-flight requests, + * which are very likely to be exactly the injected + * requests, or part of them; + * - the minimum interval for sampling the total + * service time and updating the inject limit has + * elapsed. + */ + if (bfqq == bfqd->in_service_queue && + (bfqd->rq_in_driver == 0 || + (bfqq->last_serv_time_ns > 0 && + bfqd->rqs_injected && bfqd->rq_in_driver > 0)) && + time_is_before_eq_jiffies(bfqq->decrease_time_jif + + msecs_to_jiffies(100))) { + bfqd->last_empty_occupied_ns = ktime_get_ns(); + /* + * Start the state machine for measuring the + * total service time of rq: setting + * wait_dispatch will cause bfqd->waited_rq to + * be set when rq will be dispatched. + */ + bfqd->wait_dispatch = true; + bfqd->rqs_injected = false; + } + } + elv_rb_add(&bfqq->sort_list, rq); /* @@ -1715,8 +1884,9 @@ static void bfq_add_request(struct request *rq) /* * Adjust priority tree position, if next_rq changes. + * See comments on bfq_pos_tree_add_move() for the unlikely(). */ - if (prev != bfqq->next_rq) + if (unlikely(!bfqd->nonrot_with_queueing && prev != bfqq->next_rq)) bfq_pos_tree_add_move(bfqd, bfqq); if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */ @@ -1856,7 +2026,9 @@ static void bfq_remove_request(struct request_queue *q, bfqq->pos_root = NULL; } } else { - bfq_pos_tree_add_move(bfqd, bfqq); + /* see comments on bfq_pos_tree_add_move() for the unlikely() */ + if (unlikely(!bfqd->nonrot_with_queueing)) + bfq_pos_tree_add_move(bfqd, bfqq); } if (rq->cmd_flags & REQ_META) @@ -1941,7 +2113,12 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, */ if (prev != bfqq->next_rq) { bfq_updated_next_req(bfqd, bfqq); - bfq_pos_tree_add_move(bfqd, bfqq); + /* + * See comments on bfq_pos_tree_add_move() for + * the unlikely(). + */ + if (unlikely(!bfqd->nonrot_with_queueing)) + bfq_pos_tree_add_move(bfqd, bfqq); } } } @@ -2224,6 +2401,46 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_queue *in_service_bfqq, *new_bfqq; /* + * Do not perform queue merging if the device is non + * rotational and performs internal queueing. In fact, such a + * device reaches a high speed through internal parallelism + * and pipelining. This means that, to reach a high + * throughput, it must have many requests enqueued at the same + * time. But, in this configuration, the internal scheduling + * algorithm of the device does exactly the job of queue + * merging: it reorders requests so as to obtain as much as + * possible a sequential I/O pattern. As a consequence, with + * the workload generated by processes doing interleaved I/O, + * the throughput reached by the device is likely to be the + * same, with and without queue merging. + * + * Disabling merging also provides a remarkable benefit in + * terms of throughput. Merging tends to make many workloads + * artificially more uneven, because of shared queues + * remaining non empty for incomparably more time than + * non-merged queues. This may accentuate workload + * asymmetries. For example, if one of the queues in a set of + * merged queues has a higher weight than a normal queue, then + * the shared queue may inherit such a high weight and, by + * staying almost always active, may force BFQ to perform I/O + * plugging most of the time. This evidently makes it harder + * for BFQ to let the device reach a high throughput. + * + * Finally, the likely() macro below is not used because one + * of the two branches is more likely than the other, but to + * have the code path after the following if() executed as + * fast as possible for the case of a non rotational device + * with queueing. We want it because this is the fastest kind + * of device. On the opposite end, the likely() may lengthen + * the execution time of BFQ for the case of slower devices + * (rotational or at least without queueing). But in this case + * the execution time of BFQ matters very little, if not at + * all. + */ + if (likely(bfqd->nonrot_with_queueing)) + return NULL; + + /* * Prevent bfqq from being merged if it has been created too * long ago. The idea is that true cooperating processes, and * thus their associated bfq_queues, are supposed to be @@ -2286,6 +2503,7 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) if (!bic) return; + bic->saved_weight = bfqq->entity.orig_weight; bic->saved_ttime = bfqq->ttime; bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq); bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); @@ -2374,6 +2592,16 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, * assignment causes no harm). */ new_bfqq->bic = NULL; + /* + * If the queue is shared, the pid is the pid of one of the associated + * processes. Which pid depends on the exact sequence of merge events + * the queue underwent. So printing such a pid is useless and confusing + * because it reports a random pid between those of the associated + * processes. + * We mark such a queue with a pid -1, and then print SHARED instead of + * a pid in logging messages. + */ + new_bfqq->pid = -1; bfqq->bic = NULL; /* release process reference to bfqq */ bfq_put_queue(bfqq); @@ -2408,8 +2636,8 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, /* * bic still points to bfqq, then it has not yet been * redirected to some other bfq_queue, and a queue - * merge beween bfqq and new_bfqq can be safely - * fulfillled, i.e., bic can be redirected to new_bfqq + * merge between bfqq and new_bfqq can be safely + * fulfilled, i.e., bic can be redirected to new_bfqq * and bfqq can be put. */ bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq, @@ -2543,10 +2771,14 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd) * queue). */ if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 && - bfq_symmetric_scenario(bfqd)) + !bfq_asymmetric_scenario(bfqd, bfqq)) sl = min_t(u64, sl, BFQ_MIN_TT); + else if (bfqq->wr_coeff > 1) + sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC); bfqd->last_idling_start = ktime_get(); + bfqd->last_idling_start_jiffies = jiffies; + hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl), HRTIMER_MODE_REL); bfqg_stats_set_start_idle_time(bfqq_group(bfqq)); @@ -2848,8 +3080,10 @@ static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_requeue_bfqq(bfqd, bfqq, true); /* * Resort priority tree of potential close cooperators. + * See comments on bfq_pos_tree_add_move() for the unlikely(). */ - bfq_pos_tree_add_move(bfqd, bfqq); + if (unlikely(!bfqd->nonrot_with_queueing)) + bfq_pos_tree_add_move(bfqd, bfqq); } /* @@ -3223,13 +3457,6 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd, jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4); } -static bool bfq_bfqq_injectable(struct bfq_queue *bfqq) -{ - return BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 && - blk_queue_nonrot(bfqq->bfqd->queue) && - bfqq->bfqd->hw_tag; -} - /** * bfq_bfqq_expire - expire a queue. * @bfqd: device owning the queue. @@ -3344,6 +3571,14 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, slow, bfqq->dispatched, bfq_bfqq_has_short_ttime(bfqq)); /* + * bfqq expired, so no total service time needs to be computed + * any longer: reset state machine for measuring total service + * times. + */ + bfqd->rqs_injected = bfqd->wait_dispatch = false; + bfqd->waited_rq = NULL; + + /* * Increase, decrease or leave budget unchanged according to * reason. */ @@ -3352,8 +3587,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, /* bfqq is gone, no more actions on it */ return; - bfqq->injected_service = 0; - /* mark bfqq as waiting a request only if a bic still points to it */ if (!bfq_bfqq_busy(bfqq) && reason != BFQQE_BUDGET_TIMEOUT && @@ -3497,8 +3730,9 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, } /* - * There is a case where idling must be performed not for - * throughput concerns, but to preserve service guarantees. + * There is a case where idling does not have to be performed for + * throughput concerns, but to preserve the throughput share of + * the process associated with bfqq. * * To introduce this case, we can note that allowing the drive * to enqueue more than one request at a time, and hence @@ -3514,77 +3748,83 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, * concern about per-process throughput distribution, and * makes its decisions only on a per-request basis. Therefore, * the service distribution enforced by the drive's internal - * scheduler is likely to coincide with the desired - * device-throughput distribution only in a completely - * symmetric scenario where: - * (i) each of these processes must get the same throughput as - * the others; - * (ii) the I/O of each process has the same properties, in - * terms of locality (sequential or random), direction - * (reads or writes), request sizes, greediness - * (from I/O-bound to sporadic), and so on. - * In fact, in such a scenario, the drive tends to treat - * the requests of each of these processes in about the same - * way as the requests of the others, and thus to provide - * each of these processes with about the same throughput - * (which is exactly the desired throughput distribution). In - * contrast, in any asymmetric scenario, device idling is - * certainly needed to guarantee that bfqq receives its - * assigned fraction of the device throughput (see [1] for - * details). - * The problem is that idling may significantly reduce - * throughput with certain combinations of types of I/O and - * devices. An important example is sync random I/O, on flash - * storage with command queueing. So, unless bfqq falls in the - * above cases where idling also boosts throughput, it would - * be important to check conditions (i) and (ii) accurately, - * so as to avoid idling when not strictly needed for service - * guarantees. + * scheduler is likely to coincide with the desired throughput + * distribution only in a completely symmetric, or favorably + * skewed scenario where: + * (i-a) each of these processes must get the same throughput as + * the others, + * (i-b) in case (i-a) does not hold, it holds that the process + * associated with bfqq must receive a lower or equal + * throughput than any of the other processes; + * (ii) the I/O of each process has the same properties, in + * terms of locality (sequential or random), direction + * (reads or writes), request sizes, greediness + * (from I/O-bound to sporadic), and so on; + + * In fact, in such a scenario, the drive tends to treat the requests + * of each process in about the same way as the requests of the + * others, and thus to provide each of these processes with about the + * same throughput. This is exactly the desired throughput + * distribution if (i-a) holds, or, if (i-b) holds instead, this is an + * even more convenient distribution for (the process associated with) + * bfqq. * - * Unfortunately, it is extremely difficult to thoroughly - * check condition (ii). And, in case there are active groups, - * it becomes very difficult to check condition (i) too. In - * fact, if there are active groups, then, for condition (i) - * to become false, it is enough that an active group contains - * more active processes or sub-groups than some other active - * group. More precisely, for condition (i) to hold because of - * such a group, it is not even necessary that the group is - * (still) active: it is sufficient that, even if the group - * has become inactive, some of its descendant processes still - * have some request already dispatched but still waiting for - * completion. In fact, requests have still to be guaranteed - * their share of the throughput even after being - * dispatched. In this respect, it is easy to show that, if a - * group frequently becomes inactive while still having - * in-flight requests, and if, when this happens, the group is - * not considered in the calculation of whether the scenario - * is asymmetric, then the group may fail to be guaranteed its - * fair share of the throughput (basically because idling may - * not be performed for the descendant processes of the group, - * but it had to be). We address this issue with the - * following bi-modal behavior, implemented in the function - * bfq_symmetric_scenario(). + * In contrast, in any asymmetric or unfavorable scenario, device + * idling (I/O-dispatch plugging) is certainly needed to guarantee + * that bfqq receives its assigned fraction of the device throughput + * (see [1] for details). + * + * The problem is that idling may significantly reduce throughput with + * certain combinations of types of I/O and devices. An important + * example is sync random I/O on flash storage with command + * queueing. So, unless bfqq falls in cases where idling also boosts + * throughput, it is important to check conditions (i-a), i(-b) and + * (ii) accurately, so as to avoid idling when not strictly needed for + * service guarantees. + * + * Unfortunately, it is extremely difficult to thoroughly check + * condition (ii). And, in case there are active groups, it becomes + * very difficult to check conditions (i-a) and (i-b) too. In fact, + * if there are active groups, then, for conditions (i-a) or (i-b) to + * become false 'indirectly', it is enough that an active group + * contains more active processes or sub-groups than some other active + * group. More precisely, for conditions (i-a) or (i-b) to become + * false because of such a group, it is not even necessary that the + * group is (still) active: it is sufficient that, even if the group + * has become inactive, some of its descendant processes still have + * some request already dispatched but still waiting for + * completion. In fact, requests have still to be guaranteed their + * share of the throughput even after being dispatched. In this + * respect, it is easy to show that, if a group frequently becomes + * inactive while still having in-flight requests, and if, when this + * happens, the group is not considered in the calculation of whether + * the scenario is asymmetric, then the group may fail to be + * guaranteed its fair share of the throughput (basically because + * idling may not be performed for the descendant processes of the + * group, but it had to be). We address this issue with the following + * bi-modal behavior, implemented in the function + * bfq_asymmetric_scenario(). * * If there are groups with requests waiting for completion * (as commented above, some of these groups may even be * already inactive), then the scenario is tagged as * asymmetric, conservatively, without checking any of the - * conditions (i) and (ii). So the device is idled for bfqq. + * conditions (i-a), (i-b) or (ii). So the device is idled for bfqq. * This behavior matches also the fact that groups are created * exactly if controlling I/O is a primary concern (to * preserve bandwidth and latency guarantees). * - * On the opposite end, if there are no groups with requests - * waiting for completion, then only condition (i) is actually - * controlled, i.e., provided that condition (i) holds, idling - * is not performed, regardless of whether condition (ii) - * holds. In other words, only if condition (i) does not hold, - * then idling is allowed, and the device tends to be - * prevented from queueing many requests, possibly of several - * processes. Since there are no groups with requests waiting - * for completion, then, to control condition (i) it is enough - * to check just whether all the queues with requests waiting - * for completion also have the same weight. + * On the opposite end, if there are no groups with requests waiting + * for completion, then only conditions (i-a) and (i-b) are actually + * controlled, i.e., provided that conditions (i-a) or (i-b) holds, + * idling is not performed, regardless of whether condition (ii) + * holds. In other words, only if conditions (i-a) and (i-b) do not + * hold, then idling is allowed, and the device tends to be prevented + * from queueing many requests, possibly of several processes. Since + * there are no groups with requests waiting for completion, then, to + * control conditions (i-a) and (i-b) it is enough to check just + * whether all the queues with requests waiting for completion also + * have the same weight. * * Not checking condition (ii) evidently exposes bfqq to the * risk of getting less throughput than its fair share. @@ -3636,7 +3876,7 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, * compound condition that is checked below for deciding * whether the scenario is asymmetric. To explain this * compound condition, we need to add that the function - * bfq_symmetric_scenario checks the weights of only + * bfq_asymmetric_scenario checks the weights of only * non-weight-raised queues, for efficiency reasons (see * comments on bfq_weights_tree_add()). Then the fact that * bfqq is weight-raised is checked explicitly here. More @@ -3664,7 +3904,7 @@ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, return (bfqq->wr_coeff > 1 && bfqd->wr_busy_queues < bfq_tot_busy_queues(bfqd)) || - !bfq_symmetric_scenario(bfqd); + bfq_asymmetric_scenario(bfqd, bfqq); } /* @@ -3740,26 +3980,98 @@ static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq) return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq); } -static struct bfq_queue *bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) +/* + * This function chooses the queue from which to pick the next extra + * I/O request to inject, if it finds a compatible queue. See the + * comments on bfq_update_inject_limit() for details on the injection + * mechanism, and for the definitions of the quantities mentioned + * below. + */ +static struct bfq_queue * +bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) { - struct bfq_queue *bfqq; + struct bfq_queue *bfqq, *in_serv_bfqq = bfqd->in_service_queue; + unsigned int limit = in_serv_bfqq->inject_limit; + /* + * If + * - bfqq is not weight-raised and therefore does not carry + * time-critical I/O, + * or + * - regardless of whether bfqq is weight-raised, bfqq has + * however a long think time, during which it can absorb the + * effect of an appropriate number of extra I/O requests + * from other queues (see bfq_update_inject_limit for + * details on the computation of this number); + * then injection can be performed without restrictions. + */ + bool in_serv_always_inject = in_serv_bfqq->wr_coeff == 1 || + !bfq_bfqq_has_short_ttime(in_serv_bfqq); /* - * A linear search; but, with a high probability, very few - * steps are needed to find a candidate queue, i.e., a queue - * with enough budget left for its next request. In fact: + * If + * - the baseline total service time could not be sampled yet, + * so the inject limit happens to be still 0, and + * - a lot of time has elapsed since the plugging of I/O + * dispatching started, so drive speed is being wasted + * significantly; + * then temporarily raise inject limit to one request. + */ + if (limit == 0 && in_serv_bfqq->last_serv_time_ns == 0 && + bfq_bfqq_wait_request(in_serv_bfqq) && + time_is_before_eq_jiffies(bfqd->last_idling_start_jiffies + + bfqd->bfq_slice_idle) + ) + limit = 1; + + if (bfqd->rq_in_driver >= limit) + return NULL; + + /* + * Linear search of the source queue for injection; but, with + * a high probability, very few steps are needed to find a + * candidate queue, i.e., a queue with enough budget left for + * its next request. In fact: * - BFQ dynamically updates the budget of every queue so as * to accommodate the expected backlog of the queue; * - if a queue gets all its requests dispatched as injected * service, then the queue is removed from the active list - * (and re-added only if it gets new requests, but with - * enough budget for its new backlog). + * (and re-added only if it gets new requests, but then it + * is assigned again enough budget for its new backlog). */ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) if (!RB_EMPTY_ROOT(&bfqq->sort_list) && + (in_serv_always_inject || bfqq->wr_coeff > 1) && bfq_serv_to_charge(bfqq->next_rq, bfqq) <= - bfq_bfqq_budget_left(bfqq)) - return bfqq; + bfq_bfqq_budget_left(bfqq)) { + /* + * Allow for only one large in-flight request + * on non-rotational devices, for the + * following reason. On non-rotationl drives, + * large requests take much longer than + * smaller requests to be served. In addition, + * the drive prefers to serve large requests + * w.r.t. to small ones, if it can choose. So, + * having more than one large requests queued + * in the drive may easily make the next first + * request of the in-service queue wait for so + * long to break bfqq's service guarantees. On + * the bright side, large requests let the + * drive reach a very high throughput, even if + * there is only one in-flight large request + * at a time. + */ + if (blk_queue_nonrot(bfqd->queue) && + blk_rq_sectors(bfqq->next_rq) >= + BFQQ_SECT_THR_NONROT) + limit = min_t(unsigned int, 1, limit); + else + limit = in_serv_bfqq->inject_limit; + + if (bfqd->rq_in_driver < limit) { + bfqd->rqs_injected = true; + return bfqq; + } + } return NULL; } @@ -3846,14 +4158,32 @@ check_queue: * for a new request, or has requests waiting for a completion and * may idle after their completion, then keep it anyway. * - * Yet, to boost throughput, inject service from other queues if - * possible. + * Yet, inject service from other queues if it boosts + * throughput and is possible. */ if (bfq_bfqq_wait_request(bfqq) || (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) { - if (bfq_bfqq_injectable(bfqq) && - bfqq->injected_service * bfqq->inject_coeff < - bfqq->entity.service * 10) + struct bfq_queue *async_bfqq = + bfqq->bic && bfqq->bic->bfqq[0] && + bfq_bfqq_busy(bfqq->bic->bfqq[0]) ? + bfqq->bic->bfqq[0] : NULL; + + /* + * If the process associated with bfqq has also async + * I/O pending, then inject it + * unconditionally. Injecting I/O from the same + * process can cause no harm to the process. On the + * contrary, it can only increase bandwidth and reduce + * latency for the process. + */ + if (async_bfqq && + icq_to_bic(async_bfqq->next_rq->elv.icq) == bfqq->bic && + bfq_serv_to_charge(async_bfqq->next_rq, async_bfqq) <= + bfq_bfqq_budget_left(async_bfqq)) + bfqq = bfqq->bic->bfqq[0]; + else if (!idling_boosts_thr_without_issues(bfqd, bfqq) && + (bfqq->wr_coeff == 1 || bfqd->wr_busy_queues > 1 || + !bfq_bfqq_has_short_ttime(bfqq))) bfqq = bfq_choose_bfqq_for_injection(bfqd); else bfqq = NULL; @@ -3945,15 +4275,15 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd, bfq_bfqq_served(bfqq, service_to_charge); - bfq_dispatch_remove(bfqd->queue, rq); + if (bfqq == bfqd->in_service_queue && bfqd->wait_dispatch) { + bfqd->wait_dispatch = false; + bfqd->waited_rq = rq; + } - if (bfqq != bfqd->in_service_queue) { - if (likely(bfqd->in_service_queue)) - bfqd->in_service_queue->injected_service += - bfq_serv_to_charge(rq, bfqq); + bfq_dispatch_remove(bfqd->queue, rq); + if (bfqq != bfqd->in_service_queue) goto return_rq; - } /* * If weight raising has to terminate for bfqq, then next @@ -4384,13 +4714,6 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfq_mark_bfqq_has_short_ttime(bfqq); bfq_mark_bfqq_sync(bfqq); bfq_mark_bfqq_just_created(bfqq); - /* - * Aggressively inject a lot of service: up to 90%. - * This coefficient remains constant during bfqq life, - * but this behavior might be changed, after enough - * testing and tuning. - */ - bfqq->inject_coeff = 1; } else bfq_clear_bfqq_sync(bfqq); @@ -4529,6 +4852,11 @@ bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq, { bfqq->seek_history <<= 1; bfqq->seek_history |= BFQ_RQ_SEEKY(bfqd, bfqq->last_request_pos, rq); + + if (bfqq->wr_coeff > 1 && + bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && + BFQQ_TOTALLY_SEEKY(bfqq)) + bfq_bfqq_end_wr(bfqq); } static void bfq_update_has_short_ttime(struct bfq_data *bfqd, @@ -4823,6 +5151,9 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd) bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD; bfqd->max_rq_in_driver = 0; bfqd->hw_tag_samples = 0; + + bfqd->nonrot_with_queueing = + blk_queue_nonrot(bfqd->queue) && bfqd->hw_tag; } static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) @@ -4950,6 +5281,147 @@ static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq) } /* + * The processes associated with bfqq may happen to generate their + * cumulative I/O at a lower rate than the rate at which the device + * could serve the same I/O. This is rather probable, e.g., if only + * one process is associated with bfqq and the device is an SSD. It + * results in bfqq becoming often empty while in service. In this + * respect, if BFQ is allowed to switch to another queue when bfqq + * remains empty, then the device goes on being fed with I/O requests, + * and the throughput is not affected. In contrast, if BFQ is not + * allowed to switch to another queue---because bfqq is sync and + * I/O-dispatch needs to be plugged while bfqq is temporarily + * empty---then, during the service of bfqq, there will be frequent + * "service holes", i.e., time intervals during which bfqq gets empty + * and the device can only consume the I/O already queued in its + * hardware queues. During service holes, the device may even get to + * remaining idle. In the end, during the service of bfqq, the device + * is driven at a lower speed than the one it can reach with the kind + * of I/O flowing through bfqq. + * + * To counter this loss of throughput, BFQ implements a "request + * injection mechanism", which tries to fill the above service holes + * with I/O requests taken from other queues. The hard part in this + * mechanism is finding the right amount of I/O to inject, so as to + * both boost throughput and not break bfqq's bandwidth and latency + * guarantees. In this respect, the mechanism maintains a per-queue + * inject limit, computed as below. While bfqq is empty, the injection + * mechanism dispatches extra I/O requests only until the total number + * of I/O requests in flight---i.e., already dispatched but not yet + * completed---remains lower than this limit. + * + * A first definition comes in handy to introduce the algorithm by + * which the inject limit is computed. We define as first request for + * bfqq, an I/O request for bfqq that arrives while bfqq is in + * service, and causes bfqq to switch from empty to non-empty. The + * algorithm updates the limit as a function of the effect of + * injection on the service times of only the first requests of + * bfqq. The reason for this restriction is that these are the + * requests whose service time is affected most, because they are the + * first to arrive after injection possibly occurred. + * + * To evaluate the effect of injection, the algorithm measures the + * "total service time" of first requests. We define as total service + * time of an I/O request, the time that elapses since when the + * request is enqueued into bfqq, to when it is completed. This + * quantity allows the whole effect of injection to be measured. It is + * easy to see why. Suppose that some requests of other queues are + * actually injected while bfqq is empty, and that a new request R + * then arrives for bfqq. If the device does start to serve all or + * part of the injected requests during the service hole, then, + * because of this extra service, it may delay the next invocation of + * the dispatch hook of BFQ. Then, even after R gets eventually + * dispatched, the device may delay the actual service of R if it is + * still busy serving the extra requests, or if it decides to serve, + * before R, some extra request still present in its queues. As a + * conclusion, the cumulative extra delay caused by injection can be + * easily evaluated by just comparing the total service time of first + * requests with and without injection. + * + * The limit-update algorithm works as follows. On the arrival of a + * first request of bfqq, the algorithm measures the total time of the + * request only if one of the three cases below holds, and, for each + * case, it updates the limit as described below: + * + * (1) If there is no in-flight request. This gives a baseline for the + * total service time of the requests of bfqq. If the baseline has + * not been computed yet, then, after computing it, the limit is + * set to 1, to start boosting throughput, and to prepare the + * ground for the next case. If the baseline has already been + * computed, then it is updated, in case it results to be lower + * than the previous value. + * + * (2) If the limit is higher than 0 and there are in-flight + * requests. By comparing the total service time in this case with + * the above baseline, it is possible to know at which extent the + * current value of the limit is inflating the total service + * time. If the inflation is below a certain threshold, then bfqq + * is assumed to be suffering from no perceivable loss of its + * service guarantees, and the limit is even tentatively + * increased. If the inflation is above the threshold, then the + * limit is decreased. Due to the lack of any hysteresis, this + * logic makes the limit oscillate even in steady workload + * conditions. Yet we opted for it, because it is fast in reaching + * the best value for the limit, as a function of the current I/O + * workload. To reduce oscillations, this step is disabled for a + * short time interval after the limit happens to be decreased. + * + * (3) Periodically, after resetting the limit, to make sure that the + * limit eventually drops in case the workload changes. This is + * needed because, after the limit has gone safely up for a + * certain workload, it is impossible to guess whether the + * baseline total service time may have changed, without measuring + * it again without injection. A more effective version of this + * step might be to just sample the baseline, by interrupting + * injection only once, and then to reset/lower the limit only if + * the total service time with the current limit does happen to be + * too large. + * + * More details on each step are provided in the comments on the + * pieces of code that implement these steps: the branch handling the + * transition from empty to non empty in bfq_add_request(), the branch + * handling injection in bfq_select_queue(), and the function + * bfq_choose_bfqq_for_injection(). These comments also explain some + * exceptions, made by the injection mechanism in some special cases. + */ +static void bfq_update_inject_limit(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns; + unsigned int old_limit = bfqq->inject_limit; + + if (bfqq->last_serv_time_ns > 0) { + u64 threshold = (bfqq->last_serv_time_ns * 3)>>1; + + if (tot_time_ns >= threshold && old_limit > 0) { + bfqq->inject_limit--; + bfqq->decrease_time_jif = jiffies; + } else if (tot_time_ns < threshold && + old_limit < bfqd->max_rq_in_driver<<1) + bfqq->inject_limit++; + } + + /* + * Either we still have to compute the base value for the + * total service time, and there seem to be the right + * conditions to do it, or we can lower the last base value + * computed. + */ + if ((bfqq->last_serv_time_ns == 0 && bfqd->rq_in_driver == 0) || + tot_time_ns < bfqq->last_serv_time_ns) { + bfqq->last_serv_time_ns = tot_time_ns; + /* + * Now we certainly have a base value: make sure we + * start trying injection. + */ + bfqq->inject_limit = max_t(unsigned int, 1, old_limit); + } + + /* update complete, not waiting for any request completion any longer */ + bfqd->waited_rq = NULL; +} + +/* * Handle either a requeue or a finish for rq. The things to do are * the same in both cases: all references to rq are to be dropped. In * particular, rq is considered completed from the point of view of @@ -4993,6 +5465,9 @@ static void bfq_finish_requeue_request(struct request *rq) spin_lock_irqsave(&bfqd->lock, flags); + if (rq == bfqd->waited_rq) + bfq_update_inject_limit(bfqd, bfqq); + bfq_completed_request(bfqq, bfqd); bfq_finish_requeue_request_body(bfqq); @@ -5156,7 +5631,7 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio) * preparation is that, after the prepare_request hook is invoked for * rq, rq may still be transformed into a request with no icq, i.e., a * request not associated with any queue. No bfq hook is invoked to - * signal this tranformation. As a consequence, should these + * signal this transformation. As a consequence, should these * preparation operations be performed when the prepare_request hook * is invoked, and should rq be transformed one moment later, bfq * would end up in an inconsistent state, because it would have @@ -5247,7 +5722,29 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) } } - if (unlikely(bfq_bfqq_just_created(bfqq))) + /* + * Consider bfqq as possibly belonging to a burst of newly + * created queues only if: + * 1) A burst is actually happening (bfqd->burst_size > 0) + * or + * 2) There is no other active queue. In fact, if, in + * contrast, there are active queues not belonging to the + * possible burst bfqq may belong to, then there is no gain + * in considering bfqq as belonging to a burst, and + * therefore in not weight-raising bfqq. See comments on + * bfq_handle_burst(). + * + * This filtering also helps eliminating false positives, + * occurring when bfqq does not belong to an actual large + * burst, but some background task (e.g., a service) happens + * to trigger the creation of new queues very close to when + * bfqq and its possible companion queues are created. See + * comments on bfq_handle_burst() for further details also on + * this issue. + */ + if (unlikely(bfq_bfqq_just_created(bfqq) && + (bfqd->burst_size > 0 || + bfq_tot_busy_queues(bfqd) == 0))) bfq_handle_burst(bfqd, bfqq); return bfqq; @@ -5507,7 +6004,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) HRTIMER_MODE_REL); bfqd->idle_slice_timer.function = bfq_idle_slice_timer; - bfqd->queue_weights_tree = RB_ROOT; + bfqd->queue_weights_tree = RB_ROOT_CACHED; bfqd->num_groups_with_pending_reqs = 0; INIT_LIST_HEAD(&bfqd->active_list); @@ -5515,6 +6012,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) INIT_HLIST_HEAD(&bfqd->burst_list); bfqd->hw_tag = -1; + bfqd->nonrot_with_queueing = blk_queue_nonrot(bfqd->queue); bfqd->bfq_max_budget = bfq_default_max_budget; diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 86394e503ca9..eba7cd449ab4 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -32,6 +32,8 @@ #define BFQ_DEFAULT_GRP_IOPRIO 0 #define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE +#define MAX_PID_STR_LENGTH 12 + /* * Soft real-time applications are extremely more latency sensitive * than interactive ones. Over-raise the weight of the former to @@ -89,7 +91,7 @@ struct bfq_service_tree { * expiration. This peculiar definition allows for the following * optimization, not yet exploited: while a given entity is still in * service, we already know which is the best candidate for next - * service among the other active entitities in the same parent + * service among the other active entities in the same parent * entity. We can then quickly compare the timestamps of the * in-service entity with those of such best candidate. * @@ -140,7 +142,7 @@ struct bfq_weight_counter { * * Unless cgroups are used, the weight value is calculated from the * ioprio to export the same interface as CFQ. When dealing with - * ``well-behaved'' queues (i.e., queues that do not spend too much + * "well-behaved" queues (i.e., queues that do not spend too much * time to consume their budget and have true sequential behavior, and * when there are no external factors breaking anticipation) the * relative weights at each level of the cgroups hierarchy should be @@ -240,6 +242,13 @@ struct bfq_queue { /* next ioprio and ioprio class if a change is in progress */ unsigned short new_ioprio, new_ioprio_class; + /* last total-service-time sample, see bfq_update_inject_limit() */ + u64 last_serv_time_ns; + /* limit for request injection */ + unsigned int inject_limit; + /* last time the inject limit has been decreased, in jiffies */ + unsigned long decrease_time_jif; + /* * Shared bfq_queue if queue is cooperating with one or more * other queues. @@ -357,29 +366,6 @@ struct bfq_queue { /* max service rate measured so far */ u32 max_service_rate; - /* - * Ratio between the service received by bfqq while it is in - * service, and the cumulative service (of requests of other - * queues) that may be injected while bfqq is empty but still - * in service. To increase precision, the coefficient is - * measured in tenths of unit. Here are some example of (1) - * ratios, (2) resulting percentages of service injected - * w.r.t. to the total service dispatched while bfqq is in - * service, and (3) corresponding values of the coefficient: - * 1 (50%) -> 10 - * 2 (33%) -> 20 - * 10 (9%) -> 100 - * 9.9 (9%) -> 99 - * 1.5 (40%) -> 15 - * 0.5 (66%) -> 5 - * 0.1 (90%) -> 1 - * - * So, if the coefficient is lower than 10, then - * injected service is more than bfqq service. - */ - unsigned int inject_coeff; - /* amount of service injected in current service slot */ - unsigned int injected_service; }; /** @@ -419,6 +405,15 @@ struct bfq_io_cq { bool was_in_burst_list; /* + * Save the weight when a merge occurs, to be able + * to restore it in case of split. If the weight is not + * correctly resumed when the queue is recycled, + * then the weight of the recycled queue could differ + * from the weight of the original queue. + */ + unsigned int saved_weight; + + /* * Similar to previous fields: save wr information. */ unsigned long saved_wr_coeff; @@ -450,7 +445,7 @@ struct bfq_data { * weight-raised @bfq_queue (see the comments to the functions * bfq_weights_tree_[add|remove] for further details). */ - struct rb_root queue_weights_tree; + struct rb_root_cached queue_weights_tree; /* * Number of groups with at least one descendant process that @@ -513,6 +508,9 @@ struct bfq_data { /* number of requests dispatched and waiting for completion */ int rq_in_driver; + /* true if the device is non rotational and performs queueing */ + bool nonrot_with_queueing; + /* * Maximum number of requests in driver in the last * @hw_tag_samples completed requests. @@ -544,6 +542,26 @@ struct bfq_data { /* time of last request completion (ns) */ u64 last_completion; + /* time of last transition from empty to non-empty (ns) */ + u64 last_empty_occupied_ns; + + /* + * Flag set to activate the sampling of the total service time + * of a just-arrived first I/O request (see + * bfq_update_inject_limit()). This will cause the setting of + * waited_rq when the request is finally dispatched. + */ + bool wait_dispatch; + /* + * If set, then bfq_update_inject_limit() is invoked when + * waited_rq is eventually completed. + */ + struct request *waited_rq; + /* + * True if some request has been injected during the last service hole. + */ + bool rqs_injected; + /* time of first rq dispatch in current observation interval (ns) */ u64 first_dispatch; /* time of last rq dispatch in current observation interval (ns) */ @@ -553,6 +571,7 @@ struct bfq_data { ktime_t last_budget_start; /* beginning of the last idle slice */ ktime_t last_idling_start; + unsigned long last_idling_start_jiffies; /* number of samples in current observation interval */ int peak_rate_samples; @@ -898,10 +917,10 @@ void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync); struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic); void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq); void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq, - struct rb_root *root); + struct rb_root_cached *root); void __bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_queue *bfqq, - struct rb_root *root); + struct rb_root_cached *root); void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_queue *bfqq); void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq, @@ -1008,13 +1027,23 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq); /* --------------- end of interface of B-WF2Q+ ---------------- */ /* Logging facilities. */ +static inline void bfq_pid_to_str(int pid, char *str, int len) +{ + if (pid != -1) + snprintf(str, len, "%d", pid); + else + snprintf(str, len, "SHARED-"); +} + #ifdef CONFIG_BFQ_GROUP_IOSCHED struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ + char pid_str[MAX_PID_STR_LENGTH]; \ + bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ blk_add_cgroup_trace_msg((bfqd)->queue, \ bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \ - "bfq%d%c " fmt, (bfqq)->pid, \ + "bfq%s%c " fmt, pid_str, \ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', ##args); \ } while (0) @@ -1025,10 +1054,13 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #else /* CONFIG_BFQ_GROUP_IOSCHED */ -#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \ - blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid, \ +#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ + char pid_str[MAX_PID_STR_LENGTH]; \ + bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ + blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str, \ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ - ##args) + ##args); \ +} while (0) #define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0) #endif /* CONFIG_BFQ_GROUP_IOSCHED */ diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index ae4d000ac0af..48d899cfbe03 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -59,7 +59,7 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service); * bfq_update_next_in_service - update sd->next_in_service * @sd: sched_data for which to perform the update. * @new_entity: if not NULL, pointer to the entity whose activation, - * requeueing or repositionig triggered the invocation of + * requeueing or repositioning triggered the invocation of * this function. * @expiration: id true, this function is being invoked after the * expiration of the in-service entity @@ -90,7 +90,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd, /* * If this update is triggered by the activation, requeueing - * or repositiong of an entity that does not coincide with + * or repositioning of an entity that does not coincide with * sd->next_in_service, then a full lookup in the active tree * can be avoided. In fact, it is enough to check whether the * just-modified entity has the same priority as @@ -737,7 +737,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st, struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); unsigned int prev_weight, new_weight; struct bfq_data *bfqd = NULL; - struct rb_root *root; + struct rb_root_cached *root; #ifdef CONFIG_BFQ_GROUP_IOSCHED struct bfq_sched_data *sd; struct bfq_group *bfqg; @@ -1396,7 +1396,7 @@ left: * In this first case, update the virtual time in @st too (see the * comments on this update inside the function). * - * In constrast, if there is an in-service entity, then return the + * In contrast, if there is an in-service entity, then return the * entity that would be set in service if not only the above * conditions, but also the next one held true: the currently * in-service entity, on expiration, @@ -1479,12 +1479,12 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd, * is being invoked as a part of the expiration path * of the in-service queue. In this case, even if * sd->in_service_entity is not NULL, - * sd->in_service_entiy at this point is actually not + * sd->in_service_entity at this point is actually not * in service any more, and, if needed, has already * been properly queued or requeued into the right * tree. The reason why sd->in_service_entity is still * not NULL here, even if expiration is true, is that - * sd->in_service_entiy is reset as a last step in the + * sd->in_service_entity is reset as a last step in the * expiration path. So, if expiration is true, tell * __bfq_lookup_next_entity that there is no * sd->in_service_entity. diff --git a/block/bio.c b/block/bio.c index 716510ecd7ff..5959141d4e46 100644 --- a/block/bio.c +++ b/block/bio.c @@ -647,25 +647,70 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs) } EXPORT_SYMBOL(bio_clone_fast); +static inline bool page_is_mergeable(const struct bio_vec *bv, + struct page *page, unsigned int len, unsigned int off, + bool same_page) +{ + phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + + bv->bv_offset + bv->bv_len - 1; + phys_addr_t page_addr = page_to_phys(page); + + if (vec_end_addr + 1 != page_addr + off) + return false; + if (xen_domain() && !xen_biovec_phys_mergeable(bv, page)) + return false; + + if ((vec_end_addr & PAGE_MASK) != page_addr) { + if (same_page) + return false; + if (pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page) + return false; + } + + return true; +} + +/* + * Check if the @page can be added to the current segment(@bv), and make + * sure to call it only if page_is_mergeable(@bv, @page) is true + */ +static bool can_add_page_to_seg(struct request_queue *q, + struct bio_vec *bv, struct page *page, unsigned len, + unsigned offset) +{ + unsigned long mask = queue_segment_boundary(q); + phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset; + phys_addr_t addr2 = page_to_phys(page) + offset + len - 1; + + if ((addr1 | mask) != (addr2 | mask)) + return false; + + if (bv->bv_len + len > queue_max_segment_size(q)) + return false; + + return true; +} + /** - * bio_add_pc_page - attempt to add page to bio + * __bio_add_pc_page - attempt to add page to passthrough bio * @q: the target queue * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset + * @put_same_page: put the page if it is same with last added page * * Attempt to add a page to the bio_vec maplist. This can fail for a * number of reasons, such as the bio being full or target block device * limitations. The target block device must allow bio's up to PAGE_SIZE, * so it is always possible to add a single page to an empty bio. * - * This should only be used by REQ_PC bios. + * This should only be used by passthrough bios. */ -int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page - *page, unsigned int len, unsigned int offset) +int __bio_add_pc_page(struct request_queue *q, struct bio *bio, + struct page *page, unsigned int len, unsigned int offset, + bool put_same_page) { - int retried_segments = 0; struct bio_vec *bvec; /* @@ -683,11 +728,14 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page * a consecutive offset. Optimize this special case. */ if (bio->bi_vcnt > 0) { - struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1]; - - if (page == prev->bv_page && - offset == prev->bv_offset + prev->bv_len) { - prev->bv_len += len; + bvec = &bio->bi_io_vec[bio->bi_vcnt - 1]; + + if (page == bvec->bv_page && + offset == bvec->bv_offset + bvec->bv_len) { + if (put_same_page) + put_page(page); + bvec_merge: + bvec->bv_len += len; bio->bi_iter.bi_size += len; goto done; } @@ -696,13 +744,20 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ - if (bvec_gap_to_prev(q, prev, offset)) + if (bvec_gap_to_prev(q, bvec, offset)) return 0; + + if (page_is_mergeable(bvec, page, len, offset, false) && + can_add_page_to_seg(q, bvec, page, len, offset)) + goto bvec_merge; } if (bio_full(bio)) return 0; + if (bio->bi_phys_segments >= queue_max_segments(q)) + return 0; + /* * setup the new entry, we might clear it again later if we * cannot add the page @@ -712,38 +767,19 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page bvec->bv_len = len; bvec->bv_offset = offset; bio->bi_vcnt++; - bio->bi_phys_segments++; bio->bi_iter.bi_size += len; - /* - * Perform a recount if the number of segments is greater - * than queue_max_segments(q). - */ - - while (bio->bi_phys_segments > queue_max_segments(q)) { - - if (retried_segments) - goto failed; - - retried_segments = 1; - blk_recount_segments(q, bio); - } - - /* If we may be able to merge these biovecs, force a recount */ - if (bio->bi_vcnt > 1 && biovec_phys_mergeable(q, bvec - 1, bvec)) - bio_clear_flag(bio, BIO_SEG_VALID); - done: + bio->bi_phys_segments = bio->bi_vcnt; + bio_set_flag(bio, BIO_SEG_VALID); return len; +} +EXPORT_SYMBOL(__bio_add_pc_page); - failed: - bvec->bv_page = NULL; - bvec->bv_len = 0; - bvec->bv_offset = 0; - bio->bi_vcnt--; - bio->bi_iter.bi_size -= len; - blk_recount_segments(q, bio); - return 0; +int bio_add_pc_page(struct request_queue *q, struct bio *bio, + struct page *page, unsigned int len, unsigned int offset) +{ + return __bio_add_pc_page(q, bio, page, len, offset, false); } EXPORT_SYMBOL(bio_add_pc_page); @@ -770,18 +806,12 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page, if (bio->bi_vcnt > 0) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + - bv->bv_offset + bv->bv_len - 1; - phys_addr_t page_addr = page_to_phys(page); - - if (vec_end_addr + 1 != page_addr + off) - return false; - if (same_page && (vec_end_addr & PAGE_MASK) != page_addr) - return false; - bv->bv_len += len; - bio->bi_iter.bi_size += len; - return true; + if (page_is_mergeable(bv, page, len, off, same_page)) { + bv->bv_len += len; + bio->bi_iter.bi_size += len; + return true; + } } return false; } @@ -836,6 +866,26 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); +static void bio_get_pages(struct bio *bio) +{ + struct bvec_iter_all iter_all; + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i, iter_all) + get_page(bvec->bv_page); +} + +static void bio_release_pages(struct bio *bio) +{ + struct bvec_iter_all iter_all; + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i, iter_all) + put_page(bvec->bv_page); +} + static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) { const struct bio_vec *bv = iter->bvec; @@ -848,20 +898,10 @@ static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) len = min_t(size_t, bv->bv_len - iter->iov_offset, iter->count); size = bio_add_page(bio, bv->bv_page, len, bv->bv_offset + iter->iov_offset); - if (size == len) { - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { - struct page *page; - int i; - - mp_bvec_for_each_page(page, bv, i) - get_page(page); - } - - iov_iter_advance(iter, size); - return 0; - } - - return -EINVAL; + if (unlikely(size != len)) + return -EINVAL; + iov_iter_advance(iter, size); + return 0; } #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) @@ -934,29 +974,24 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { const bool is_bvec = iov_iter_is_bvec(iter); - unsigned short orig_vcnt = bio->bi_vcnt; + int ret; - /* - * If this is a BVEC iter, then the pages are kernel pages. Don't - * release them on IO completion, if the caller asked us to. - */ - if (is_bvec && iov_iter_bvec_no_ref(iter)) - bio_set_flag(bio, BIO_NO_PAGE_REF); + if (WARN_ON_ONCE(bio->bi_vcnt)) + return -EINVAL; do { - int ret; - if (is_bvec) ret = __bio_iov_bvec_add_pages(bio, iter); else ret = __bio_iov_iter_get_pages(bio, iter); + } while (!ret && iov_iter_count(iter) && !bio_full(bio)); - if (unlikely(ret)) - return bio->bi_vcnt > orig_vcnt ? 0 : ret; - - } while (iov_iter_count(iter) && !bio_full(bio)); + if (iov_iter_bvec_no_ref(iter)) + bio_set_flag(bio, BIO_NO_PAGE_REF); + else + bio_get_pages(bio); - return 0; + return bio->bi_vcnt ? 0 : ret; } static void submit_bio_wait_endio(struct bio *bio) @@ -1388,21 +1423,14 @@ struct bio *bio_map_user_iov(struct request_queue *q, for (j = 0; j < npages; j++) { struct page *page = pages[j]; unsigned int n = PAGE_SIZE - offs; - unsigned short prev_bi_vcnt = bio->bi_vcnt; if (n > bytes) n = bytes; - if (!bio_add_pc_page(q, bio, page, n, offs)) + if (!__bio_add_pc_page(q, bio, page, n, offs, + true)) break; - /* - * check if vector was merged with previous - * drop page reference if needed - */ - if (bio->bi_vcnt == prev_bi_vcnt) - put_page(page); - added += n; bytes -= n; offs = 0; @@ -1659,16 +1687,6 @@ void bio_set_pages_dirty(struct bio *bio) } } -static void bio_release_pages(struct bio *bio) -{ - struct bio_vec *bvec; - int i; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, i, iter_all) - put_page(bvec->bv_page); -} - /* * bio_check_pages_dirty() will check that all the BIO's pages are still dirty. * If they are, then fine. If, however, some pages are clean then they must @@ -2203,6 +2221,9 @@ static int __init init_bio(void) bio_slab_nr = 0; bio_slabs = kcalloc(bio_slab_max, sizeof(struct bio_slab), GFP_KERNEL); + + BUILD_BUG_ON(BIO_FLAG_LAST > BVEC_POOL_OFFSET); + if (!bio_slabs) panic("bio: can't allocate bios\n"); diff --git a/block/blk-merge.c b/block/blk-merge.c index 1c9d4f0f96ea..247b17f2a0f6 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -267,23 +267,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, goto split; } - if (bvprvp) { - if (seg_size + bv.bv_len > queue_max_segment_size(q)) - goto new_segment; - if (!biovec_phys_mergeable(q, bvprvp, &bv)) - goto new_segment; - - seg_size += bv.bv_len; - bvprv = bv; - bvprvp = &bvprv; - sectors += bv.bv_len >> 9; - - if (nsegs == 1 && seg_size > front_seg_size) - front_seg_size = seg_size; - - continue; - } -new_segment: if (nsegs == max_segs) goto split; @@ -370,12 +353,12 @@ EXPORT_SYMBOL(blk_queue_split); static unsigned int __blk_recalc_rq_segments(struct request_queue *q, struct bio *bio) { - struct bio_vec bv, bvprv = { NULL }; - int prev = 0; + struct bio_vec uninitialized_var(bv), bvprv = { NULL }; unsigned int seg_size, nr_phys_segs; unsigned front_seg_size; struct bio *fbio, *bbio; struct bvec_iter iter; + bool new_bio = false; if (!bio) return 0; @@ -396,7 +379,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, nr_phys_segs = 0; for_each_bio(bio) { bio_for_each_bvec(bv, bio, iter) { - if (prev) { + if (new_bio) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; @@ -404,7 +387,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, goto new_segment; seg_size += bv.bv_len; - bvprv = bv; if (nr_phys_segs == 1 && seg_size > front_seg_size) @@ -413,12 +395,15 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, continue; } new_segment: - bvprv = bv; - prev = 1; bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size, &front_seg_size, NULL, UINT_MAX); + new_bio = false; } bbio = bio; + if (likely(bio->bi_iter.bi_size)) { + bvprv = bv; + new_bio = true; + } } fbio->bi_seg_front_size = front_seg_size; @@ -484,79 +469,85 @@ static unsigned blk_bvec_map_sg(struct request_queue *q, struct scatterlist **sg) { unsigned nbytes = bvec->bv_len; - unsigned nsegs = 0, total = 0, offset = 0; + unsigned nsegs = 0, total = 0; while (nbytes > 0) { - unsigned seg_size; - struct page *pg; - unsigned idx; + unsigned offset = bvec->bv_offset + total; + unsigned len = min(get_max_segment_size(q, offset), nbytes); *sg = blk_next_sg(sg, sglist); + sg_set_page(*sg, bvec->bv_page, len, offset); - seg_size = get_max_segment_size(q, bvec->bv_offset + total); - seg_size = min(nbytes, seg_size); - - offset = (total + bvec->bv_offset) % PAGE_SIZE; - idx = (total + bvec->bv_offset) / PAGE_SIZE; - pg = bvec_nth_page(bvec->bv_page, idx); - - sg_set_page(*sg, pg, seg_size, offset); - - total += seg_size; - nbytes -= seg_size; + total += len; + nbytes -= len; nsegs++; } return nsegs; } -static inline void -__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec, - struct scatterlist *sglist, struct bio_vec *bvprv, - struct scatterlist **sg, int *nsegs) +static inline int __blk_bvec_map_sg(struct bio_vec bv, + struct scatterlist *sglist, struct scatterlist **sg) +{ + *sg = blk_next_sg(sg, sglist); + sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); + return 1; +} + +/* only try to merge bvecs into one sg if they are from two bios */ +static inline bool +__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec, + struct bio_vec *bvprv, struct scatterlist **sg) { int nbytes = bvec->bv_len; - if (*sg) { - if ((*sg)->length + nbytes > queue_max_segment_size(q)) - goto new_segment; - if (!biovec_phys_mergeable(q, bvprv, bvec)) - goto new_segment; + if (!*sg) + return false; - (*sg)->length += nbytes; - } else { -new_segment: - if (bvec->bv_offset + bvec->bv_len <= PAGE_SIZE) { - *sg = blk_next_sg(sg, sglist); - sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset); - (*nsegs) += 1; - } else - (*nsegs) += blk_bvec_map_sg(q, bvec, sglist, sg); - } - *bvprv = *bvec; -} + if ((*sg)->length + nbytes > queue_max_segment_size(q)) + return false; -static inline int __blk_bvec_map_sg(struct request_queue *q, struct bio_vec bv, - struct scatterlist *sglist, struct scatterlist **sg) -{ - *sg = sglist; - sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); - return 1; + if (!biovec_phys_mergeable(q, bvprv, bvec)) + return false; + + (*sg)->length += nbytes; + + return true; } static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist, struct scatterlist **sg) { - struct bio_vec bvec, bvprv = { NULL }; + struct bio_vec uninitialized_var(bvec), bvprv = { NULL }; struct bvec_iter iter; int nsegs = 0; + bool new_bio = false; - for_each_bio(bio) - bio_for_each_bvec(bvec, bio, iter) - __blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg, - &nsegs); + for_each_bio(bio) { + bio_for_each_bvec(bvec, bio, iter) { + /* + * Only try to merge bvecs from two bios given we + * have done bio internal merge when adding pages + * to bio + */ + if (new_bio && + __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg)) + goto next_bvec; + + if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE) + nsegs += __blk_bvec_map_sg(bvec, sglist, sg); + else + nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg); + next_bvec: + new_bio = false; + } + if (likely(bio->bi_iter.bi_size)) { + bvprv = bvec; + new_bio = true; + } + } return nsegs; } @@ -572,9 +563,9 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, int nsegs = 0; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - nsegs = __blk_bvec_map_sg(q, rq->special_vec, sglist, &sg); + nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, &sg); else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME) - nsegs = __blk_bvec_map_sg(q, bio_iovec(rq->bio), sglist, &sg); + nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, &sg); else if (rq->bio) nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg); diff --git a/block/blk.h b/block/blk.h index 5d636ee41663..e27fd1512e4b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -75,7 +75,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, if (addr1 + vec1->bv_len != addr2) return false; - if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2)) + if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page)) return false; if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask)) return false; diff --git a/block/elevator.c b/block/elevator.c index d6d835a08de6..2e5399d9f40f 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -509,8 +509,6 @@ void elv_unregister_queue(struct request_queue *q) int elv_register(struct elevator_type *e) { - char *def = ""; - /* create icq_cache if requested */ if (e->icq_size) { if (WARN_ON(e->icq_size < sizeof(struct io_cq)) || @@ -535,8 +533,8 @@ int elv_register(struct elevator_type *e) list_add_tail(&e->list, &elv_list); spin_unlock(&elv_list_lock); - printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name, - def); + printk(KERN_INFO "io scheduler %s registered\n", e->elevator_name); + return 0; } EXPORT_SYMBOL_GPL(elv_register); diff --git a/block/genhd.c b/block/genhd.c index 703267865f14..1d0d25f7b0fe 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1628,12 +1628,11 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk) /* * If device-specific poll interval is set, always use it. If - * the default is being used, poll iff there are events which - * can't be monitored asynchronously. + * the default is being used, poll if the POLL flag is set. */ if (ev->poll_msecs >= 0) intv_msecs = ev->poll_msecs; - else if (disk->events & ~disk->async_events) + else if (disk->event_flags & DISK_EVENT_FLAG_POLL) intv_msecs = disk_events_dfl_poll_msecs; return msecs_to_jiffies(intv_msecs); @@ -1843,11 +1842,13 @@ static void disk_check_events(struct disk_events *ev, /* * Tell userland about new events. Only the events listed in - * @disk->events are reported. Unlisted events are processed the - * same internally but never get reported to userland. + * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT + * is set. Otherwise, events are processed internally but never + * get reported to userland. */ for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) - if (events & disk->events & (1 << i)) + if ((events & disk->events & (1 << i)) && + (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) envp[nr_events++] = disk_uevents[i]; if (nr_events) @@ -1860,6 +1861,7 @@ static void disk_check_events(struct disk_events *ev, * * events : list of all supported events * events_async : list of events which can be detected w/o polling + * (always empty, only for backwards compatibility) * events_poll_msecs : polling interval, 0: disable, -1: system default */ static ssize_t __disk_events_show(unsigned int events, char *buf) @@ -1884,15 +1886,16 @@ static ssize_t disk_events_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); + if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) + return 0; + return __disk_events_show(disk->events, buf); } static ssize_t disk_events_async_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct gendisk *disk = dev_to_disk(dev); - - return __disk_events_show(disk->async_events, buf); + return 0; } static ssize_t disk_events_poll_msecs_show(struct device *dev, @@ -1901,6 +1904,9 @@ static ssize_t disk_events_poll_msecs_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); + if (!disk->ev) + return sprintf(buf, "-1\n"); + return sprintf(buf, "%ld\n", disk->ev->poll_msecs); } @@ -1917,6 +1923,9 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev, if (intv < 0 && intv != -1) return -EINVAL; + if (!disk->ev) + return -ENODEV; + disk_block_events(disk); disk->ev->poll_msecs = intv; __disk_unblock_events(disk, true); @@ -1981,7 +1990,7 @@ static void disk_alloc_events(struct gendisk *disk) { struct disk_events *ev; - if (!disk->fops->check_events) + if (!disk->fops->check_events || !disk->events) return; ev = kzalloc(sizeof(*ev), GFP_KERNEL); @@ -2003,14 +2012,14 @@ static void disk_alloc_events(struct gendisk *disk) static void disk_add_events(struct gendisk *disk) { - if (!disk->ev) - return; - /* FIXME: error handling */ if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0) pr_warn("%s: failed to create sysfs files for events\n", disk->disk_name); + if (!disk->ev) + return; + mutex_lock(&disk_events_mutex); list_add_tail(&disk->ev->node, &disk_events); mutex_unlock(&disk_events_mutex); @@ -2024,14 +2033,13 @@ static void disk_add_events(struct gendisk *disk) static void disk_del_events(struct gendisk *disk) { - if (!disk->ev) - return; + if (disk->ev) { + disk_block_events(disk); - disk_block_events(disk); - - mutex_lock(&disk_events_mutex); - list_del_init(&disk->ev->node); - mutex_unlock(&disk_events_mutex); + mutex_lock(&disk_events_mutex); + list_del_init(&disk->ev->node); + mutex_unlock(&disk_events_mutex); + } sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs); } diff --git a/block/opal_proto.h b/block/opal_proto.h index e20be8258854..b6e352cfe982 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -170,6 +170,8 @@ enum opal_token { OPAL_READLOCKED = 0x07, OPAL_WRITELOCKED = 0x08, OPAL_ACTIVEKEY = 0x0A, + /* lockingsp table */ + OPAL_LIFECYCLE = 0x06, /* locking info table */ OPAL_MAXRANGES = 0x04, /* mbr control */ diff --git a/block/sed-opal.c b/block/sed-opal.c index e0de4dd448b3..b1aa0cc25803 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -85,7 +85,6 @@ struct opal_dev { void *data; sec_send_recv *send_recv; - const struct opal_step *steps; struct mutex dev_lock; u16 comid; u32 hsn; @@ -157,7 +156,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = { /* C_PIN_TABLE object ID's */ - [OPAL_C_PIN_MSID] = + [OPAL_C_PIN_MSID] = { 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x84, 0x02}, [OPAL_C_PIN_SID] = { 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x00, 0x01}, @@ -181,7 +180,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = { * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00 * Section: 6.3 Assigned UIDs */ -static const u8 opalmethod[][OPAL_UID_LENGTH] = { +static const u8 opalmethod[][OPAL_METHOD_LENGTH] = { [OPAL_PROPERTIES] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x01 }, [OPAL_STARTSESSION] = @@ -217,6 +216,7 @@ static const u8 opalmethod[][OPAL_UID_LENGTH] = { }; static int end_opal_session_error(struct opal_dev *dev); +static int opal_discovery0_step(struct opal_dev *dev); struct opal_suspend_data { struct opal_lock_unlock unlk; @@ -382,37 +382,50 @@ static void check_geometry(struct opal_dev *dev, const void *data) dev->lowest_lba = geo->lowest_aligned_lba; } -static int next(struct opal_dev *dev) +static int execute_step(struct opal_dev *dev, + const struct opal_step *step, size_t stepIndex) { - const struct opal_step *step; - int state = 0, error = 0; + int error = step->fn(dev, step->data); - do { - step = &dev->steps[state]; - if (!step->fn) - break; + if (error) { + pr_debug("Step %zu (%pS) failed with error %d: %s\n", + stepIndex, step->fn, error, + opal_error_to_human(error)); + } + + return error; +} - error = step->fn(dev, step->data); - if (error) { - pr_debug("Error on step function: %d with error %d: %s\n", - state, error, - opal_error_to_human(error)); - - /* For each OPAL command we do a discovery0 then we - * start some sort of session. - * If we haven't passed state 1 then there was an error - * on discovery0 or during the attempt to start a - * session. Therefore we shouldn't attempt to terminate - * a session, as one has not yet been created. - */ - if (state > 1) { - end_opal_session_error(dev); - return error; - } +static int execute_steps(struct opal_dev *dev, + const struct opal_step *steps, size_t n_steps) +{ + size_t state = 0; + int error; - } - state++; - } while (!error); + /* first do a discovery0 */ + error = opal_discovery0_step(dev); + if (error) + return error; + + for (state = 0; state < n_steps; state++) { + error = execute_step(dev, &steps[state], state); + if (error) + goto out_error; + } + + return 0; + +out_error: + /* + * For each OPAL command the first step in steps starts some sort of + * session. If an error occurred in the initial discovery0 or if an + * error occurred in the first step (and thus stopping the loop with + * state == 0) then there was an error before or during the attempt to + * start a session. Therefore we shouldn't attempt to terminate a + * session, as one has not yet been created. + */ + if (state > 0) + end_opal_session_error(dev); return error; } @@ -510,15 +523,32 @@ static int opal_discovery0(struct opal_dev *dev, void *data) return opal_discovery0_end(dev); } -static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok) +static int opal_discovery0_step(struct opal_dev *dev) +{ + const struct opal_step discovery0_step = { + opal_discovery0, + }; + return execute_step(dev, &discovery0_step, 0); +} + +static bool can_add(int *err, struct opal_dev *cmd, size_t len) { if (*err) - return; - if (cmd->pos >= IO_BUFFER_LENGTH - 1) { - pr_debug("Error adding u8: end of buffer.\n"); + return false; + + if (len > IO_BUFFER_LENGTH || cmd->pos > IO_BUFFER_LENGTH - len) { + pr_debug("Error adding %zu bytes: end of buffer.\n", len); *err = -ERANGE; - return; + return false; } + + return true; +} + +static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok) +{ + if (!can_add(err, cmd, 1)) + return; cmd->cmd[cmd->pos++] = tok; } @@ -551,7 +581,6 @@ static void add_medium_atom_header(struct opal_dev *cmd, bool bytestring, static void add_token_u64(int *err, struct opal_dev *cmd, u64 number) { - size_t len; int msb; @@ -563,9 +592,8 @@ static void add_token_u64(int *err, struct opal_dev *cmd, u64 number) msb = fls64(number); len = DIV_ROUND_UP(msb, 8); - if (cmd->pos >= IO_BUFFER_LENGTH - len - 1) { + if (!can_add(err, cmd, len + 1)) { pr_debug("Error adding u64: end of buffer.\n"); - *err = -ERANGE; return; } add_short_atom_header(cmd, false, false, len); @@ -573,24 +601,19 @@ static void add_token_u64(int *err, struct opal_dev *cmd, u64 number) add_token_u8(err, cmd, number >> (len * 8)); } -static void add_token_bytestring(int *err, struct opal_dev *cmd, - const u8 *bytestring, size_t len) +static u8 *add_bytestring_header(int *err, struct opal_dev *cmd, size_t len) { size_t header_len = 1; bool is_short_atom = true; - if (*err) - return; - if (len & ~SHORT_ATOM_LEN_MASK) { header_len = 2; is_short_atom = false; } - if (len >= IO_BUFFER_LENGTH - cmd->pos - header_len) { + if (!can_add(err, cmd, header_len + len)) { pr_debug("Error adding bytestring: end of buffer.\n"); - *err = -ERANGE; - return; + return NULL; } if (is_short_atom) @@ -598,9 +621,19 @@ static void add_token_bytestring(int *err, struct opal_dev *cmd, else add_medium_atom_header(cmd, true, false, len); - memcpy(&cmd->cmd[cmd->pos], bytestring, len); - cmd->pos += len; + return &cmd->cmd[cmd->pos]; +} + +static void add_token_bytestring(int *err, struct opal_dev *cmd, + const u8 *bytestring, size_t len) +{ + u8 *start; + start = add_bytestring_header(err, cmd, len); + if (!start) + return; + memcpy(start, bytestring, len); + cmd->pos += len; } static int build_locking_range(u8 *buffer, size_t length, u8 lr) @@ -623,7 +656,7 @@ static int build_locking_range(u8 *buffer, size_t length, u8 lr) static int build_locking_user(u8 *buffer, size_t length, u8 lr) { if (length > OPAL_UID_LENGTH) { - pr_debug("Can't build locking range user, Length OOB\n"); + pr_debug("Can't build locking range user. Length OOB\n"); return -ERANGE; } @@ -649,6 +682,9 @@ static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn) struct opal_header *hdr; int err = 0; + /* close the parameter list opened from cmd_start */ + add_token_u8(&err, cmd, OPAL_ENDLIST); + add_token_u8(&err, cmd, OPAL_ENDOFDATA); add_token_u8(&err, cmd, OPAL_STARTLIST); add_token_u8(&err, cmd, 0); @@ -687,6 +723,11 @@ static const struct opal_resp_tok *response_get_token( { const struct opal_resp_tok *tok; + if (!resp) { + pr_debug("Response is NULL\n"); + return ERR_PTR(-EINVAL); + } + if (n >= resp->num) { pr_debug("Token number doesn't exist: %d, resp: %d\n", n, resp->num); @@ -869,27 +910,19 @@ static size_t response_get_string(const struct parsed_resp *resp, int n, const char **store) { u8 skip; - const struct opal_resp_tok *token; + const struct opal_resp_tok *tok; *store = NULL; - if (!resp) { - pr_debug("Response is NULL\n"); + tok = response_get_token(resp, n); + if (IS_ERR(tok)) return 0; - } - - if (n >= resp->num) { - pr_debug("Response has %d tokens. Can't access %d\n", - resp->num, n); - return 0; - } - token = &resp->toks[n]; - if (token->type != OPAL_DTA_TOKENID_BYTESTRING) { + if (tok->type != OPAL_DTA_TOKENID_BYTESTRING) { pr_debug("Token is not a byte string!\n"); return 0; } - switch (token->width) { + switch (tok->width) { case OPAL_WIDTH_TINY: case OPAL_WIDTH_SHORT: skip = 1; @@ -905,37 +938,29 @@ static size_t response_get_string(const struct parsed_resp *resp, int n, return 0; } - *store = token->pos + skip; - return token->len - skip; + *store = tok->pos + skip; + return tok->len - skip; } static u64 response_get_u64(const struct parsed_resp *resp, int n) { - if (!resp) { - pr_debug("Response is NULL\n"); - return 0; - } + const struct opal_resp_tok *tok; - if (n >= resp->num) { - pr_debug("Response has %d tokens. Can't access %d\n", - resp->num, n); + tok = response_get_token(resp, n); + if (IS_ERR(tok)) return 0; - } - if (resp->toks[n].type != OPAL_DTA_TOKENID_UINT) { - pr_debug("Token is not unsigned it: %d\n", - resp->toks[n].type); + if (tok->type != OPAL_DTA_TOKENID_UINT) { + pr_debug("Token is not unsigned int: %d\n", tok->type); return 0; } - if (!(resp->toks[n].width == OPAL_WIDTH_TINY || - resp->toks[n].width == OPAL_WIDTH_SHORT)) { - pr_debug("Atom is not short or tiny: %d\n", - resp->toks[n].width); + if (tok->width != OPAL_WIDTH_TINY && tok->width != OPAL_WIDTH_SHORT) { + pr_debug("Atom is not short or tiny: %d\n", tok->width); return 0; } - return resp->toks[n].stored.u; + return tok->stored.u; } static bool response_token_matches(const struct opal_resp_tok *token, u8 match) @@ -991,6 +1016,27 @@ static void clear_opal_cmd(struct opal_dev *dev) memset(dev->cmd, 0, IO_BUFFER_LENGTH); } +static int cmd_start(struct opal_dev *dev, const u8 *uid, const u8 *method) +{ + int err = 0; + + clear_opal_cmd(dev); + set_comid(dev, dev->comid); + + add_token_u8(&err, dev, OPAL_CALL); + add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH); + add_token_bytestring(&err, dev, method, OPAL_METHOD_LENGTH); + + /* + * Every method call is followed by its parameters enclosed within + * OPAL_STARTLIST and OPAL_ENDLIST tokens. We automatically open the + * parameter list here and close it later in cmd_finalize. + */ + add_token_u8(&err, dev, OPAL_STARTLIST); + + return err; +} + static int start_opal_session_cont(struct opal_dev *dev) { u32 hsn, tsn; @@ -1050,24 +1096,47 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont) return opal_send_recv(dev, cont); } +/* + * request @column from table @table on device @dev. On success, the column + * data will be available in dev->resp->tok[4] + */ +static int generic_get_column(struct opal_dev *dev, const u8 *table, + u64 column) +{ + int err; + + err = cmd_start(dev, table, opalmethod[OPAL_GET]); + + add_token_u8(&err, dev, OPAL_STARTLIST); + + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_STARTCOLUMN); + add_token_u64(&err, dev, column); + add_token_u8(&err, dev, OPAL_ENDNAME); + + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_ENDCOLUMN); + add_token_u64(&err, dev, column); + add_token_u8(&err, dev, OPAL_ENDNAME); + + add_token_u8(&err, dev, OPAL_ENDLIST); + + if (err) + return err; + + return finalize_and_send(dev, parse_and_check_status); +} + static int gen_key(struct opal_dev *dev, void *data) { u8 uid[OPAL_UID_LENGTH]; - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + int err; memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len)); kfree(dev->prev_data); dev->prev_data = NULL; - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_GENKEY], - OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_ENDLIST); + err = cmd_start(dev, uid, opalmethod[OPAL_GENKEY]); if (err) { pr_debug("Error building gen key command\n"); @@ -1105,62 +1174,39 @@ static int get_active_key_cont(struct opal_dev *dev) static int get_active_key(struct opal_dev *dev, void *data) { u8 uid[OPAL_UID_LENGTH]; - int err = 0; + int err; u8 *lr = data; - clear_opal_cmd(dev); - set_comid(dev, dev->comid); - err = build_locking_range(uid, sizeof(uid), *lr); if (err) return err; - err = 0; - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 3); /* startCloumn */ - add_token_u8(&err, dev, 10); /* ActiveKey */ - add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 4); /* endColumn */ - add_token_u8(&err, dev, 10); /* ActiveKey */ - add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); - add_token_u8(&err, dev, OPAL_ENDLIST); - if (err) { - pr_debug("Error building get active key command\n"); + err = generic_get_column(dev, uid, OPAL_ACTIVEKEY); + if (err) return err; - } - return finalize_and_send(dev, get_active_key_cont); + return get_active_key_cont(dev); } static int generic_lr_enable_disable(struct opal_dev *dev, u8 *uid, bool rle, bool wle, bool rl, bool wl) { - int err = 0; + int err; - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH); + err = cmd_start(dev, uid, opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 5); /* ReadLockEnabled */ + add_token_u8(&err, dev, OPAL_READLOCKENABLED); add_token_u8(&err, dev, rle); add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 6); /* WriteLockEnabled */ + add_token_u8(&err, dev, OPAL_WRITELOCKENABLED); add_token_u8(&err, dev, wle); add_token_u8(&err, dev, OPAL_ENDNAME); @@ -1176,7 +1222,6 @@ static int generic_lr_enable_disable(struct opal_dev *dev, add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); return err; } @@ -1197,10 +1242,7 @@ static int setup_locking_range(struct opal_dev *dev, void *data) u8 uid[OPAL_UID_LENGTH]; struct opal_user_lr_setup *setup = data; u8 lr; - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + int err; lr = setup->session.opal_key.lr; err = build_locking_range(uid, sizeof(uid), lr); @@ -1210,40 +1252,34 @@ static int setup_locking_range(struct opal_dev *dev, void *data) if (lr == 0) err = enable_global_lr(dev, uid, setup); else { - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], - OPAL_UID_LENGTH); + err = cmd_start(dev, uid, opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 3); /* Ranges Start */ + add_token_u8(&err, dev, OPAL_RANGESTART); add_token_u64(&err, dev, setup->range_start); add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 4); /* Ranges length */ + add_token_u8(&err, dev, OPAL_RANGELENGTH); add_token_u64(&err, dev, setup->range_length); add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 5); /*ReadLockEnabled */ + add_token_u8(&err, dev, OPAL_READLOCKENABLED); add_token_u64(&err, dev, !!setup->RLE); add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 6); /*WriteLockEnabled*/ + add_token_u8(&err, dev, OPAL_WRITELOCKENABLED); add_token_u64(&err, dev, !!setup->WLE); add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); - } if (err) { pr_debug("Error building Setup Locking range command.\n"); @@ -1261,29 +1297,21 @@ static int start_generic_opal_session(struct opal_dev *dev, u8 key_len) { u32 hsn; - int err = 0; + int err; if (key == NULL && auth != OPAL_ANYBODY_UID) return OPAL_INVAL_PARAM; - clear_opal_cmd(dev); - - set_comid(dev, dev->comid); hsn = GENERIC_HOST_SESSION_NUM; + err = cmd_start(dev, opaluid[OPAL_SMUID_UID], + opalmethod[OPAL_STARTSESSION]); - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION], - OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u64(&err, dev, hsn); add_token_bytestring(&err, dev, opaluid[sp_type], OPAL_UID_LENGTH); add_token_u8(&err, dev, 1); switch (auth) { case OPAL_ANYBODY_UID: - add_token_u8(&err, dev, OPAL_ENDLIST); break; case OPAL_ADMIN1_UID: case OPAL_SID_UID: @@ -1296,7 +1324,6 @@ static int start_generic_opal_session(struct opal_dev *dev, add_token_bytestring(&err, dev, opaluid[auth], OPAL_UID_LENGTH); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); break; default: pr_debug("Cannot start Admin SP session with auth %d\n", auth); @@ -1324,6 +1351,7 @@ static int start_SIDASP_opal_session(struct opal_dev *dev, void *data) if (!key) { const struct opal_key *okey = data; + ret = start_generic_opal_session(dev, OPAL_SID_UID, OPAL_ADMINSP_UID, okey->key, @@ -1341,6 +1369,7 @@ static int start_SIDASP_opal_session(struct opal_dev *dev, void *data) static int start_admin1LSP_opal_session(struct opal_dev *dev, void *data) { struct opal_key *key = data; + return start_generic_opal_session(dev, OPAL_ADMIN1_UID, OPAL_LOCKINGSP_UID, key->key, key->key_len); @@ -1356,30 +1385,21 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data) u8 *key = session->opal_key.key; u32 hsn = GENERIC_HOST_SESSION_NUM; - clear_opal_cmd(dev); - set_comid(dev, dev->comid); - - if (session->sum) { + if (session->sum) err = build_locking_user(lk_ul_user, sizeof(lk_ul_user), session->opal_key.lr); - if (err) - return err; - - } else if (session->who != OPAL_ADMIN1 && !session->sum) { + else if (session->who != OPAL_ADMIN1 && !session->sum) err = build_locking_user(lk_ul_user, sizeof(lk_ul_user), session->who - 1); - if (err) - return err; - } else + else memcpy(lk_ul_user, opaluid[OPAL_ADMIN1_UID], OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION], - OPAL_UID_LENGTH); + if (err) + return err; + + err = cmd_start(dev, opaluid[OPAL_SMUID_UID], + opalmethod[OPAL_STARTSESSION]); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u64(&err, dev, hsn); add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID], OPAL_UID_LENGTH); @@ -1392,7 +1412,6 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data) add_token_u8(&err, dev, 3); add_token_bytestring(&err, dev, lk_ul_user, OPAL_UID_LENGTH); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); if (err) { pr_debug("Error building STARTSESSION command.\n"); @@ -1404,18 +1423,10 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data) static int revert_tper(struct opal_dev *dev, void *data) { - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + int err; - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_ADMINSP_UID], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_REVERT], - OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_ENDLIST); + err = cmd_start(dev, opaluid[OPAL_ADMINSP_UID], + opalmethod[OPAL_REVERT]); if (err) { pr_debug("Error building REVERT TPER command.\n"); return err; @@ -1428,18 +1439,12 @@ static int internal_activate_user(struct opal_dev *dev, void *data) { struct opal_session_info *session = data; u8 uid[OPAL_UID_LENGTH]; - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + int err; memcpy(uid, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH); uid[7] = session->who; - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); + err = cmd_start(dev, uid, opalmethod[OPAL_SET]); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); add_token_u8(&err, dev, OPAL_STARTLIST); @@ -1449,7 +1454,6 @@ static int internal_activate_user(struct opal_dev *dev, void *data) add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); if (err) { pr_debug("Error building Activate UserN command.\n"); @@ -1463,20 +1467,12 @@ static int erase_locking_range(struct opal_dev *dev, void *data) { struct opal_session_info *session = data; u8 uid[OPAL_UID_LENGTH]; - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + int err; if (build_locking_range(uid, sizeof(uid), session->opal_key.lr) < 0) return -ERANGE; - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_ERASE], - OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_ENDLIST); + err = cmd_start(dev, uid, opalmethod[OPAL_ERASE]); if (err) { pr_debug("Error building Erase Locking Range Command.\n"); @@ -1488,26 +1484,20 @@ static int erase_locking_range(struct opal_dev *dev, void *data) static int set_mbr_done(struct opal_dev *dev, void *data) { u8 *mbr_done_tf = data; - int err = 0; + int err; - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + err = cmd_start(dev, opaluid[OPAL_MBRCONTROL], + opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 2); /* Done */ + add_token_u8(&err, dev, OPAL_MBRDONE); add_token_u8(&err, dev, *mbr_done_tf); /* Done T or F */ add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); if (err) { pr_debug("Error Building set MBR Done command\n"); @@ -1520,26 +1510,20 @@ static int set_mbr_done(struct opal_dev *dev, void *data) static int set_mbr_enable_disable(struct opal_dev *dev, void *data) { u8 *mbr_en_dis = data; - int err = 0; + int err; - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + err = cmd_start(dev, opaluid[OPAL_MBRCONTROL], + opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 1); + add_token_u8(&err, dev, OPAL_MBRENABLE); add_token_u8(&err, dev, *mbr_en_dis); add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); if (err) { pr_debug("Error Building set MBR done command\n"); @@ -1552,26 +1536,19 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data) static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid, struct opal_dev *dev) { - int err = 0; + int err; - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + err = cmd_start(dev, cpin_uid, opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, cpin_uid, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], - OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 3); /* PIN */ + add_token_u8(&err, dev, OPAL_PIN); add_token_bytestring(&err, dev, key, key_len); add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); return err; } @@ -1619,10 +1596,7 @@ static int add_user_to_lr(struct opal_dev *dev, void *data) u8 lr_buffer[OPAL_UID_LENGTH]; u8 user_uid[OPAL_UID_LENGTH]; struct opal_lock_unlock *lkul = data; - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); + int err; memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_RDLOCKED], OPAL_UID_LENGTH); @@ -1637,12 +1611,8 @@ static int add_user_to_lr(struct opal_dev *dev, void *data) user_uid[7] = lkul->session.who; - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], - OPAL_UID_LENGTH); + err = cmd_start(dev, lr_buffer, opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); @@ -1680,7 +1650,6 @@ static int add_user_to_lr(struct opal_dev *dev, void *data) add_token_u8(&err, dev, OPAL_ENDNAME); add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); if (err) { pr_debug("Error building add user to locking range command.\n"); @@ -1697,9 +1666,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data) u8 read_locked = 1, write_locked = 1; int err = 0; - clear_opal_cmd(dev); - set_comid(dev, dev->comid); - if (build_locking_range(lr_buffer, sizeof(lr_buffer), lkul->session.opal_key.lr) < 0) return -ERANGE; @@ -1714,17 +1680,15 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data) write_locked = 0; break; case OPAL_LK: - /* vars are initalized to locked */ + /* vars are initialized to locked */ break; default: pr_debug("Tried to set an invalid locking state... returning to uland\n"); return OPAL_INVAL_PARAM; } - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH); - add_token_u8(&err, dev, OPAL_STARTLIST); + err = cmd_start(dev, lr_buffer, opalmethod[OPAL_SET]); + add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, OPAL_VALUES); add_token_u8(&err, dev, OPAL_STARTLIST); @@ -1741,7 +1705,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data) add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); if (err) { pr_debug("Error building SET command.\n"); @@ -1775,7 +1738,7 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data) write_locked = 0; break; case OPAL_LK: - /* vars are initalized to locked */ + /* vars are initialized to locked */ break; default: pr_debug("Tried to set an invalid locking state.\n"); @@ -1796,17 +1759,10 @@ static int activate_lsp(struct opal_dev *dev, void *data) struct opal_lr_act *opal_act = data; u8 user_lr[OPAL_UID_LENGTH]; u8 uint_3 = 0x83; - int err = 0, i; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); - - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_ACTIVATE], - OPAL_UID_LENGTH); + int err, i; + err = cmd_start(dev, opaluid[OPAL_LOCKINGSP_UID], + opalmethod[OPAL_ACTIVATE]); if (opal_act->sum) { err = build_locking_range(user_lr, sizeof(user_lr), @@ -1814,7 +1770,6 @@ static int activate_lsp(struct opal_dev *dev, void *data) if (err) return err; - add_token_u8(&err, dev, OPAL_STARTLIST); add_token_u8(&err, dev, OPAL_STARTNAME); add_token_u8(&err, dev, uint_3); add_token_u8(&err, dev, 6); @@ -1829,11 +1784,6 @@ static int activate_lsp(struct opal_dev *dev, void *data) } add_token_u8(&err, dev, OPAL_ENDLIST); add_token_u8(&err, dev, OPAL_ENDNAME); - add_token_u8(&err, dev, OPAL_ENDLIST); - - } else { - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_ENDLIST); } if (err) { @@ -1844,17 +1794,19 @@ static int activate_lsp(struct opal_dev *dev, void *data) return finalize_and_send(dev, parse_and_check_status); } -static int get_lsp_lifecycle_cont(struct opal_dev *dev) +/* Determine if we're in the Manufactured Inactive or Active state */ +static int get_lsp_lifecycle(struct opal_dev *dev, void *data) { u8 lc_status; - int error = 0; + int err; - error = parse_and_check_status(dev); - if (error) - return error; + err = generic_get_column(dev, opaluid[OPAL_LOCKINGSP_UID], + OPAL_LIFECYCLE); + if (err) + return err; lc_status = response_get_u64(&dev->parsed, 4); - /* 0x08 is Manufacured Inactive */ + /* 0x08 is Manufactured Inactive */ /* 0x09 is Manufactured */ if (lc_status != OPAL_MANUFACTURED_INACTIVE) { pr_debug("Couldn't determine the status of the Lifecycle state\n"); @@ -1864,56 +1816,19 @@ static int get_lsp_lifecycle_cont(struct opal_dev *dev) return 0; } -/* Determine if we're in the Manufactured Inactive or Active state */ -static int get_lsp_lifecycle(struct opal_dev *dev, void *data) -{ - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); - - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH); - - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_STARTLIST); - - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 3); /* Start Column */ - add_token_u8(&err, dev, 6); /* Lifecycle Column */ - add_token_u8(&err, dev, OPAL_ENDNAME); - - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 4); /* End Column */ - add_token_u8(&err, dev, 6); /* Lifecycle Column */ - add_token_u8(&err, dev, OPAL_ENDNAME); - - add_token_u8(&err, dev, OPAL_ENDLIST); - add_token_u8(&err, dev, OPAL_ENDLIST); - - if (err) { - pr_debug("Error Building GET Lifecycle Status command\n"); - return err; - } - - return finalize_and_send(dev, get_lsp_lifecycle_cont); -} - -static int get_msid_cpin_pin_cont(struct opal_dev *dev) +static int get_msid_cpin_pin(struct opal_dev *dev, void *data) { const char *msid_pin; size_t strlen; - int error = 0; + int err; - error = parse_and_check_status(dev); - if (error) - return error; + err = generic_get_column(dev, opaluid[OPAL_C_PIN_MSID], OPAL_PIN); + if (err) + return err; strlen = response_get_string(&dev->parsed, 4, &msid_pin); if (!msid_pin) { - pr_debug("%s: Couldn't extract PIN from response\n", __func__); + pr_debug("Couldn't extract MSID_CPIN from response\n"); return OPAL_INVAL_PARAM; } @@ -1926,42 +1841,6 @@ static int get_msid_cpin_pin_cont(struct opal_dev *dev) return 0; } -static int get_msid_cpin_pin(struct opal_dev *dev, void *data) -{ - int err = 0; - - clear_opal_cmd(dev); - set_comid(dev, dev->comid); - - add_token_u8(&err, dev, OPAL_CALL); - add_token_bytestring(&err, dev, opaluid[OPAL_C_PIN_MSID], - OPAL_UID_LENGTH); - add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH); - - add_token_u8(&err, dev, OPAL_STARTLIST); - add_token_u8(&err, dev, OPAL_STARTLIST); - - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 3); /* Start Column */ - add_token_u8(&err, dev, 3); /* PIN */ - add_token_u8(&err, dev, OPAL_ENDNAME); - - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, 4); /* End Column */ - add_token_u8(&err, dev, 3); /* Lifecycle Column */ - add_token_u8(&err, dev, OPAL_ENDNAME); - - add_token_u8(&err, dev, OPAL_ENDLIST); - add_token_u8(&err, dev, OPAL_ENDLIST); - - if (err) { - pr_debug("Error building Get MSID CPIN PIN command.\n"); - return err; - } - - return finalize_and_send(dev, get_msid_cpin_pin_cont); -} - static int end_opal_session(struct opal_dev *dev, void *data) { int err = 0; @@ -1977,18 +1856,14 @@ static int end_opal_session(struct opal_dev *dev, void *data) static int end_opal_session_error(struct opal_dev *dev) { - const struct opal_step error_end_session[] = { - { end_opal_session, }, - { NULL, } + const struct opal_step error_end_session = { + end_opal_session, }; - dev->steps = error_end_session; - return next(dev); + return execute_step(dev, &error_end_session, 0); } -static inline void setup_opal_dev(struct opal_dev *dev, - const struct opal_step *steps) +static inline void setup_opal_dev(struct opal_dev *dev) { - dev->steps = steps; dev->tsn = 0; dev->hsn = 0; dev->prev_data = NULL; @@ -1996,15 +1871,11 @@ static inline void setup_opal_dev(struct opal_dev *dev, static int check_opal_support(struct opal_dev *dev) { - const struct opal_step steps[] = { - { opal_discovery0, }, - { NULL, } - }; int ret; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, steps); - ret = next(dev); + setup_opal_dev(dev); + ret = opal_discovery0_step(dev); dev->supported = !ret; mutex_unlock(&dev->dev_lock); return ret; @@ -2057,18 +1928,16 @@ static int opal_secure_erase_locking_range(struct opal_dev *dev, struct opal_session_info *opal_session) { const struct opal_step erase_steps[] = { - { opal_discovery0, }, { start_auth_opal_session, opal_session }, { get_active_key, &opal_session->opal_key.lr }, { gen_key, }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; int ret; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, erase_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, erase_steps, ARRAY_SIZE(erase_steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2077,17 +1946,15 @@ static int opal_erase_locking_range(struct opal_dev *dev, struct opal_session_info *opal_session) { const struct opal_step erase_steps[] = { - { opal_discovery0, }, { start_auth_opal_session, opal_session }, { erase_locking_range, opal_session }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; int ret; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, erase_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, erase_steps, ARRAY_SIZE(erase_steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2095,15 +1962,16 @@ static int opal_erase_locking_range(struct opal_dev *dev, static int opal_enable_disable_shadow_mbr(struct opal_dev *dev, struct opal_mbr_data *opal_mbr) { + u8 enable_disable = opal_mbr->enable_disable == OPAL_MBR_ENABLE ? + OPAL_TRUE : OPAL_FALSE; + const struct opal_step mbr_steps[] = { - { opal_discovery0, }, { start_admin1LSP_opal_session, &opal_mbr->key }, - { set_mbr_done, &opal_mbr->enable_disable }, + { set_mbr_done, &enable_disable }, { end_opal_session, }, { start_admin1LSP_opal_session, &opal_mbr->key }, - { set_mbr_enable_disable, &opal_mbr->enable_disable }, - { end_opal_session, }, - { NULL, } + { set_mbr_enable_disable, &enable_disable }, + { end_opal_session, } }; int ret; @@ -2112,8 +1980,8 @@ static int opal_enable_disable_shadow_mbr(struct opal_dev *dev, return -EINVAL; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, mbr_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, mbr_steps, ARRAY_SIZE(mbr_steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2130,7 +1998,7 @@ static int opal_save(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk) suspend->lr = lk_unlk->session.opal_key.lr; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, NULL); + setup_opal_dev(dev); add_suspend_info(dev, suspend); mutex_unlock(&dev->dev_lock); return 0; @@ -2140,11 +2008,9 @@ static int opal_add_user_to_lr(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk) { const struct opal_step steps[] = { - { opal_discovery0, }, { start_admin1LSP_opal_session, &lk_unlk->session.opal_key }, { add_user_to_lr, lk_unlk }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; int ret; @@ -2166,8 +2032,8 @@ static int opal_add_user_to_lr(struct opal_dev *dev, } mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, steps, ARRAY_SIZE(steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2175,16 +2041,14 @@ static int opal_add_user_to_lr(struct opal_dev *dev, static int opal_reverttper(struct opal_dev *dev, struct opal_key *opal) { const struct opal_step revert_steps[] = { - { opal_discovery0, }, { start_SIDASP_opal_session, opal }, - { revert_tper, }, /* controller will terminate session */ - { NULL, } + { revert_tper, } /* controller will terminate session */ }; int ret; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, revert_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, revert_steps, ARRAY_SIZE(revert_steps)); mutex_unlock(&dev->dev_lock); /* @@ -2201,37 +2065,34 @@ static int __opal_lock_unlock(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk) { const struct opal_step unlock_steps[] = { - { opal_discovery0, }, { start_auth_opal_session, &lk_unlk->session }, { lock_unlock_locking_range, lk_unlk }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; const struct opal_step unlock_sum_steps[] = { - { opal_discovery0, }, { start_auth_opal_session, &lk_unlk->session }, { lock_unlock_locking_range_sum, lk_unlk }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; - dev->steps = lk_unlk->session.sum ? unlock_sum_steps : unlock_steps; - return next(dev); + if (lk_unlk->session.sum) + return execute_steps(dev, unlock_sum_steps, + ARRAY_SIZE(unlock_sum_steps)); + else + return execute_steps(dev, unlock_steps, + ARRAY_SIZE(unlock_steps)); } static int __opal_set_mbr_done(struct opal_dev *dev, struct opal_key *key) { - u8 mbr_done_tf = 1; - const struct opal_step mbrdone_step [] = { - { opal_discovery0, }, + u8 mbr_done_tf = OPAL_TRUE; + const struct opal_step mbrdone_step[] = { { start_admin1LSP_opal_session, key }, { set_mbr_done, &mbr_done_tf }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; - dev->steps = mbrdone_step; - return next(dev); + return execute_steps(dev, mbrdone_step, ARRAY_SIZE(mbrdone_step)); } static int opal_lock_unlock(struct opal_dev *dev, @@ -2252,14 +2113,12 @@ static int opal_lock_unlock(struct opal_dev *dev, static int opal_take_ownership(struct opal_dev *dev, struct opal_key *opal) { const struct opal_step owner_steps[] = { - { opal_discovery0, }, { start_anybodyASP_opal_session, }, { get_msid_cpin_pin, }, { end_opal_session, }, { start_SIDASP_opal_session, opal }, { set_sid_cpin_pin, opal }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; int ret; @@ -2267,21 +2126,20 @@ static int opal_take_ownership(struct opal_dev *dev, struct opal_key *opal) return -ENODEV; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, owner_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, owner_steps, ARRAY_SIZE(owner_steps)); mutex_unlock(&dev->dev_lock); return ret; } -static int opal_activate_lsp(struct opal_dev *dev, struct opal_lr_act *opal_lr_act) +static int opal_activate_lsp(struct opal_dev *dev, + struct opal_lr_act *opal_lr_act) { const struct opal_step active_steps[] = { - { opal_discovery0, }, { start_SIDASP_opal_session, &opal_lr_act->key }, { get_lsp_lifecycle, }, { activate_lsp, opal_lr_act }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; int ret; @@ -2289,8 +2147,8 @@ static int opal_activate_lsp(struct opal_dev *dev, struct opal_lr_act *opal_lr_a return -EINVAL; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, active_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, active_steps, ARRAY_SIZE(active_steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2299,17 +2157,15 @@ static int opal_setup_locking_range(struct opal_dev *dev, struct opal_user_lr_setup *opal_lrs) { const struct opal_step lr_steps[] = { - { opal_discovery0, }, { start_auth_opal_session, &opal_lrs->session }, { setup_locking_range, opal_lrs }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; int ret; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, lr_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, lr_steps, ARRAY_SIZE(lr_steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2317,11 +2173,9 @@ static int opal_setup_locking_range(struct opal_dev *dev, static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw) { const struct opal_step pw_steps[] = { - { opal_discovery0, }, { start_auth_opal_session, &opal_pw->session }, { set_new_pw, &opal_pw->new_user_pw }, - { end_opal_session, }, - { NULL } + { end_opal_session, } }; int ret; @@ -2332,8 +2186,8 @@ static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw) return -EINVAL; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, pw_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, pw_steps, ARRAY_SIZE(pw_steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2342,11 +2196,9 @@ static int opal_activate_user(struct opal_dev *dev, struct opal_session_info *opal_session) { const struct opal_step act_steps[] = { - { opal_discovery0, }, { start_admin1LSP_opal_session, &opal_session->opal_key }, { internal_activate_user, opal_session }, - { end_opal_session, }, - { NULL, } + { end_opal_session, } }; int ret; @@ -2358,8 +2210,8 @@ static int opal_activate_user(struct opal_dev *dev, } mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, act_steps); - ret = next(dev); + setup_opal_dev(dev); + ret = execute_steps(dev, act_steps, ARRAY_SIZE(act_steps)); mutex_unlock(&dev->dev_lock); return ret; } @@ -2376,7 +2228,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev) return false; mutex_lock(&dev->dev_lock); - setup_opal_dev(dev, NULL); + setup_opal_dev(dev); list_for_each_entry(suspend, &dev->unlk_lst, node) { dev->tsn = 0; diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 0903e0803ec8..92b930cb3b72 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1829,6 +1829,7 @@ static int __init fd_probe_drives(void) disk->major = FLOPPY_MAJOR; disk->first_minor = drive; disk->fops = &floppy_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; sprintf(disk->disk_name, "fd%d", drive); disk->private_data = &unit[drive]; set_capacity(disk, 880*2); diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index b0dbbdfeb33e..c7b5c4671f05 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -2028,6 +2028,7 @@ static int __init atari_floppy_init (void) unit[i].disk->first_minor = i; sprintf(unit[i].disk->disk_name, "fd%d", i); unit[i].disk->fops = &floppy_fops; + unit[i].disk->events = DISK_EVENT_MEDIA_CHANGE; unit[i].disk->private_data = &unit[i]; set_capacity(unit[i].disk, MAX_DISK_SIZE * 2); add_disk(unit[i].disk); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 000a2f4c0e92..acd7af3630e9 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1317,10 +1317,6 @@ struct bm_extent { #define DRBD_MAX_SECTORS_FIXED_BM \ ((MD_128MB_SECT - MD_32kB_SECT - MD_4kB_SECT) * (1LL<<(BM_EXT_SHIFT-9))) -#if !defined(CONFIG_LBDAF) && BITS_PER_LONG == 32 -#define DRBD_MAX_SECTORS DRBD_MAX_SECTORS_32 -#define DRBD_MAX_SECTORS_FLEX DRBD_MAX_SECTORS_32 -#else #define DRBD_MAX_SECTORS DRBD_MAX_SECTORS_FIXED_BM /* 16 TB in units of sectors */ #if BITS_PER_LONG == 32 @@ -1333,7 +1329,6 @@ struct bm_extent { #define DRBD_MAX_SECTORS_FLEX (1UL << 51) /* corresponds to (1UL << 38) bits right now. */ #endif -#endif /* Estimate max bio size as 256 * PAGE_SIZE, * so for typical PAGE_SIZE of 4k, that is (1<<20) Byte. diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 95f608d1a098..8072bd9881e6 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4540,6 +4540,7 @@ static int __init do_floppy_init(void) disks[drive]->major = FLOPPY_MAJOR; disks[drive]->first_minor = TOMINOR(drive); disks[drive]->fops = &floppy_fops; + disks[drive]->events = DISK_EVENT_MEDIA_CHANGE; sprintf(disks[drive]->disk_name, "fd%d", drive); timer_setup(&motor_off_timer[drive], motor_off_callback, 0); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bf1c61cab8eb..102d79575895 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -264,12 +264,20 @@ lo_do_transfer(struct loop_device *lo, int cmd, return ret; } +static inline void loop_iov_iter_bvec(struct iov_iter *i, + unsigned int direction, const struct bio_vec *bvec, + unsigned long nr_segs, size_t count) +{ + iov_iter_bvec(i, direction, bvec, nr_segs, count); + i->type |= ITER_BVEC_FLAG_NO_REF; +} + static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) { struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); + loop_iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); @@ -347,7 +355,7 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, ssize_t len; rq_for_each_segment(bvec, rq, iter) { - iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); + loop_iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) return len; @@ -388,7 +396,7 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq, b.bv_offset = 0; b.bv_len = bvec.bv_len; - iov_iter_bvec(&i, READ, &b, 1, b.bv_len); + loop_iov_iter_bvec(&i, READ, &b, 1, b.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) { ret = len; @@ -555,7 +563,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, } atomic_set(&cmd->ref, 2); - iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); + loop_iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; @@ -900,6 +908,24 @@ static int loop_prepare_queue(struct loop_device *lo) return 0; } +static void loop_update_rotational(struct loop_device *lo) +{ + struct file *file = lo->lo_backing_file; + struct inode *file_inode = file->f_mapping->host; + struct block_device *file_bdev = file_inode->i_sb->s_bdev; + struct request_queue *q = lo->lo_queue; + bool nonrot = true; + + /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ + if (file_bdev) + nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev)); + + if (nonrot) + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + else + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); +} + static int loop_set_fd(struct loop_device *lo, fmode_t mode, struct block_device *bdev, unsigned int arg) { @@ -963,6 +989,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); + loop_update_rotational(lo); loop_update_dio(lo); set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 6d415b20fb70..001dbdcbf355 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -343,6 +343,7 @@ static void pcd_init_units(void) strcpy(disk->disk_name, cd->name); /* umm... */ disk->fops = &pcd_bdops; disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; + disk->events = DISK_EVENT_MEDIA_CHANGE; } } diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 0ff9b12d0e35..6f9ad3fc716f 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -897,6 +897,7 @@ static void pd_probe_drive(struct pd_unit *disk) p->fops = &pd_fops; p->major = major; p->first_minor = (disk - pd) << PD_BITS; + p->events = DISK_EVENT_MEDIA_CHANGE; disk->gd = p; p->private_data = disk; diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index 35e6e271b219..1e9c50a7256c 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -319,6 +319,7 @@ static void __init pf_init_units(void) disk->first_minor = unit; strcpy(disk->disk_name, pf->name); disk->fops = &pf_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; if (!(*drives[unit])[D_PRT]) pf_drive_count++; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index f5a71023f76c..024060165afa 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2761,7 +2761,6 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) /* inherit events of the host device */ disk->events = pd->bdev->bd_disk->events; - disk->async_events = pd->bdev->bd_disk->async_events; add_disk(disk); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 4e1d9b31f60c..cc61c5ce3ad5 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -102,7 +102,7 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev, rq_for_each_segment(bvec, req, iter) { unsigned long flags; - dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %lu\n", + dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %llu\n", __func__, __LINE__, i, bio_sectors(iter.bio), iter.bio->bi_iter.bi_sector); @@ -496,7 +496,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) dev->regions[dev->region_idx].size*priv->blocking_factor); dev_info(&dev->sbd.core, - "%s is a %s (%llu MiB total, %lu MiB for OtherOS)\n", + "%s is a %s (%llu MiB total, %llu MiB for OtherOS)\n", gendisk->disk_name, priv->model, priv->raw_capacity >> 11, get_capacity(gendisk) >> 11); diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 3fa6fcc34790..67b5ec281c6d 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -862,6 +862,7 @@ static int swim_floppy_init(struct swim_priv *swd) swd->unit[drive].disk->first_minor = drive; sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive); swd->unit[drive].disk->fops = &floppy_fops; + swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE; swd->unit[drive].disk->private_data = &swd->unit[drive]; set_capacity(swd->unit[drive].disk, 2880); add_disk(swd->unit[drive].disk); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 1e2ae90d7715..cf42729c788e 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1216,6 +1216,7 @@ static int swim3_attach(struct macio_dev *mdev, disk->first_minor = floppy_count; disk->fops = &floppy_fops; disk->private_data = fs; + disk->events = DISK_EVENT_MEDIA_CHANGE; disk->flags |= GENHD_FL_REMOVABLE; sprintf(disk->disk_name, "fd%d", floppy_count); set_capacity(disk, 2880); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2a7ca4a1e6f7..f1d90cd3dc47 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -693,7 +693,8 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set) { struct virtio_blk *vblk = set->driver_data; - return blk_mq_virtio_map_queues(&set->map[0], vblk->vdev, 0); + return blk_mq_virtio_map_queues(&set->map[HCTX_TYPE_DEFAULT], + vblk->vdev, 0); } #ifdef CONFIG_VIRTIO_BLK_SCSI diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index 32a21b8d1d85..464c9092bc8b 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -1032,6 +1032,7 @@ static int ace_setup(struct ace_device *ace) ace->gd->major = ace_major; ace->gd->first_minor = ace->id * ACE_NUM_MINORS; ace->gd->fops = &ace_fops; + ace->gd->events = DISK_EVENT_MEDIA_CHANGE; ace->gd->queue = ace->queue; ace->gd->private_data = ace; snprintf(ace->gd->disk_name, 32, "xs%c", ace->id + 'a'); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index f8b7345fe1cb..5cf3bade0d57 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -786,6 +786,7 @@ static int probe_gdrom(struct platform_device *devptr) goto probe_fail_cdrom_register; } gd.disk->fops = &gdrom_bdops; + gd.disk->events = DISK_EVENT_MEDIA_CHANGE; /* latch on to the interrupt */ err = gdrom_set_interrupt_handlers(); if (err) diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 1f03884a6808..3b15adc6ce98 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -1797,6 +1797,7 @@ static int ide_cd_probe(ide_drive_t *drive) ide_cd_read_toc(drive); g->fops = &idecd_ops; g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; + g->events = DISK_EVENT_MEDIA_CHANGE; device_add_disk(&drive->gendev, g, NULL); return 0; diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 4a6e1a413ead..46f2df288c6a 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -82,8 +82,9 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr) /* * ide-cd always generates media changed event if media is missing, which - * makes it impossible to use for proper event reporting, so disk->events - * is cleared to 0 and the following function is used only to trigger + * makes it impossible to use for proper event reporting, so + * DISK_EVENT_FLAG_UEVENT is cleared in disk->event_flags + * and the following function is used only to trigger * revalidation and never propagated to userland. */ unsigned int ide_cdrom_check_events_real(struct cdrom_device_info *cdi, diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index 04e008e8f6f9..f233b34ea0c0 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -299,8 +299,9 @@ static unsigned int ide_gd_check_events(struct gendisk *disk, /* * The following is used to force revalidation on the first open on * removeable devices, and never gets reported to userland as - * genhd->events is 0. This is intended as removeable ide disk - * can't really detect MEDIA_CHANGE events. + * DISK_EVENT_FLAG_UEVENT isn't set in genhd->event_flags. + * This is intended as removable ide disk can't really detect + * MEDIA_CHANGE events. */ ret = drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED; drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED; @@ -416,6 +417,7 @@ static int ide_gd_probe(ide_drive_t *drive) if (drive->dev_flags & IDE_DFLAG_REMOVABLE) g->flags = GENHD_FL_REMOVABLE; g->fops = &ide_gd_ops; + g->events = DISK_EVENT_MEDIA_CHANGE; device_add_disk(&drive->gendev, g, NULL); return 0; diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index 12b5216c2cfe..721efc493942 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -135,9 +135,8 @@ struct dm_dev *dm_snap_cow(struct dm_snapshot *snap); /* * Funtions to manipulate consecutive chunks */ -# if defined(CONFIG_LBDAF) || (BITS_PER_LONG == 64) -# define DM_CHUNK_CONSECUTIVE_BITS 8 -# define DM_CHUNK_NUMBER_BITS 56 +#define DM_CHUNK_CONSECUTIVE_BITS 8 +#define DM_CHUNK_NUMBER_BITS 56 static inline chunk_t dm_chunk_number(chunk_t chunk) { @@ -163,29 +162,6 @@ static inline void dm_consecutive_chunk_count_dec(struct dm_exception *e) e->new_chunk -= (1ULL << DM_CHUNK_NUMBER_BITS); } -# else -# define DM_CHUNK_CONSECUTIVE_BITS 0 - -static inline chunk_t dm_chunk_number(chunk_t chunk) -{ - return chunk; -} - -static inline unsigned dm_consecutive_chunk_count(struct dm_exception *e) -{ - return 0; -} - -static inline void dm_consecutive_chunk_count_inc(struct dm_exception *e) -{ -} - -static inline void dm_consecutive_chunk_count_dec(struct dm_exception *e) -{ -} - -# endif - /* * Return the number of sectors in the device. */ diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 7c678f50aaa3..05075613af93 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -88,14 +88,10 @@ struct journal_entry { #if BITS_PER_LONG == 64 #define journal_entry_set_sector(je, x) do { smp_wmb(); WRITE_ONCE((je)->u.sector, cpu_to_le64(x)); } while (0) -#define journal_entry_get_sector(je) le64_to_cpu((je)->u.sector) -#elif defined(CONFIG_LBDAF) -#define journal_entry_set_sector(je, x) do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32((x) >> 32)); } while (0) -#define journal_entry_get_sector(je) le64_to_cpu((je)->u.sector) #else -#define journal_entry_set_sector(je, x) do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32(0)); } while (0) -#define journal_entry_get_sector(je) le32_to_cpu((je)->u.s.sector_lo) +#define journal_entry_set_sector(je, x) do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32((x) >> 32)); } while (0) #endif +#define journal_entry_get_sector(je) le64_to_cpu((je)->u.sector) #define journal_entry_is_unused(je) ((je)->u.s.sector_hi == cpu_to_le32(-1)) #define journal_entry_set_unused(je) do { ((je)->u.s.sector_hi = cpu_to_le32(-1)); } while (0) #define journal_entry_is_inprogress(je) ((je)->u.s.sector_hi == cpu_to_le32(-2)) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 1cd4f991792c..3a62a46b75c7 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -490,10 +490,10 @@ void md_bitmap_print_sb(struct bitmap *bitmap) pr_debug(" magic: %08x\n", le32_to_cpu(sb->magic)); pr_debug(" version: %d\n", le32_to_cpu(sb->version)); pr_debug(" uuid: %08x.%08x.%08x.%08x\n", - le32_to_cpu(*(__u32 *)(sb->uuid+0)), - le32_to_cpu(*(__u32 *)(sb->uuid+4)), - le32_to_cpu(*(__u32 *)(sb->uuid+8)), - le32_to_cpu(*(__u32 *)(sb->uuid+12))); + le32_to_cpu(*(__le32 *)(sb->uuid+0)), + le32_to_cpu(*(__le32 *)(sb->uuid+4)), + le32_to_cpu(*(__le32 *)(sb->uuid+8)), + le32_to_cpu(*(__le32 *)(sb->uuid+12))); pr_debug(" events: %llu\n", (unsigned long long) le64_to_cpu(sb->events)); pr_debug("events cleared: %llu\n", diff --git a/drivers/md/md.c b/drivers/md/md.c index 05ffffb8b769..541015373f6a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -88,8 +88,7 @@ static struct kobj_type md_ktype; struct md_cluster_operations *md_cluster_ops; EXPORT_SYMBOL(md_cluster_ops); -struct module *md_cluster_mod; -EXPORT_SYMBOL(md_cluster_mod); +static struct module *md_cluster_mod; static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; @@ -132,24 +131,6 @@ static inline int speed_max(struct mddev *mddev) mddev->sync_speed_max : sysctl_speed_limit_max; } -static void * flush_info_alloc(gfp_t gfp_flags, void *data) -{ - return kzalloc(sizeof(struct flush_info), gfp_flags); -} -static void flush_info_free(void *flush_info, void *data) -{ - kfree(flush_info); -} - -static void * flush_bio_alloc(gfp_t gfp_flags, void *data) -{ - return kzalloc(sizeof(struct flush_bio), gfp_flags); -} -static void flush_bio_free(void *flush_bio, void *data) -{ - kfree(flush_bio); -} - static struct ctl_table_header *raid_table_header; static struct ctl_table raid_table[] = { @@ -423,54 +404,31 @@ static int md_congested(void *data, int bits) /* * Generic flush handling for md */ -static void submit_flushes(struct work_struct *ws) -{ - struct flush_info *fi = container_of(ws, struct flush_info, flush_work); - struct mddev *mddev = fi->mddev; - struct bio *bio = fi->bio; - - bio->bi_opf &= ~REQ_PREFLUSH; - md_handle_request(mddev, bio); - - mempool_free(fi, mddev->flush_pool); -} -static void md_end_flush(struct bio *fbio) +static void md_end_flush(struct bio *bio) { - struct flush_bio *fb = fbio->bi_private; - struct md_rdev *rdev = fb->rdev; - struct flush_info *fi = fb->fi; - struct bio *bio = fi->bio; - struct mddev *mddev = fi->mddev; + struct md_rdev *rdev = bio->bi_private; + struct mddev *mddev = rdev->mddev; rdev_dec_pending(rdev, mddev); - if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) { - /* an empty barrier - all done */ - bio_endio(bio); - mempool_free(fi, mddev->flush_pool); - } else { - INIT_WORK(&fi->flush_work, submit_flushes); - queue_work(md_wq, &fi->flush_work); - } + if (atomic_dec_and_test(&mddev->flush_pending)) { + /* The pre-request flush has finished */ + queue_work(md_wq, &mddev->flush_work); } - - mempool_free(fb, mddev->flush_bio_pool); - bio_put(fbio); + bio_put(bio); } -void md_flush_request(struct mddev *mddev, struct bio *bio) +static void md_submit_flush_data(struct work_struct *ws); + +static void submit_flushes(struct work_struct *ws) { + struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct md_rdev *rdev; - struct flush_info *fi; - - fi = mempool_alloc(mddev->flush_pool, GFP_NOIO); - - fi->bio = bio; - fi->mddev = mddev; - atomic_set(&fi->flush_pending, 1); + mddev->start_flush = ktime_get_boottime(); + INIT_WORK(&mddev->flush_work, md_submit_flush_data); + atomic_set(&mddev->flush_pending, 1); rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) if (rdev->raid_disk >= 0 && @@ -480,37 +438,74 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) * we reclaim rcu_read_lock */ struct bio *bi; - struct flush_bio *fb; atomic_inc(&rdev->nr_pending); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); - - fb = mempool_alloc(mddev->flush_bio_pool, GFP_NOIO); - fb->fi = fi; - fb->rdev = rdev; - bi = bio_alloc_mddev(GFP_NOIO, 0, mddev); - bio_set_dev(bi, rdev->bdev); bi->bi_end_io = md_end_flush; - bi->bi_private = fb; + bi->bi_private = rdev; + bio_set_dev(bi, rdev->bdev); bi->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - - atomic_inc(&fi->flush_pending); + atomic_inc(&mddev->flush_pending); submit_bio(bi); - rcu_read_lock(); rdev_dec_pending(rdev, mddev); } rcu_read_unlock(); + if (atomic_dec_and_test(&mddev->flush_pending)) + queue_work(md_wq, &mddev->flush_work); +} + +static void md_submit_flush_data(struct work_struct *ws) +{ + struct mddev *mddev = container_of(ws, struct mddev, flush_work); + struct bio *bio = mddev->flush_bio; + + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->last_flush = mddev->start_flush; + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + + if (bio->bi_iter.bi_size == 0) { + /* an empty barrier - all done */ + bio_endio(bio); + } else { + bio->bi_opf &= ~REQ_PREFLUSH; + md_handle_request(mddev, bio); + } +} - if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) { +void md_flush_request(struct mddev *mddev, struct bio *bio) +{ + ktime_t start = ktime_get_boottime(); + spin_lock_irq(&mddev->lock); + wait_event_lock_irq(mddev->sb_wait, + !mddev->flush_bio || + ktime_after(mddev->last_flush, start), + mddev->lock); + if (!ktime_after(mddev->last_flush, start)) { + WARN_ON(mddev->flush_bio); + mddev->flush_bio = bio; + bio = NULL; + } + spin_unlock_irq(&mddev->lock); + + if (!bio) { + INIT_WORK(&mddev->flush_work, submit_flushes); + queue_work(md_wq, &mddev->flush_work); + } else { + /* flush was performed for some other bio while we waited. */ + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); - mempool_free(fi, mddev->flush_pool); - } else { - INIT_WORK(&fi->flush_work, submit_flushes); - queue_work(md_wq, &fi->flush_work); + else { + bio->bi_opf &= ~REQ_PREFLUSH; + mddev->pers->make_request(mddev, bio); } } } @@ -560,6 +555,7 @@ void mddev_init(struct mddev *mddev) atomic_set(&mddev->openers, 0); atomic_set(&mddev->active_io, 0); spin_lock_init(&mddev->lock); + atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); init_waitqueue_head(&mddev->recovery_wait); mddev->reshape_position = MaxSector; @@ -1109,8 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor * (not needed for Linear and RAID0 as metadata doesn't * record this size) */ - if (IS_ENABLED(CONFIG_LBDAF) && (u64)rdev->sectors >= (2ULL << 32) && - sb->level >= 1) + if ((u64)rdev->sectors >= (2ULL << 32) && sb->level >= 1) rdev->sectors = (sector_t)(2ULL << 32) - 2; if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1) @@ -1408,8 +1403,7 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) /* Limit to 4TB as metadata cannot record more than that. * 4TB == 2^32 KB, or 2*2^32 sectors. */ - if (IS_ENABLED(CONFIG_LBDAF) && (u64)num_sectors >= (2ULL << 32) && - rdev->mddev->level >= 1) + if ((u64)num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1) num_sectors = (sector_t)(2ULL << 32) - 2; do { md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, @@ -1553,7 +1547,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ */ s32 offset; sector_t bb_sector; - u64 *bbp; + __le64 *bbp; int i; int sectors = le16_to_cpu(sb->bblog_size); if (sectors > (PAGE_SIZE / 512)) @@ -1565,7 +1559,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ if (!sync_page_io(rdev, bb_sector, sectors << 9, rdev->bb_page, REQ_OP_READ, 0, true)) return -EIO; - bbp = (u64 *)page_address(rdev->bb_page); + bbp = (__le64 *)page_address(rdev->bb_page); rdev->badblocks.shift = sb->bblog_shift; for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) { u64 bb = le64_to_cpu(*bbp); @@ -1877,7 +1871,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) md_error(mddev, rdev); else { struct badblocks *bb = &rdev->badblocks; - u64 *bbp = (u64 *)page_address(rdev->bb_page); + __le64 *bbp = (__le64 *)page_address(rdev->bb_page); u64 *p = bb->page; sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS); if (bb->changed) { @@ -2855,8 +2849,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) err = 0; } } else if (cmd_match(buf, "re-add")) { - if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) && - rdev->saved_raid_disk >= 0) { + if (!rdev->mddev->pers) + err = -EINVAL; + else if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) && + rdev->saved_raid_disk >= 0) { /* clear_bit is performed _after_ all the devices * have their local Faulty bit cleared. If any writes * happen in the meantime in the local node, they @@ -5511,22 +5507,6 @@ int md_run(struct mddev *mddev) if (err) return err; } - if (mddev->flush_pool == NULL) { - mddev->flush_pool = mempool_create(NR_FLUSH_INFOS, flush_info_alloc, - flush_info_free, mddev); - if (!mddev->flush_pool) { - err = -ENOMEM; - goto abort; - } - } - if (mddev->flush_bio_pool == NULL) { - mddev->flush_bio_pool = mempool_create(NR_FLUSH_BIOS, flush_bio_alloc, - flush_bio_free, mddev); - if (!mddev->flush_bio_pool) { - err = -ENOMEM; - goto abort; - } - } spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); @@ -5686,11 +5666,8 @@ int md_run(struct mddev *mddev) return 0; abort: - mempool_destroy(mddev->flush_bio_pool); - mddev->flush_bio_pool = NULL; - mempool_destroy(mddev->flush_pool); - mddev->flush_pool = NULL; - + bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->sync_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -5894,14 +5871,6 @@ static void __md_stop(struct mddev *mddev) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - if (mddev->flush_bio_pool) { - mempool_destroy(mddev->flush_bio_pool); - mddev->flush_bio_pool = NULL; - } - if (mddev->flush_pool) { - mempool_destroy(mddev->flush_pool); - mddev->flush_pool = NULL; - } } void md_stop(struct mddev *mddev) @@ -9257,7 +9226,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) * reshape is happening in the remote node, we need to * update reshape_position and call start_reshape. */ - mddev->reshape_position = sb->reshape_position; + mddev->reshape_position = le64_to_cpu(sb->reshape_position); if (mddev->pers->update_reshape_pos) mddev->pers->update_reshape_pos(mddev); if (mddev->pers->start_reshape) diff --git a/drivers/md/md.h b/drivers/md/md.h index c52afb52c776..257cb4c9e22b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -252,19 +252,6 @@ enum mddev_sb_flags { MD_SB_NEED_REWRITE, /* metadata write needs to be repeated */ }; -#define NR_FLUSH_INFOS 8 -#define NR_FLUSH_BIOS 64 -struct flush_info { - struct bio *bio; - struct mddev *mddev; - struct work_struct flush_work; - atomic_t flush_pending; -}; -struct flush_bio { - struct flush_info *fi; - struct md_rdev *rdev; -}; - struct mddev { void *private; struct md_personality *pers; @@ -470,8 +457,16 @@ struct mddev { * metadata and bitmap writes */ - mempool_t *flush_pool; - mempool_t *flush_bio_pool; + /* Generic flush handling. + * The last to finish preflush schedules a worker to submit + * the rest of the request (without the REQ_PREFLUSH flag). + */ + struct bio *flush_bio; + atomic_t flush_pending; + ktime_t start_flush, last_flush; /* last_flush is when the last completed + * flush was started. + */ + struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index c033bfcb209e..2b0a715e70c9 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -711,6 +711,8 @@ static bool is_full_stripe_write(struct stripe_head *sh) } static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) + __acquires(&sh1->stripe_lock) + __acquires(&sh2->stripe_lock) { if (sh1 > sh2) { spin_lock_irq(&sh2->stripe_lock); @@ -722,6 +724,8 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) } static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) + __releases(&sh1->stripe_lock) + __releases(&sh2->stripe_lock) { spin_unlock(&sh1->stripe_lock); spin_unlock_irq(&sh2->stripe_lock); @@ -4223,26 +4227,15 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, case check_state_check_result: sh->check_state = check_state_idle; + if (s->failed > 1) + break; /* handle a successful check operation, if parity is correct * we are done. Otherwise update the mismatch count and repair * parity if !MD_RECOVERY_CHECK */ if (sh->ops.zero_sum_result == 0) { - /* both parities are correct */ - if (!s->failed) - set_bit(STRIPE_INSYNC, &sh->state); - else { - /* in contrast to the raid5 case we can validate - * parity, but still have a failure to write - * back - */ - sh->check_state = check_state_compute_result; - /* Returning at this point means that we may go - * off and bring p and/or q uptodate again so - * we make sure to check zero_sum_result again - * to verify if p or q need writeback - */ - } + /* Any parity checked was correct */ + set_bit(STRIPE_INSYNC, &sh->state); } else { atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) { @@ -6166,6 +6159,8 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio, static int handle_active_stripes(struct r5conf *conf, int group, struct r5worker *worker, struct list_head *temp_inactive_list) + __releases(&conf->device_lock) + __acquires(&conf->device_lock) { struct stripe_head *batch[MAX_STRIPE_BATCH], *sh; int i, batch_size = 0, hash; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index d271bd731af7..01f40672507f 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -391,7 +391,7 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn) bb_present = badblocks_check(&nd_region->bb, meta_start, meta_num, &first_bad, &num_bad); if (bb_present) { - dev_dbg(&nd_pfn->dev, "meta: %x badblocks at %lx\n", + dev_dbg(&nd_pfn->dev, "meta: %x badblocks at %llx\n", num_bad, first_bad); nsoff = ALIGN_DOWN((nd_region->ndr_start + (first_bad << 9)) - nsio->res.start, @@ -410,7 +410,7 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn) } if (rc) { dev_err(&nd_pfn->dev, - "error clearing %x badblocks at %lx\n", + "error clearing %x badblocks at %llx\n", num_bad, first_bad); return rc; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2c43e12b70af..248ff3b48041 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1105,7 +1105,7 @@ static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl, error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id)); if (error) { - dev_warn(ctrl->device, "Identify namespace failed\n"); + dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error); kfree(id); return NULL; } @@ -1588,7 +1588,7 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) static void nvme_update_disk_info(struct gendisk *disk, struct nvme_ns *ns, struct nvme_id_ns *id) { - sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9); + sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9); unsigned short bs = 1 << ns->lba_shift; blk_mq_freeze_queue(disk->queue); @@ -2549,7 +2549,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->crdt[2] = le16_to_cpu(id->crdt3); ctrl->oacs = le16_to_cpu(id->oacs); - ctrl->oncs = le16_to_cpup(&id->oncs); + ctrl->oncs = le16_to_cpu(id->oncs); ctrl->oaes = le32_to_cpu(id->oaes); atomic_set(&ctrl->abort_limit, id->acl + 1); ctrl->vwc = id->vwc; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a90cf5d63aac..c1eecde6b853 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -177,7 +177,6 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl) * commands and one for I/O commands). */ struct nvme_queue { - struct device *q_dmadev; struct nvme_dev *dev; spinlock_t sq_lock; struct nvme_command *sq_cmds; @@ -189,7 +188,7 @@ struct nvme_queue { dma_addr_t cq_dma_addr; u32 __iomem *q_db; u16 q_depth; - s16 cq_vector; + u16 cq_vector; u16 sq_tail; u16 last_sq_tail; u16 cq_head; @@ -200,6 +199,7 @@ struct nvme_queue { #define NVMEQ_ENABLED 0 #define NVMEQ_SQ_CMB 1 #define NVMEQ_DELETE_ERROR 2 +#define NVMEQ_POLLED 3 u32 *dbbuf_sq_db; u32 *dbbuf_cq_db; u32 *dbbuf_sq_ei; @@ -208,10 +208,10 @@ struct nvme_queue { }; /* - * The nvme_iod describes the data in an I/O, including the list of PRP - * entries. You can't see it in this data structure because C doesn't let - * me express that. Use nvme_init_iod to ensure there's enough space - * allocated to store the PRP list. + * The nvme_iod describes the data in an I/O. + * + * The sg pointer contains the list of PRP/SGL chunk allocations in addition + * to the actual struct scatterlist. */ struct nvme_iod { struct nvme_request req; @@ -220,11 +220,10 @@ struct nvme_iod { int aborted; int npages; /* In the PRP list. 0 means small pool in use */ int nents; /* Used in scatterlist */ - int length; /* Of data, in bytes */ dma_addr_t first_dma; - struct scatterlist meta_sg; /* metadata requires single contiguous buffer */ + unsigned int dma_len; /* length of single DMA segment mapping */ + dma_addr_t meta_dma; struct scatterlist *sg; - struct scatterlist inline_sg[0]; }; /* @@ -372,12 +371,6 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, } /* - * Max size of iod being embedded in the request payload - */ -#define NVME_INT_PAGES 2 -#define NVME_INT_BYTES(dev) (NVME_INT_PAGES * (dev)->ctrl.page_size) - -/* * Will slightly overestimate the number of pages needed. This is OK * as it only leads to a small amount of wasted memory for the lifetime of * the I/O. @@ -411,15 +404,6 @@ static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev, return alloc_size + sizeof(struct scatterlist) * nseg; } -static unsigned int nvme_pci_cmd_size(struct nvme_dev *dev, bool use_sgl) -{ - unsigned int alloc_size = nvme_pci_iod_alloc_size(dev, - NVME_INT_BYTES(dev), NVME_INT_PAGES, - use_sgl); - - return sizeof(struct nvme_iod) + alloc_size; -} - static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { @@ -584,37 +568,26 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) return true; } -static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev) +static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) { - struct nvme_iod *iod = blk_mq_rq_to_pdu(rq); - int nseg = blk_rq_nr_phys_segments(rq); - unsigned int size = blk_rq_payload_bytes(rq); - - iod->use_sgl = nvme_pci_use_sgls(dev, rq); + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + enum dma_data_direction dma_dir = rq_data_dir(req) ? + DMA_TO_DEVICE : DMA_FROM_DEVICE; + const int last_prp = dev->ctrl.page_size / sizeof(__le64) - 1; + dma_addr_t dma_addr = iod->first_dma, next_dma_addr; + int i; - if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) { - iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC); - if (!iod->sg) - return BLK_STS_RESOURCE; - } else { - iod->sg = iod->inline_sg; + if (iod->dma_len) { + dma_unmap_page(dev->dev, dma_addr, iod->dma_len, dma_dir); + return; } - iod->aborted = 0; - iod->npages = -1; - iod->nents = 0; - iod->length = size; + WARN_ON_ONCE(!iod->nents); - return BLK_STS_OK; -} + /* P2PDMA requests do not need to be unmapped */ + if (!is_pci_p2pdma_page(sg_page(iod->sg))) + dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req)); -static void nvme_free_iod(struct nvme_dev *dev, struct request *req) -{ - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - const int last_prp = dev->ctrl.page_size / sizeof(__le64) - 1; - dma_addr_t dma_addr = iod->first_dma, next_dma_addr; - - int i; if (iod->npages == 0) dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], @@ -638,8 +611,7 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req) dma_addr = next_dma_addr; } - if (iod->sg != iod->inline_sg) - mempool_free(iod->sg, dev->iod_mempool); + mempool_free(iod->sg, dev->iod_mempool); } static void nvme_print_sgl(struct scatterlist *sgl, int nents) @@ -829,80 +801,103 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, return BLK_STS_OK; } +static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev, + struct request *req, struct nvme_rw_command *cmnd, + struct bio_vec *bv) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + unsigned int first_prp_len = dev->ctrl.page_size - bv->bv_offset; + + iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0); + if (dma_mapping_error(dev->dev, iod->first_dma)) + return BLK_STS_RESOURCE; + iod->dma_len = bv->bv_len; + + cmnd->dptr.prp1 = cpu_to_le64(iod->first_dma); + if (bv->bv_len > first_prp_len) + cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma + first_prp_len); + return 0; +} + +static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev, + struct request *req, struct nvme_rw_command *cmnd, + struct bio_vec *bv) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + + iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0); + if (dma_mapping_error(dev->dev, iod->first_dma)) + return BLK_STS_RESOURCE; + iod->dma_len = bv->bv_len; + + cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma); + cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len); + cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4; + return 0; +} + static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct request_queue *q = req->q; - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; - blk_status_t ret = BLK_STS_IOERR; + blk_status_t ret = BLK_STS_RESOURCE; int nr_mapped; + if (blk_rq_nr_phys_segments(req) == 1) { + struct bio_vec bv = req_bvec(req); + + if (!is_pci_p2pdma_page(bv.bv_page)) { + if (bv.bv_offset + bv.bv_len <= dev->ctrl.page_size * 2) + return nvme_setup_prp_simple(dev, req, + &cmnd->rw, &bv); + + if (iod->nvmeq->qid && + dev->ctrl.sgls & ((1 << 0) | (1 << 1))) + return nvme_setup_sgl_simple(dev, req, + &cmnd->rw, &bv); + } + } + + iod->dma_len = 0; + iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC); + if (!iod->sg) + return BLK_STS_RESOURCE; sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); - iod->nents = blk_rq_map_sg(q, req, iod->sg); + iod->nents = blk_rq_map_sg(req->q, req, iod->sg); if (!iod->nents) goto out; - ret = BLK_STS_RESOURCE; - if (is_pci_p2pdma_page(sg_page(iod->sg))) nr_mapped = pci_p2pdma_map_sg(dev->dev, iod->sg, iod->nents, - dma_dir); + rq_dma_dir(req)); else nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, - dma_dir, DMA_ATTR_NO_WARN); + rq_dma_dir(req), DMA_ATTR_NO_WARN); if (!nr_mapped) goto out; + iod->use_sgl = nvme_pci_use_sgls(dev, req); if (iod->use_sgl) ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped); else ret = nvme_pci_setup_prps(dev, req, &cmnd->rw); - - if (ret != BLK_STS_OK) - goto out_unmap; - - ret = BLK_STS_IOERR; - if (blk_integrity_rq(req)) { - if (blk_rq_count_integrity_sg(q, req->bio) != 1) - goto out_unmap; - - sg_init_table(&iod->meta_sg, 1); - if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1) - goto out_unmap; - - if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir)) - goto out_unmap; - - cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg)); - } - - return BLK_STS_OK; - -out_unmap: - dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir); out: + if (ret != BLK_STS_OK) + nvme_unmap_data(dev, req); return ret; } -static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) +static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req, + struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; - - if (iod->nents) { - /* P2PDMA requests do not need to be unmapped */ - if (!is_pci_p2pdma_page(sg_page(iod->sg))) - dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir); - if (blk_integrity_rq(req)) - dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir); - } - - nvme_cleanup_cmd(req); - nvme_free_iod(dev, req); + iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req), + rq_dma_dir(req), 0); + if (dma_mapping_error(dev->dev, iod->meta_dma)) + return BLK_STS_IOERR; + cmnd->rw.metadata = cpu_to_le64(iod->meta_dma); + return 0; } /* @@ -915,9 +910,14 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, struct nvme_queue *nvmeq = hctx->driver_data; struct nvme_dev *dev = nvmeq->dev; struct request *req = bd->rq; + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_command cmnd; blk_status_t ret; + iod->aborted = 0; + iod->npages = -1; + iod->nents = 0; + /* * We should not need to do this, but we're still using this to * ensure we can drain requests on a dying queue. @@ -929,21 +929,23 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, if (ret) return ret; - ret = nvme_init_iod(req, dev); - if (ret) - goto out_free_cmd; - if (blk_rq_nr_phys_segments(req)) { ret = nvme_map_data(dev, req, &cmnd); if (ret) - goto out_cleanup_iod; + goto out_free_cmd; + } + + if (blk_integrity_rq(req)) { + ret = nvme_map_metadata(dev, req, &cmnd); + if (ret) + goto out_unmap_data; } blk_mq_start_request(req); nvme_submit_cmd(nvmeq, &cmnd, bd->last); return BLK_STS_OK; -out_cleanup_iod: - nvme_free_iod(dev, req); +out_unmap_data: + nvme_unmap_data(dev, req); out_free_cmd: nvme_cleanup_cmd(req); return ret; @@ -952,8 +954,14 @@ out_free_cmd: static void nvme_pci_complete_rq(struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + struct nvme_dev *dev = iod->nvmeq->dev; - nvme_unmap_data(iod->nvmeq->dev, req); + nvme_cleanup_cmd(req); + if (blk_integrity_rq(req)) + dma_unmap_page(dev->dev, iod->meta_dma, + rq_integrity_vec(req)->bv_len, rq_data_dir(req)); + if (blk_rq_nr_phys_segments(req)) + nvme_unmap_data(dev, req); nvme_complete_rq(req); } @@ -1088,7 +1096,7 @@ static int nvme_poll_irqdisable(struct nvme_queue *nvmeq, unsigned int tag) * using the CQ lock. For normal interrupt driven threads we have * to disable the interrupt to avoid racing with it. */ - if (nvmeq->cq_vector == -1) { + if (test_bit(NVMEQ_POLLED, &nvmeq->flags)) { spin_lock(&nvmeq->cq_poll_lock); found = nvme_process_cq(nvmeq, &start, &end, tag); spin_unlock(&nvmeq->cq_poll_lock); @@ -1148,7 +1156,7 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid, struct nvme_command c; int flags = NVME_QUEUE_PHYS_CONTIG; - if (vector != -1) + if (!test_bit(NVMEQ_POLLED, &nvmeq->flags)) flags |= NVME_CQ_IRQ_ENABLED; /* @@ -1161,10 +1169,7 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid, c.create_cq.cqid = cpu_to_le16(qid); c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1); c.create_cq.cq_flags = cpu_to_le16(flags); - if (vector != -1) - c.create_cq.irq_vector = cpu_to_le16(vector); - else - c.create_cq.irq_vector = 0; + c.create_cq.irq_vector = cpu_to_le16(vector); return nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0); } @@ -1371,16 +1376,16 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) static void nvme_free_queue(struct nvme_queue *nvmeq) { - dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth), + dma_free_coherent(nvmeq->dev->dev, CQ_SIZE(nvmeq->q_depth), (void *)nvmeq->cqes, nvmeq->cq_dma_addr); if (!nvmeq->sq_cmds) return; if (test_and_clear_bit(NVMEQ_SQ_CMB, &nvmeq->flags)) { - pci_free_p2pmem(to_pci_dev(nvmeq->q_dmadev), + pci_free_p2pmem(to_pci_dev(nvmeq->dev->dev), nvmeq->sq_cmds, SQ_SIZE(nvmeq->q_depth)); } else { - dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth), + dma_free_coherent(nvmeq->dev->dev, SQ_SIZE(nvmeq->q_depth), nvmeq->sq_cmds, nvmeq->sq_dma_addr); } } @@ -1410,10 +1415,8 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq) nvmeq->dev->online_queues--; if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q) blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q); - if (nvmeq->cq_vector == -1) - return 0; - pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq); - nvmeq->cq_vector = -1; + if (!test_and_clear_bit(NVMEQ_POLLED, &nvmeq->flags)) + pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq); return 0; } @@ -1498,7 +1501,6 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth) if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth)) goto free_cqdma; - nvmeq->q_dmadev = dev->dev; nvmeq->dev = dev; spin_lock_init(&nvmeq->sq_lock); spin_lock_init(&nvmeq->cq_poll_lock); @@ -1507,7 +1509,6 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth) nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; nvmeq->q_depth = depth; nvmeq->qid = qid; - nvmeq->cq_vector = -1; dev->ctrl.queue_count++; return 0; @@ -1552,7 +1553,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) { struct nvme_dev *dev = nvmeq->dev; int result; - s16 vector; + u16 vector = 0; clear_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags); @@ -1563,7 +1564,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) if (!polled) vector = dev->num_vecs == 1 ? 0 : qid; else - vector = -1; + set_bit(NVMEQ_POLLED, &nvmeq->flags); result = adapter_alloc_cq(dev, qid, nvmeq, vector); if (result) @@ -1578,7 +1579,8 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) nvmeq->cq_vector = vector; nvme_init_queue(nvmeq, qid); - if (vector != -1) { + if (!polled) { + nvmeq->cq_vector = vector; result = queue_request_irq(nvmeq); if (result < 0) goto release_sq; @@ -1588,7 +1590,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) return result; release_sq: - nvmeq->cq_vector = -1; dev->online_queues--; adapter_delete_sq(dev, qid); release_cq: @@ -1639,7 +1640,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH; dev->admin_tagset.timeout = ADMIN_TIMEOUT; dev->admin_tagset.numa_node = dev_to_node(dev->dev); - dev->admin_tagset.cmd_size = nvme_pci_cmd_size(dev, false); + dev->admin_tagset.cmd_size = sizeof(struct nvme_iod); dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; dev->admin_tagset.driver_data = dev; @@ -1730,7 +1731,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) nvme_init_queue(nvmeq, 0); result = queue_request_irq(nvmeq); if (result) { - nvmeq->cq_vector = -1; + dev->online_queues--; return result; } @@ -2171,10 +2172,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) * number of interrupts. */ result = queue_request_irq(adminq); - if (result) { - adminq->cq_vector = -1; + if (result) return result; - } set_bit(NVMEQ_ENABLED, &adminq->flags); result = nvme_create_io_queues(dev); @@ -2286,11 +2285,7 @@ static int nvme_dev_add(struct nvme_dev *dev) dev->tagset.numa_node = dev_to_node(dev->dev); dev->tagset.queue_depth = min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1; - dev->tagset.cmd_size = nvme_pci_cmd_size(dev, false); - if ((dev->ctrl.sgls & ((1 << 0) | (1 << 1))) && sgl_threshold) { - dev->tagset.cmd_size = max(dev->tagset.cmd_size, - nvme_pci_cmd_size(dev, true)); - } + dev->tagset.cmd_size = sizeof(struct nvme_iod); dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE; dev->tagset.driver_data = dev; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b3e765a95af8..4d8dd29479c0 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -214,6 +214,8 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid) { struct nvmet_ctrl *ctrl; + lockdep_assert_held(&subsys->lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) { nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid)); if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR)) @@ -494,13 +496,14 @@ int nvmet_ns_enable(struct nvmet_ns *ns) int ret; mutex_lock(&subsys->lock); - ret = -EMFILE; - if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) - goto out_unlock; ret = 0; if (ns->enabled) goto out_unlock; + ret = -EMFILE; + if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) + goto out_unlock; + ret = nvmet_bdev_ns_enable(ns); if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 98b7b1f4ee96..9369a11fe7a9 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -128,12 +128,12 @@ struct nvmet_fc_tgt_queue { struct nvmet_cq nvme_cq; struct nvmet_sq nvme_sq; struct nvmet_fc_tgt_assoc *assoc; - struct nvmet_fc_fcp_iod *fod; /* array of fcp_iods */ struct list_head fod_list; struct list_head pending_cmd_list; struct list_head avail_defer_list; struct workqueue_struct *work_q; struct kref ref; + struct nvmet_fc_fcp_iod fod[]; /* array of fcp_iods */ } __aligned(sizeof(unsigned long long)); struct nvmet_fc_tgt_assoc { @@ -588,9 +588,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, if (qid > NVMET_NR_QUEUES) return NULL; - queue = kzalloc((sizeof(*queue) + - (sizeof(struct nvmet_fc_fcp_iod) * sqsize)), - GFP_KERNEL); + queue = kzalloc(struct_size(queue, fod, sqsize), GFP_KERNEL); if (!queue) return NULL; @@ -603,7 +601,6 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, if (!queue->work_q) goto out_a_put; - queue->fod = (struct nvmet_fc_fcp_iod *)&queue[1]; queue->qid = qid; queue->sqsize = sqsize; queue->assoc = assoc; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index a065dbfc43b1..3efc52f9c309 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -196,7 +196,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req, GFP_KERNEL, 0, bio); if (ret && ret != -EOPNOTSUPP) { req->error_slba = le64_to_cpu(range->slba); - return blk_to_nvme_status(req, errno_to_blk_status(ret)); + return errno_to_nvme_status(req, ret); } return NVME_SC_SUCCESS; } @@ -252,7 +252,6 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) { struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes; struct bio *bio = NULL; - u16 status = NVME_SC_SUCCESS; sector_t sector; sector_t nr_sector; int ret; @@ -264,13 +263,12 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) ret = __blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector, GFP_KERNEL, &bio, 0); - status = blk_to_nvme_status(req, errno_to_blk_status(ret)); if (bio) { bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; submit_bio(bio); } else { - nvmet_req_complete(req, status); + nvmet_req_complete(req, errno_to_nvme_status(req, ret)); } } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index ad0df786fe93..0a941abf56ec 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -371,7 +371,8 @@ static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd) cmd->state = NVMET_TCP_SEND_DATA_PDU; pdu->hdr.type = nvme_tcp_c2h_data; - pdu->hdr.flags = NVME_TCP_F_DATA_LAST; + pdu->hdr.flags = NVME_TCP_F_DATA_LAST | (queue->nvme_sq.sqhd_disabled ? + NVME_TCP_F_DATA_SUCCESS : 0); pdu->hdr.hlen = sizeof(*pdu); pdu->hdr.pdo = pdu->hdr.hlen + hdgst; pdu->hdr.plen = @@ -542,8 +543,19 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd) cmd->state = NVMET_TCP_SEND_DDGST; cmd->offset = 0; } else { - nvmet_setup_response_pdu(cmd); + if (queue->nvme_sq.sqhd_disabled) { + cmd->queue->snd_cmd = NULL; + nvmet_tcp_put_cmd(cmd); + } else { + nvmet_setup_response_pdu(cmd); + } } + + if (queue->nvme_sq.sqhd_disabled) { + kfree(cmd->iov); + sgl_free(cmd->req.sg); + } + return 1; } @@ -619,7 +631,13 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd) return ret; cmd->offset += ret; - nvmet_setup_response_pdu(cmd); + + if (queue->nvme_sq.sqhd_disabled) { + cmd->queue->snd_cmd = NULL; + nvmet_tcp_put_cmd(cmd); + } else { + nvmet_setup_response_pdu(cmd); + } return 1; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 2b2bc4b49d78..ebc80354714c 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2256,22 +2256,6 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, #define READ_CAPACITY_RETRIES_ON_RESET 10 -/* - * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set - * and the reported logical block size is bigger than 512 bytes. Note - * that last_sector is a u64 and therefore logical_to_sectors() is not - * applicable. - */ -static bool sd_addressable_capacity(u64 lba, unsigned int sector_size) -{ - u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9); - - if (sizeof(sector_t) == 4 && last_sector > U32_MAX) - return false; - - return true; -} - static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, unsigned char *buffer) { @@ -2337,14 +2321,6 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, return -ENODEV; } - if (!sd_addressable_capacity(lba, sector_size)) { - sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " - "kernel compiled with support for large block " - "devices.\n"); - sdkp->capacity = 0; - return -EOVERFLOW; - } - /* Logical blocks per physical block exponent */ sdkp->physical_block_size = (1 << (buffer[13] & 0xf)) * sector_size; @@ -2426,14 +2402,6 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, return sector_size; } - if (!sd_addressable_capacity(lba, sector_size)) { - sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " - "kernel compiled with support for large block " - "devices.\n"); - sdkp->capacity = 0; - return -EOVERFLOW; - } - sdkp->capacity = lba + 1; sdkp->physical_block_size = sector_size; return sector_size; @@ -3325,6 +3293,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie) if (sdp->removable) { gd->flags |= GENHD_FL_REMOVABLE; gd->events |= DISK_EVENT_MEDIA_CHANGE; + gd->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT; } blk_pm_runtime_init(sdp->request_queue, dev); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 039c27c2d7b3..c3f443d5aea8 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -716,6 +716,7 @@ static int sr_probe(struct device *dev) disk->fops = &sr_bdops; disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST; + disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT; blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT); diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c index f3fbb700f569..05a286d24f14 100644 --- a/drivers/xen/biomerge.c +++ b/drivers/xen/biomerge.c @@ -4,12 +4,13 @@ #include <xen/xen.h> #include <xen/page.h> +/* check if @page can be merged with 'vec1' */ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, - const struct bio_vec *vec2) + const struct page *page) { #if XEN_PAGE_SIZE == PAGE_SIZE unsigned long bfn1 = pfn_to_bfn(page_to_pfn(vec1->bv_page)); - unsigned long bfn2 = pfn_to_bfn(page_to_pfn(vec2->bv_page)); + unsigned long bfn2 = pfn_to_bfn(page_to_pfn(page)); return bfn1 + PFN_DOWN(vec1->bv_offset + vec1->bv_len) == bfn2; #else diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e7ae26e36c9c..38faf661e237 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1760,8 +1760,6 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_msg(sb, KERN_ERR, "filesystem too large to resize to %llu blocks safely", n_blocks_count); - if (sizeof(sector_t) < 8) - ext4_warning(sb, "CONFIG_LBDAF not enabled"); return -EINVAL; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6ed4eb81e674..d10e9e724bdd 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2706,13 +2706,9 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) loff_t res; loff_t upper_limit = MAX_LFS_FILESIZE; - /* small i_blocks in vfs inode? */ - if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { - /* - * CONFIG_LBDAF is not enabled implies the inode - * i_block represent total blocks in 512 bytes - * 32 == size of vfs inode i_blocks * 8 - */ + BUILD_BUG_ON(sizeof(blkcnt_t) < sizeof(u64)); + + if (!has_huge_files) { upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ @@ -2753,11 +2749,11 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) * number of 512-byte sectors of the file. */ - if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { + if (!has_huge_files) { /* - * !has_huge_files or CONFIG_LBDAF not enabled implies that - * the inode i_block field represents total file blocks in - * 2^32 512-byte sectors == size of vfs inode i_blocks * 8 + * !has_huge_files or implies that the inode i_block field + * represents total file blocks in 2^32 512-byte sectors == + * size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; @@ -2897,18 +2893,6 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) ~EXT4_FEATURE_RO_COMPAT_SUPP)); return 0; } - /* - * Large file size enabled file system can only be mounted - * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF - */ - if (ext4_has_feature_huge_file(sb)) { - if (sizeof(blkcnt_t) < sizeof(u64)) { - ext4_msg(sb, KERN_ERR, "Filesystem with huge files " - "cannot be mounted RDWR without " - "CONFIG_LBDAF"); - return 0; - } - } if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) { ext4_msg(sb, KERN_ERR, "Can't support bigalloc feature without " @@ -4057,8 +4041,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); - if (sizeof(sector_t) < 8) - ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); goto failed_mount; } diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index 3ed2b088dcfd..6a1e499543f5 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -1,6 +1,5 @@ config GFS2_FS tristate "GFS2 file system support" - depends on (64BIT || LBDAF) select FS_POSIX_ACL select CRC32 select LIBCRC32C diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 5f93cfacb3d1..69d02cf8cf37 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -121,7 +121,6 @@ config PNFS_FILE_LAYOUT config PNFS_BLOCK tristate depends on NFS_V4_1 && BLK_DEV_DM - depends on 64BIT || LBDAF default NFS_V4 config PNFS_FLEXFILE_LAYOUT diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 96ae7cedd487..fc3d29eceb2f 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -600,7 +600,6 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits, */ #if BITS_PER_LONG == 32 -# if defined(CONFIG_LBDAF) BUILD_BUG_ON(sizeof(sector_t) != 8); /* * We might be limited by page cache size. @@ -614,15 +613,6 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits, */ bitshift = 31; } -# else - /* - * We are limited by the size of sector_t. Use block size, as - * that's what we expose to the VFS. - */ - bytes = 1 << bbits; - trim = 1; - bitshift = 31; -# endif #endif /* diff --git a/fs/stack.c b/fs/stack.c index a54e33ed10f1..664ed35558bd 100644 --- a/fs/stack.c +++ b/fs/stack.c @@ -21,11 +21,10 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src) i_size = i_size_read(src); /* - * But if CONFIG_LBDAF (on 32-bit), we ought to make an effort to - * keep the two halves of i_blocks in sync despite SMP or PREEMPT - - * though stat's generic_fillattr() doesn't bother, and we won't be - * applying quotas (where i_blocks does become important) at the - * upper level. + * But on 32-bit, we ought to make an effort to keep the two halves of + * i_blocks in sync despite SMP or PREEMPT - though stat's + * generic_fillattr() doesn't bother, and we won't be applying quotas + * (where i_blocks does become important) at the upper level. * * We don't actually know what locking is used at the lower level; * but if it's a filesystem that supports quotas, it will be using @@ -44,9 +43,9 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src) * include/linux/fs.h). We don't necessarily hold i_mutex when this * is called, so take i_lock for that case. * - * And if CONFIG_LBDAF (on 32-bit), continue our effort to keep the - * two halves of i_blocks in sync despite SMP or PREEMPT: use i_lock - * for that case too, and do both at once by combining the tests. + * And if on 32-bit, continue our effort to keep the two halves of + * i_blocks in sync despite SMP or PREEMPT: use i_lock for that case + * too, and do both at once by combining the tests. * * There is none of this locking overhead in the 64-bit case. */ diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 457ac9f97377..99af5e5bda9f 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -1,7 +1,6 @@ config XFS_FS tristate "XFS filesystem support" depends on BLOCK - depends on (64BIT || LBDAF) select EXPORTFS select LIBCRC32C select FS_IOMAP diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f093ea244849..703b6be063ef 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -539,26 +539,18 @@ xfs_max_file_offset( /* Figure out maximum filesize, on Linux this can depend on * the filesystem blocksize (on 32 bit platforms). - * __block_write_begin does this in an [unsigned] long... + * __block_write_begin does this in an [unsigned] long long... * page->index << (PAGE_SHIFT - bbits) * So, for page sized blocks (4K on 32 bit platforms), * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is * (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1) * but for smaller blocksizes it is less (bbits = log2 bsize). - * Note1: get_block_t takes a long (implicit cast from above) - * Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch - * can optionally convert the [unsigned] long from above into - * an [unsigned] long long. */ #if BITS_PER_LONG == 32 -# if defined(CONFIG_LBDAF) ASSERT(sizeof(sector_t) == 8); pagefactor = PAGE_SIZE; bitshift = BITS_PER_LONG; -# else - pagefactor = PAGE_SIZE >> (PAGE_SHIFT - blockshift); -# endif #endif return (((uint64_t)pagefactor) << bitshift) - 1; diff --git a/include/linux/bio.h b/include/linux/bio.h index e584673c1881..9577ad8f6e28 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -436,6 +436,9 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +extern int __bio_add_pc_page(struct request_queue *, struct bio *, + struct page *, unsigned int, unsigned int, + bool); bool __bio_try_merge_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off, bool same_page); void __bio_add_page(struct bio *bio, struct page *page, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 791fee35df88..be418275763c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -215,21 +215,24 @@ struct bio { /* * bio flags */ -#define BIO_NO_PAGE_REF 0 /* don't put release vec pages */ -#define BIO_SEG_VALID 1 /* bi_phys_segments valid */ -#define BIO_CLONED 2 /* doesn't own data */ -#define BIO_BOUNCED 3 /* bio is a bounce bio */ -#define BIO_USER_MAPPED 4 /* contains user pages */ -#define BIO_NULL_MAPPED 5 /* contains invalid user pages */ -#define BIO_QUIET 6 /* Make BIO Quiet */ -#define BIO_CHAIN 7 /* chained bio, ->bi_remaining in effect */ -#define BIO_REFFED 8 /* bio has elevated ->bi_cnt */ -#define BIO_THROTTLED 9 /* This bio has already been subjected to +enum { + BIO_NO_PAGE_REF, /* don't put release vec pages */ + BIO_SEG_VALID, /* bi_phys_segments valid */ + BIO_CLONED, /* doesn't own data */ + BIO_BOUNCED, /* bio is a bounce bio */ + BIO_USER_MAPPED, /* contains user pages */ + BIO_NULL_MAPPED, /* contains invalid user pages */ + BIO_QUIET, /* Make BIO Quiet */ + BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ + BIO_REFFED, /* bio has elevated ->bi_cnt */ + BIO_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ -#define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion + BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ -#define BIO_QUEUE_ENTERED 11 /* can use blk_queue_enter_live() */ -#define BIO_TRACKED 12 /* set if bio goes through the rq_qos path */ + BIO_QUEUE_ENTERED, /* can use blk_queue_enter_live() */ + BIO_TRACKED, /* set if bio goes through the rq_qos path */ + BIO_FLAG_LAST +}; /* See BVEC_POOL_OFFSET below before adding new flags */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 317ab30d2904..99aa98f60b9e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -640,6 +640,13 @@ static inline bool blk_account_rq(struct request *rq) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) +#define rq_dma_dir(rq) \ + (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) + +#define dma_map_bvec(dev, bv, dir, attrs) \ + dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ + (dir), (attrs)) + static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; @@ -931,6 +938,17 @@ static inline unsigned int blk_rq_payload_bytes(struct request *rq) return blk_rq_bytes(rq); } +/* + * Return the first full biovec in the request. The caller needs to check that + * there are any bvecs before calling this helper. + */ +static inline struct bio_vec req_bvec(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return rq->special_vec; + return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); +} + static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { @@ -1547,6 +1565,17 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, return bio_integrity_intervals(bi, sectors) * bi->tuple_size; } +/* + * Return the first bvec that contains integrity data. Only drivers that are + * limited to a single integrity segment should use this helper. + */ +static inline struct bio_vec *rq_integrity_vec(struct request *rq) +{ + if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) + return NULL; + return rq->bio->bi_integrity->bip_vec; +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1621,6 +1650,11 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, return 0; } +static inline struct bio_vec *rq_integrity_vec(struct request *rq) +{ + return NULL; +} + #endif /* CONFIG_BLK_DEV_INTEGRITY */ struct block_device_operations { diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ff13cbc1887d..a4811410e4fc 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -51,11 +51,6 @@ struct bvec_iter_all { unsigned done; }; -static inline struct page *bvec_nth_page(struct page *page, int idx) -{ - return idx == 0 ? page : nth_page(page, idx); -} - /* * various member access, note that bio_data should of course not be used * on highmem page vectors @@ -92,8 +87,8 @@ static inline struct page *bvec_nth_page(struct page *page, int idx) PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ - bvec_nth_page(mp_bvec_iter_page((bvec), (iter)), \ - mp_bvec_iter_page_idx((bvec), (iter))) + (mp_bvec_iter_page((bvec), (iter)) + \ + mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ @@ -151,13 +146,18 @@ static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) return &iter_all->bv; } +static inline struct page *bvec_nth_page(struct page *page, int idx) +{ + return idx == 0 ? page : nth_page(page, idx); +} + static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { - bv->bv_page = nth_page(bv->bv_page, 1); + bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset / @@ -184,7 +184,7 @@ static inline void mp_bvec_last_segment(const struct bio_vec *bvec, unsigned total = bvec->bv_offset + bvec->bv_len; unsigned last_page = (total - 1) / PAGE_SIZE; - seg->bv_page = bvec_nth_page(bvec->bv_page, last_page); + seg->bv_page = bvec->bv_page + last_page; /* the whole segment is inside the last page */ if (bvec->bv_offset >= last_page * PAGE_SIZE) { @@ -196,9 +196,4 @@ static inline void mp_bvec_last_segment(const struct bio_vec *bvec, } } -#define mp_bvec_for_each_page(pg, bv, i) \ - for (i = (bv)->bv_offset / PAGE_SIZE; \ - (i <= (((bv)->bv_offset + (bv)->bv_len - 1) / PAGE_SIZE)) && \ - (pg = bvec_nth_page((bv)->bv_page, i)); i += 1) - #endif /* __LINUX_BVEC_ITER_H */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 06c0fd594097..6547c9256d5c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -150,6 +150,13 @@ enum { DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ }; +enum { + /* Poll even if events_poll_msecs is unset */ + DISK_EVENT_FLAG_POLL = 1 << 0, + /* Forward events to udev */ + DISK_EVENT_FLAG_UEVENT = 1 << 1, +}; + struct disk_part_tbl { struct rcu_head rcu_head; int len; @@ -184,8 +191,8 @@ struct gendisk { char disk_name[DISK_NAME_LEN]; /* name of major driver */ char *(*devnode)(struct gendisk *gd, umode_t *mode); - unsigned int events; /* supported events */ - unsigned int async_events; /* async events, subset of all */ + unsigned short events; /* supported events */ + unsigned short event_flags; /* flags related to event processing */ /* Array of pointers to partitions indexed by partno. * Protected with matching bdev lock but stat and other @@ -714,7 +721,7 @@ static inline void hd_free_part(struct hd_struct *part) */ static inline sector_t part_nr_sects_read(struct hd_struct *part) { -#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP) +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) sector_t nr_sects; unsigned seq; do { @@ -722,7 +729,7 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part) nr_sects = part->nr_sects; } while (read_seqcount_retry(&part->nr_sects_seq, seq)); return nr_sects; -#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) sector_t nr_sects; preempt_disable(); @@ -741,11 +748,11 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part) */ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) { -#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP) +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) write_seqcount_begin(&part->nr_sects_seq); part->nr_sects = size; write_seqcount_end(&part->nr_sects_seq); -#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) preempt_disable(); part->nr_sects = size; preempt_enable(); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2d14e21c16c0..a3b59d143afb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -17,6 +17,7 @@ #include <asm/byteorder.h> #include <asm/div64.h> #include <uapi/linux/kernel.h> +#include <asm/div64.h> #define STACK_MAGIC 0xdeadbeef @@ -175,18 +176,7 @@ #define _RET_IP_ (unsigned long)__builtin_return_address(0) #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) -#ifdef CONFIG_LBDAF -# define sector_div(a, b) do_div(a, b) -#else -# define sector_div(n, b)( \ -{ \ - int _res; \ - _res = (n) % (b); \ - (n) /= (b); \ - _res; \ -} \ -) -#endif +#define sector_div(a, b) do_div(a, b) /** * upper_32_bits - return bits 32-63 of a number diff --git a/include/linux/types.h b/include/linux/types.h index cc0dbbe551d5..231114ae38f4 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -127,13 +127,8 @@ typedef s64 int64_t; * * blkcnt_t is the type of the inode's block count. */ -#ifdef CONFIG_LBDAF typedef u64 sector_t; typedef u64 blkcnt_t; -#else -typedef unsigned long sector_t; -typedef unsigned long blkcnt_t; -#endif /* * The type of an index into the pagecache. diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index 627624d35030..e092e124dd16 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -58,7 +58,7 @@ struct opal_key { struct opal_lr_act { struct opal_key key; __u32 sum; - __u8 num_lrs; + __u8 num_lrs; __u8 lr[OPAL_MAX_LRS]; __u8 align[2]; /* Align to 8 byte boundary */ }; diff --git a/include/xen/xen.h b/include/xen/xen.h index 19d032373de5..19a72f591e2b 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -43,8 +43,10 @@ extern struct hvm_start_info pvh_start_info; #endif /* CONFIG_XEN_DOM0 */ struct bio_vec; +struct page; + bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, - const struct bio_vec *vec2); + const struct page *page); #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_XEN_BALLOON) extern u64 xen_saved_max_mem_size; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 00dbcdbc9a0d..caedd54fa545 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1927,7 +1927,6 @@ config TEST_STATIC_KEYS config TEST_KMOD tristate "kmod stress tester" depends on m - depends on BLOCK && (64BIT || LBDAF) # for XFS, BTRFS depends on NETDEVICES && NET_CORE && INET # for TUN select TEST_LKM select XFS_FS diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h index d27285f8ee82..8bc960e5e713 100644 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h @@ -59,11 +59,7 @@ typedef __u32 uint32_t; * * blkcnt_t is the type of the inode's block count. */ -#ifdef CONFIG_LBDAF typedef u64 sector_t; -#else -typedef unsigned long sector_t; -#endif /* * The type of an index into the pagecache. |