Home Home > GIT Browse > openSUSE-15.1
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPetr Tesarik <ptesarik@suse.cz>2019-05-24 09:57:46 +0200
committerPetr Tesarik <ptesarik@suse.cz>2019-05-24 09:57:46 +0200
commit597301e67267a50bf46c066141e7aa55983880d8 (patch)
treed0328b3cd69480da67810e4427af7428d4c03dff
parent79147af4fa7459b3ae89320cc5df5675a21844eb (diff)
parent3c842d421df4efbcf67ac54ea5a20c6810d3f769 (diff)
Merge branch 'SLE15-SP1' into openSUSE-15.1openSUSE-15.1
- Update config/armv7hl/default - Update config/armv7hl/lpae Conflicts: config/ppc64le/debug config/x86_64/debug suse-commit: af35fd11466ddb32ce5df4bc094d71af8b3b86aa
-rw-r--r--Documentation/arm/kernel_mode_neon.txt4
-rw-r--r--Documentation/x86/mds.rst2
-rw-r--r--MAINTAINERS6
-rw-r--r--arch/arm/Kconfig1
-rw-r--r--arch/arm/include/asm/barrier.h2
-rw-r--r--arch/arm/include/asm/irq.h1
-rw-r--r--arch/arm/include/asm/processor.h6
-rw-r--r--arch/arm/kernel/irq.c62
-rw-r--r--arch/arm/kernel/machine_kexec.c5
-rw-r--r--arch/arm/kernel/patch.c6
-rw-r--r--arch/arm/kernel/smp.c6
-rw-r--r--arch/arm/kernel/unwind.c14
-rw-r--r--arch/arm/lib/Makefile2
-rw-r--r--arch/arm/lib/xor-neon.c2
-rw-r--r--arch/arm/mach-imx/cpuidle-imx6q.c27
-rw-r--r--arch/arm/mach-omap2/cpuidle44xx.c16
-rw-r--r--arch/arm/mach-omap2/display.c7
-rw-r--r--arch/arm/mach-omap2/prm_common.c4
-rw-r--r--arch/arm/mach-s3c24xx/mach-osiris-dvs.c8
-rw-r--r--arch/arm/plat-pxa/ssp.c3
-rw-r--r--arch/arm/plat-samsung/Kconfig2
-rw-r--r--arch/x86/Kconfig.cpu14
-rw-r--r--arch/x86/events/amd/core.c4
-rw-r--r--arch/x86/events/amd/uncore.c20
-rw-r--r--arch/x86/events/core.c4
-rw-r--r--arch/x86/include/asm/amd_nb.h3
-rw-r--r--arch/x86/include/asm/cacheinfo.h1
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/include/asm/kvm_emulate.h4
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/processor.h3
-rw-r--r--arch/x86/include/asm/virtext.h5
-rw-r--r--arch/x86/kernel/alternative.c4
-rw-r--r--arch/x86/kernel/amd_nb.c47
-rw-r--r--arch/x86/kernel/apic/apic.c7
-rw-r--r--arch/x86/kernel/apic/probe_32.c1
-rw-r--r--arch/x86/kernel/cpu/Makefile1
-rw-r--r--arch/x86/kernel/cpu/bugs.c4
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c31
-rw-r--r--arch/x86/kernel/cpu/common.c4
-rw-r--r--arch/x86/kernel/cpu/cpu.h1
-rw-r--r--arch/x86/kernel/cpu/hygon.c408
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c21
-rw-r--r--arch/x86/kernel/cpu/mtrr/cleanup.c3
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c2
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c2
-rw-r--r--arch/x86/kernel/smpboot.c4
-rw-r--r--arch/x86/kvm/emulate.c11
-rw-r--r--arch/x86/pci/amd_bus.c6
-rw-r--r--arch/x86/xen/pmu.c12
-rw-r--r--block/bio.c5
-rw-r--r--block/genhd.c19
-rw-r--r--block/partition-generic.c7
-rw-r--r--drivers/acpi/acpi_pad.c1
-rw-r--r--drivers/acpi/acpica/dsopcode.c4
-rw-r--r--drivers/acpi/acpica/nsobject.c4
-rw-r--r--drivers/acpi/button.c5
-rw-r--r--drivers/acpi/processor_idle.c1
-rw-r--r--drivers/acpi/sleep.c4
-rw-r--r--drivers/acpi/utils.c1
-rw-r--r--drivers/base/devres.c10
-rw-r--r--drivers/char/ipmi/ipmi_msghandler.c20
-rw-r--r--drivers/cpufreq/acpi-cpufreq.c5
-rw-r--r--drivers/cpufreq/amd_freq_sensitivity.c20
-rw-r--r--drivers/crypto/caam/error.c2
-rw-r--r--drivers/crypto/vmx/aesp8-ppc.pl2
-rw-r--r--drivers/edac/amd64_edac.c10
-rw-r--r--drivers/edac/mce_amd.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc.c19
-rw-r--r--drivers/gpu/drm/amd/display/dc/dc.h3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dce/dce_aux.c9
-rw-r--r--drivers/gpu/drm/amd/display/dc/dce/dce_aux.h6
-rw-r--r--drivers/gpu/drm/bridge/adv7511/adv7511_drv.c6
-rw-r--r--drivers/gpu/drm/i915/i915_drv.h3
-rw-r--r--drivers/gpu/drm/i915/intel_audio.c57
-rw-r--r--drivers/gpu/drm/i915/intel_cdclk.c30
-rw-r--r--drivers/gpu/drm/i915/intel_display.c9
-rw-r--r--drivers/gpu/drm/i915/intel_drv.h3
-rw-r--r--drivers/gpu/drm/i915/intel_fbc.c4
-rw-r--r--drivers/gpu/drm/imx/ipuv3-crtc.c2
-rw-r--r--drivers/gpu/drm/pl111/pl111_display.c5
-rw-r--r--drivers/gpu/ipu-v3/ipu-dp.c12
-rw-r--r--drivers/hid/hid-input.c14
-rw-r--r--drivers/iio/adc/xilinx-xadc-core.c2
-rw-r--r--drivers/input/mouse/elan_i2c_core.c25
-rw-r--r--drivers/input/rmi4/rmi_driver.c6
-rw-r--r--drivers/isdn/mISDN/socket.c4
-rw-r--r--drivers/leds/leds-pwm.c5
-rw-r--r--drivers/md/md.c4
-rw-r--r--drivers/media/platform/atmel/atmel-isc.c4
-rw-r--r--drivers/media/platform/davinci/vpbe.c2
-rw-r--r--drivers/media/platform/omap/omap_vout.c15
-rw-r--r--drivers/net/ethernet/8390/mac8390.c19
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c16
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_common.c13
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/main.c20
-rw-r--r--drivers/net/ipvlan/ipvlan_core.c3
-rw-r--r--drivers/net/ipvlan/ipvlan_main.c1
-rw-r--r--drivers/net/phy/spi_ks8995.c9
-rw-r--r--drivers/net/team/team.c26
-rw-r--r--drivers/net/wireless/ath/ath10k/snoc.c2
-rw-r--r--drivers/nfc/st95hf/core.c7
-rw-r--r--drivers/nvme/host/fc.c14
-rw-r--r--drivers/pci/hotplug/pciehp.h3
-rw-r--r--drivers/pci/hotplug/pciehp_core.c6
-rw-r--r--drivers/pci/hotplug/pciehp_ctrl.c16
-rw-r--r--drivers/pci/hotplug/pciehp_hpc.c23
-rw-r--r--drivers/power/supply/axp20x_usb_power.c16
-rw-r--r--drivers/power/supply/axp288_charger.c4
-rw-r--r--drivers/s390/cio/qdio_main.c4
-rw-r--r--drivers/scsi/smartpqi/Makefile1
-rw-r--r--drivers/scsi/smartpqi/smartpqi.h231
-rw-r--r--drivers/scsi/smartpqi/smartpqi_init.c1662
-rw-r--r--drivers/scsi/smartpqi/smartpqi_sas_transport.c179
-rw-r--r--drivers/scsi/smartpqi/smartpqi_sis.c41
-rw-r--r--drivers/scsi/smartpqi/smartpqi_sis.h16
-rw-r--r--drivers/soc/fsl/qe/gpio.c4
-rw-r--r--drivers/thermal/cpu_cooling.c2
-rw-r--r--drivers/tty/serial/serial_core.c24
-rw-r--r--drivers/tty/vt/vt.c2
-rw-r--r--fs/9p/v9fs.c21
-rw-r--r--fs/9p/v9fs.h1
-rw-r--r--fs/9p/vfs_file.c6
-rw-r--r--fs/block_dev.c8
-rw-r--r--fs/btrfs/btrfs_inode.h6
-rw-r--r--fs/btrfs/inode.c17
-rw-r--r--fs/btrfs/ioctl.c10
-rw-r--r--fs/btrfs/send.c36
-rw-r--r--fs/btrfs/tree-log.c228
-rw-r--r--fs/configfs/dir.c17
-rw-r--r--fs/debugfs/inode.c13
-rw-r--r--fs/ext4/extents.c17
-rw-r--r--fs/ext4/ioctl.c2
-rw-r--r--fs/ext4/super.c60
-rw-r--r--fs/ufs/util.h2
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c4
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c58
-rw-r--r--fs/xfs/libxfs/xfs_alloc.h6
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c22
-rw-r--r--fs/xfs/libxfs/xfs_btree.c263
-rw-r--r--fs/xfs/libxfs/xfs_btree.h34
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c23
-rw-r--r--fs/xfs/libxfs/xfs_dir2.h2
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c59
-rw-r--r--fs/xfs/libxfs/xfs_dir2_data.c78
-rw-r--r--fs/xfs/libxfs/xfs_dir2_leaf.c12
-rw-r--r--fs/xfs/libxfs/xfs_dir2_node.c11
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h2
-rw-r--r--fs/xfs/libxfs/xfs_errortag.h108
-rw-r--r--fs/xfs/libxfs/xfs_format.h1
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c138
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.h12
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c6
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.h3
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h13
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c7
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c7
-rw-r--r--fs/xfs/libxfs/xfs_rmap.h3
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c14
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c2
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c4
-rw-r--r--fs/xfs/libxfs/xfs_types.h6
-rw-r--r--fs/xfs/xfs_buf.c16
-rw-r--r--fs/xfs/xfs_buf.h5
-rw-r--r--fs/xfs/xfs_error.c318
-rw-r--r--fs/xfs/xfs_error.h97
-rw-r--r--fs/xfs/xfs_inode.c12
-rw-r--r--fs/xfs/xfs_ioctl.c4
-rw-r--r--fs/xfs/xfs_iomap.c5
-rw-r--r--fs/xfs/xfs_iops.c2
-rw-r--r--fs/xfs/xfs_itable.c10
-rw-r--r--fs/xfs/xfs_linux.h8
-rw-r--r--fs/xfs/xfs_log.c154
-rw-r--r--fs/xfs/xfs_mount.c23
-rw-r--r--fs/xfs/xfs_mount.h27
-rw-r--r--fs/xfs/xfs_rtalloc.h5
-rw-r--r--fs/xfs/xfs_symlink.c6
-rw-r--r--fs/xfs/xfs_sysfs.c78
-rw-r--r--fs/xfs/xfs_trans_ail.c18
-rw-r--r--include/linux/atalk.h20
-rw-r--r--include/linux/genhd.h1
-rw-r--r--include/linux/mlx5/driver.h4
-rw-r--r--include/linux/pci_ids.h2
-rw-r--r--include/media/davinci/vpbe.h2
-rw-r--r--include/net/ip.h1
-rw-r--r--include/net/nexthop.h2
-rw-r--r--include/rdma/ib_cache.h24
-rw-r--r--lib/raid6/Makefile2
-rw-r--r--mm/huge_memory.c4
-rw-r--r--mm/mincore.c23
-rw-r--r--net/appletalk/atalk_proc.c2
-rw-r--r--net/appletalk/ddp.c37
-rw-r--r--net/appletalk/sysctl_net_atalk.c5
-rw-r--r--net/bridge/br_netfilter_hooks.c3
-rw-r--r--net/bridge/netfilter/ebtables.c18
-rw-r--r--net/core/dev.c2
-rw-r--r--net/core/dev_addr_lists.c4
-rw-r--r--net/core/ethtool.c42
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/dccp/feat.c7
-rw-r--r--net/ipv4/igmp.c5
-rw-r--r--net/ipv4/inetpeer.c1
-rw-r--r--net/ipv4/ip_input.c7
-rw-r--r--net/ipv4/ip_options.c10
-rw-r--r--net/ipv4/ip_output.c3
-rw-r--r--net/ipv4/ip_tunnel.c4
-rw-r--r--net/ipv4/ipconfig.c13
-rw-r--r--net/ipv4/netfilter/ip_tables.c1
-rw-r--r--net/ipv4/tcp_dctcp.c36
-rw-r--r--net/ipv4/tcp_output.c7
-rw-r--r--net/ipv4/xfrm4_input.c1
-rw-r--r--net/ipv4/xfrm4_mode_transport.c4
-rw-r--r--net/ipv6/addrconf.c45
-rw-r--r--net/ipv6/af_inet6.c10
-rw-r--r--net/ipv6/ip6_output.c3
-rw-r--r--net/ipv6/ip6_tunnel.c8
-rw-r--r--net/ipv6/mcast.c9
-rw-r--r--net/ipv6/netfilter/ip6_tables.c1
-rw-r--r--net/ipv6/xfrm6_input.c1
-rw-r--r--net/ipv6/xfrm6_mode_transport.c4
-rw-r--r--net/ipv6/xfrm6_output.c2
-rw-r--r--net/ipv6/xfrm6_policy.c2
-rw-r--r--net/l2tp/l2tp_core.c2
-rw-r--r--net/l2tp/l2tp_netlink.c4
-rw-r--r--net/l2tp/l2tp_ppp.c28
-rw-r--r--net/mac80211/mesh_pathtbl.c2
-rw-r--r--net/mac80211/tx.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c27
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c41
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c155
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c2
-rw-r--r--net/netfilter/nf_log.c13
-rw-r--r--net/netfilter/nf_tables_api.c71
-rw-r--r--net/netfilter/nft_ct.c20
-rw-r--r--net/netlink/af_netlink.c2
-rw-r--r--net/packet/af_packet.c16
-rw-r--r--net/rxrpc/local_object.c60
-rw-r--r--net/sched/act_sample.c8
-rw-r--r--net/sched/cls_matchall.c5
-rw-r--r--net/sctp/outqueue.c48
-rw-r--r--net/sctp/protocol.c1
-rw-r--r--net/smc/af_smc.c413
-rw-r--r--net/smc/smc.h11
-rw-r--r--net/smc/smc_clc.c10
-rw-r--r--net/smc/smc_clc.h20
-rw-r--r--net/smc/smc_close.c25
-rw-r--r--net/smc/smc_close.h1
-rw-r--r--net/smc/smc_core.c93
-rw-r--r--net/smc/smc_core.h25
-rw-r--r--net/smc/smc_ib.c48
-rw-r--r--net/smc/smc_ism.c5
-rw-r--r--net/smc/smc_pnet.c50
-rw-r--r--net/smc/smc_pnet.h7
-rw-r--r--net/socket.c2
-rw-r--r--net/vmw_vsock/virtio_transport.c13
-rw-r--r--net/wireless/nl80211.c18
-rw-r--r--net/xfrm/xfrm_input.c1
-rw-r--r--net/xfrm/xfrm_policy.c8
-rw-r--r--net/xfrm/xfrm_user.c20
-rw-r--r--sound/pci/hda/patch_realtek.c96
-rw-r--r--tools/lib/traceevent/event-parse.c2
-rw-r--r--tools/perf/arch/x86/util/kvm-stat.c2
-rw-r--r--tools/power/cpupower/utils/cpufreq-info.c6
-rw-r--r--tools/power/cpupower/utils/helpers/amd.c1
-rw-r--r--tools/power/cpupower/utils/helpers/cpuid.c8
-rw-r--r--tools/power/cpupower/utils/helpers/helpers.h2
-rw-r--r--tools/power/cpupower/utils/idle_monitor/mperf_monitor.c3
268 files changed, 5463 insertions, 2007 deletions
diff --git a/Documentation/arm/kernel_mode_neon.txt b/Documentation/arm/kernel_mode_neon.txt
index 525452726d31..b9e060c5b61e 100644
--- a/Documentation/arm/kernel_mode_neon.txt
+++ b/Documentation/arm/kernel_mode_neon.txt
@@ -6,7 +6,7 @@ TL;DR summary
* Use only NEON instructions, or VFP instructions that don't rely on support
code
* Isolate your NEON code in a separate compilation unit, and compile it with
- '-mfpu=neon -mfloat-abi=softfp'
+ '-march=armv7-a -mfpu=neon -mfloat-abi=softfp'
* Put kernel_neon_begin() and kernel_neon_end() calls around the calls into your
NEON code
* Don't sleep in your NEON code, and be aware that it will be executed with
@@ -87,7 +87,7 @@ instructions appearing in unexpected places if no special care is taken.
Therefore, the recommended and only supported way of using NEON/VFP in the
kernel is by adhering to the following rules:
* isolate the NEON code in a separate compilation unit and compile it with
- '-mfpu=neon -mfloat-abi=softfp';
+ '-march=armv7-a -mfpu=neon -mfloat-abi=softfp';
* issue the calls to kernel_neon_begin(), kernel_neon_end() as well as the calls
into the unit containing the NEON code from a compilation unit which is *not*
built with the GCC flag '-mfpu=neon' set.
diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst
index 7e5b1d2fc29c..ccb9948ac393 100644
--- a/Documentation/x86/mds.rst
+++ b/Documentation/x86/mds.rst
@@ -111,7 +111,7 @@ Kernel internal mitigation modes
off Mitigation is disabled. Either the CPU is not affected or
mds=off is supplied on the kernel command line
- full Mitigation is eanbled. CPU is affected and MD_CLEAR is
+ full Mitigation is enabled. CPU is affected and MD_CLEAR is
advertised in CPUID.
vmwerv Mitigation is enabled. CPU is affected and MD_CLEAR is not
diff --git a/MAINTAINERS b/MAINTAINERS
index 27679bc9e761..ba3361f33df5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6267,6 +6267,12 @@ W: https://linuxtv.org
S: Supported
F: drivers/media/platform/sti/hva
+HYGON PROCESSOR SUPPORT
+M: Pu Wen <puwen@hygon.cn>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+F: arch/x86/kernel/cpu/hygon.c
+
Hyper-V CORE AND DRIVERS
M: "K. Y. Srinivasan" <kys@microsoft.com>
M: Haiyang Zhang <haiyangz@microsoft.com>
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 205515e45aee..f83b6407101e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1442,6 +1442,7 @@ config NR_CPUS
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
depends on SMP
+ select GENERIC_IRQ_MIGRATION
help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu.
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index f5d698182d50..86740fbbd788 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -10,6 +10,8 @@
#define sev() __asm__ __volatile__ ("sev" : : : "memory")
#define wfe() __asm__ __volatile__ ("wfe" : : : "memory")
#define wfi() __asm__ __volatile__ ("wfi" : : : "memory")
+#else
+#define wfe() do { } while (0)
#endif
#if __LINUX_ARM_ARCH__ >= 7
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index e53638c8ed8a..61e1d089ce1a 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -24,7 +24,6 @@
#ifndef __ASSEMBLY__
struct irqaction;
struct pt_regs;
-extern void migrate_irqs(void);
extern void asm_do_IRQ(unsigned int, struct pt_regs *);
void handle_IRQ(unsigned int, struct pt_regs *);
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index c3d5fc124a05..768b6fe7640e 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -77,7 +77,11 @@ extern void release_thread(struct task_struct *);
unsigned long get_wchan(struct task_struct *p);
#if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327)
-#define cpu_relax() smp_mb()
+#define cpu_relax() \
+ do { \
+ smp_mb(); \
+ __asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;"); \
+ } while (0)
#else
#define cpu_relax() barrier()
#endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ece04a457486..5b07c7a31c31 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -31,7 +31,6 @@
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/seq_file.h>
-#include <linux/ratelimit.h>
#include <linux/errno.h>
#include <linux/list.h>
#include <linux/kallsyms.h>
@@ -119,64 +118,3 @@ int __init arch_probe_nr_irqs(void)
return nr_irqs;
}
#endif
-
-#ifdef CONFIG_HOTPLUG_CPU
-static bool migrate_one_irq(struct irq_desc *desc)
-{
- struct irq_data *d = irq_desc_get_irq_data(desc);
- const struct cpumask *affinity = irq_data_get_affinity_mask(d);
- struct irq_chip *c;
- bool ret = false;
-
- /*
- * If this is a per-CPU interrupt, or the affinity does not
- * include this CPU, then we have nothing to do.
- */
- if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
- return false;
-
- if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
- affinity = cpu_online_mask;
- ret = true;
- }
-
- c = irq_data_get_irq_chip(d);
- if (!c->irq_set_affinity)
- pr_debug("IRQ%u: unable to set affinity\n", d->irq);
- else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
- cpumask_copy(irq_data_get_affinity_mask(d), affinity);
-
- return ret;
-}
-
-/*
- * The current CPU has been marked offline. Migrate IRQs off this CPU.
- * If the affinity settings do not allow other CPUs, force them onto any
- * available CPU.
- *
- * Note: we must iterate over all IRQs, whether they have an attached
- * action structure or not, as we need to get chained interrupts too.
- */
-void migrate_irqs(void)
-{
- unsigned int i;
- struct irq_desc *desc;
- unsigned long flags;
-
- local_irq_save(flags);
-
- for_each_irq_desc(i, desc) {
- bool affinity_broken;
-
- raw_spin_lock(&desc->lock);
- affinity_broken = migrate_one_irq(desc);
- raw_spin_unlock(&desc->lock);
-
- if (affinity_broken)
- pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
- i, smp_processor_id());
- }
-
- local_irq_restore(flags);
-}
-#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index ef5ef9d40122..085880ab9903 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -90,8 +90,11 @@ void machine_crash_nonpanic_core(void *unused)
set_cpu_online(smp_processor_id(), false);
atomic_dec(&waiting_for_crash_ipi);
- while (1)
+
+ while (1) {
cpu_relax();
+ wfe();
+ }
}
void crash_smp_send_stop(void)
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index 020560b2dcb7..0297e0f6f948 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -15,7 +15,7 @@ struct patch {
unsigned int insn;
};
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
__acquires(&patch_lock)
@@ -32,7 +32,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
return addr;
if (flags)
- spin_lock_irqsave(&patch_lock, *flags);
+ raw_spin_lock_irqsave(&patch_lock, *flags);
else
__acquire(&patch_lock);
@@ -47,7 +47,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
clear_fixmap(fixmap);
if (flags)
- spin_unlock_irqrestore(&patch_lock, *flags);
+ raw_spin_unlock_irqrestore(&patch_lock, *flags);
else
__release(&patch_lock);
}
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 272dcee6735c..d345326de660 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -224,7 +224,7 @@ int __cpu_disable(void)
/*
* OK - migrate IRQs away from this CPU
*/
- migrate_irqs();
+ irq_migrate_all_off_this_cpu();
/*
* Flush user cache and TLB mappings, and then remove this CPU
@@ -568,8 +568,10 @@ static void ipi_cpu_stop(unsigned int cpu)
local_fiq_disable();
local_irq_disable();
- while (1)
+ while (1) {
cpu_relax();
+ wfe();
+ }
}
static DEFINE_PER_CPU(struct completion *, cpu_completion);
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 0bee233fef9a..314cfb232a63 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
static const struct unwind_idx *__origin_unwind_idx;
extern const struct unwind_idx __stop_unwind_idx[];
-static DEFINE_SPINLOCK(unwind_lock);
+static DEFINE_RAW_SPINLOCK(unwind_lock);
static LIST_HEAD(unwind_tables);
/* Convert a prel31 symbol to an absolute address */
@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
/* module unwind tables */
struct unwind_table *table;
- spin_lock_irqsave(&unwind_lock, flags);
+ raw_spin_lock_irqsave(&unwind_lock, flags);
list_for_each_entry(table, &unwind_tables, list) {
if (addr >= table->begin_addr &&
addr < table->end_addr) {
@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
break;
}
}
- spin_unlock_irqrestore(&unwind_lock, flags);
+ raw_spin_unlock_irqrestore(&unwind_lock, flags);
}
pr_debug("%s: idx = %p\n", __func__, idx);
@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
tab->begin_addr = text_addr;
tab->end_addr = text_addr + text_size;
- spin_lock_irqsave(&unwind_lock, flags);
+ raw_spin_lock_irqsave(&unwind_lock, flags);
list_add_tail(&tab->list, &unwind_tables);
- spin_unlock_irqrestore(&unwind_lock, flags);
+ raw_spin_unlock_irqrestore(&unwind_lock, flags);
return tab;
}
@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_table *tab)
if (!tab)
return;
- spin_lock_irqsave(&unwind_lock, flags);
+ raw_spin_lock_irqsave(&unwind_lock, flags);
list_del(&tab->list);
- spin_unlock_irqrestore(&unwind_lock, flags);
+ raw_spin_unlock_irqrestore(&unwind_lock, flags);
kfree(tab);
}
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 27f4d96258a2..b3ecffb76c3f 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -38,7 +38,7 @@ $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S
$(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S
ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
- NEON_FLAGS := -mfloat-abi=softfp -mfpu=neon
+ NEON_FLAGS := -march=armv7-a -mfloat-abi=softfp -mfpu=neon
CFLAGS_xor-neon.o += $(NEON_FLAGS)
obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o
endif
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index 2c40aeab3eaa..c691b901092f 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -14,7 +14,7 @@
MODULE_LICENSE("GPL");
#ifndef __ARM_NEON__
-#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
#endif
/*
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index bfeb25aaf9a2..326e870d7123 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -16,30 +16,23 @@
#include "cpuidle.h"
#include "hardware.h"
-static atomic_t master = ATOMIC_INIT(0);
-static DEFINE_SPINLOCK(master_lock);
+static int num_idle_cpus = 0;
+static DEFINE_SPINLOCK(cpuidle_lock);
static int imx6q_enter_wait(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
- if (atomic_inc_return(&master) == num_online_cpus()) {
- /*
- * With this lock, we prevent other cpu to exit and enter
- * this function again and become the master.
- */
- if (!spin_trylock(&master_lock))
- goto idle;
+ spin_lock(&cpuidle_lock);
+ if (++num_idle_cpus == num_online_cpus())
imx6_set_lpm(WAIT_UNCLOCKED);
- cpu_do_idle();
- imx6_set_lpm(WAIT_CLOCKED);
- spin_unlock(&master_lock);
- goto done;
- }
+ spin_unlock(&cpuidle_lock);
-idle:
cpu_do_idle();
-done:
- atomic_dec(&master);
+
+ spin_lock(&cpuidle_lock);
+ if (num_idle_cpus-- == num_online_cpus())
+ imx6_set_lpm(WAIT_CLOCKED);
+ spin_unlock(&cpuidle_lock);
return index;
}
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index a8b291f00109..dae514c8276a 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -152,6 +152,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) &&
(cx->mpu_logic_state == PWRDM_POWER_OFF);
+ /* Enter broadcast mode for periodic timers */
+ tick_broadcast_enable();
+
+ /* Enter broadcast mode for one-shot timers */
tick_broadcast_enter();
/*
@@ -218,15 +222,6 @@ fail:
return index;
}
-/*
- * For each cpu, setup the broadcast timer because local timers
- * stops for the states above C1.
- */
-static void omap_setup_broadcast_timer(void *arg)
-{
- tick_broadcast_enable();
-}
-
static struct cpuidle_driver omap4_idle_driver = {
.name = "omap4_idle",
.owner = THIS_MODULE,
@@ -319,8 +314,5 @@ int __init omap4_idle_init(void)
if (!cpu_clkdm[0] || !cpu_clkdm[1])
return -ENODEV;
- /* Configure the broadcast timer on each cpu */
- on_each_cpu(omap_setup_broadcast_timer, NULL, 1);
-
return cpuidle_register(idle_driver, cpu_online_mask);
}
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 8fa01c0ecdb2..46821e3109f6 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -83,6 +83,7 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
u32 enable_mask, enable_shift;
u32 pipd_mask, pipd_shift;
u32 reg;
+ int ret;
if (dsi_id == 0) {
enable_mask = OMAP4_DSI1_LANEENABLE_MASK;
@@ -98,7 +99,11 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
return -ENODEV;
}
- regmap_read(omap4_dsi_mux_syscon, OMAP4_DSIPHY_SYSCON_OFFSET, &reg);
+ ret = regmap_read(omap4_dsi_mux_syscon,
+ OMAP4_DSIPHY_SYSCON_OFFSET,
+ &reg);
+ if (ret)
+ return ret;
reg &= ~enable_mask;
reg &= ~pipd_mask;
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index dc11841ca334..4f1e269e6209 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -531,8 +531,10 @@ void omap_prm_reset_system(void)
prm_ll_data->reset_system();
- while (1)
+ while (1) {
cpu_relax();
+ wfe();
+ }
}
/**
diff --git a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
index 262ab0744748..f4fdfca9439b 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
@@ -70,16 +70,16 @@ static int osiris_dvs_notify(struct notifier_block *nb,
switch (val) {
case CPUFREQ_PRECHANGE:
- if (old_dvs & !new_dvs ||
- cur_dvs & !new_dvs) {
+ if ((old_dvs && !new_dvs) ||
+ (cur_dvs && !new_dvs)) {
pr_debug("%s: exiting dvs\n", __func__);
cur_dvs = false;
gpio_set_value(OSIRIS_GPIO_DVS, 1);
}
break;
case CPUFREQ_POSTCHANGE:
- if (!old_dvs & new_dvs ||
- !cur_dvs & new_dvs) {
+ if ((!old_dvs && new_dvs) ||
+ (!cur_dvs && new_dvs)) {
pr_debug("entering dvs\n");
cur_dvs = true;
gpio_set_value(OSIRIS_GPIO_DVS, 0);
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ba13f793fbce..b92673efffff 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -237,8 +237,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
if (ssp == NULL)
return -ENODEV;
- iounmap(ssp->mmio_base);
-
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
release_mem_region(res->start, resource_size(res));
@@ -248,7 +246,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
list_del(&ssp->node);
mutex_unlock(&ssp_lock);
- kfree(ssp);
return 0;
}
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index e8229b9fee4a..3265b8f86069 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -258,7 +258,7 @@ config S3C_PM_DEBUG_LED_SMDK
config SAMSUNG_PM_CHECK
bool "S3C2410 PM Suspend Memory CRC"
- depends on PM
+ depends on PM && (PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5PV210)
select CRC32
help
Enable the PM code's memory area checksum over sleep. This option
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 3ba5ff2f2d08..e3ab71bffb0a 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -438,6 +438,20 @@ config CPU_SUP_AMD
If unsure, say N.
+config CPU_SUP_HYGON
+ default y
+ bool "Support Hygon processors" if PROCESSOR_SELECT
+ select CPU_SUP_AMD
+ help
+ This enables detection, tunings and quirks for Hygon processors
+
+ You need this enabled if you want your kernel to run on an
+ Hygon CPU. Disabling this option on other types of CPUs
+ makes the kernel a tiny bit smaller. Disabling it on an Hygon
+ CPU might render the kernel unbootable.
+
+ If unsure, say N.
+
config CPU_SUP_CENTAUR
default y
bool "Support Centaur processors" if PROCESSOR_SELECT
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 27ade3cb6482..f15441b07dad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -920,6 +920,10 @@ static int __init amd_core_pmu_init(void)
* We fallback to using default amd_get_event_constraints.
*/
break;
+ case 0x18:
+ pr_cont("Fam18h ");
+ /* Using default amd_get_event_constraints. */
+ break;
default:
pr_err("core perfctr but no constraints; unknown hardware!\n");
return -ENODEV;
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 1727021f0e0d..3517c7b7a434 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -507,17 +507,19 @@ static int __init amd_uncore_init(void)
{
int ret = -ENODEV;
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return -ENODEV;
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
return -ENODEV;
- if (boot_cpu_data.x86 == 0x17) {
+ if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) {
/*
- * For F17h, the Northbridge counters are repurposed as Data
- * Fabric counters. Also, L3 counters are supported too. The PMUs
- * are exported based on family as either L2 or L3 and NB or DF.
+ * For F17h or F18h, the Northbridge counters are
+ * repurposed as Data Fabric counters. Also, L3
+ * counters are supported too. The PMUs are exported
+ * based on family as either L2 or L3 and NB or DF.
*/
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L3;
@@ -547,7 +549,9 @@ static int __init amd_uncore_init(void)
if (ret)
goto fail_nb;
- pr_info("AMD NB counters detected\n");
+ pr_info("%s NB counters detected\n",
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?
+ "HYGON" : "AMD");
ret = 0;
}
@@ -561,7 +565,9 @@ static int __init amd_uncore_init(void)
if (ret)
goto fail_llc;
- pr_info("AMD LLC counters detected\n");
+ pr_info("%s LLC counters detected\n",
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?
+ "HYGON" : "AMD");
ret = 0;
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index edfa8abbe87d..0bdd1ff697c4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1762,6 +1762,10 @@ static int __init init_hw_perf_events(void)
case X86_VENDOR_AMD:
err = amd_pmu_init();
break;
+ case X86_VENDOR_HYGON:
+ err = amd_pmu_init();
+ x86_pmu.name = "HYGON";
+ break;
default:
err = -ENOTSUPP;
}
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 00c88a01301d..456ecbd1cb55 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -101,6 +101,9 @@ static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev)
static inline bool amd_gart_present(void)
{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ return false;
+
/* GART present only on Fam15h, upto model 0fh */
if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
(boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
index e958e28f7ab5..86b63c7feab7 100644
--- a/arch/x86/include/asm/cacheinfo.h
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -3,5 +3,6 @@
#define _ASM_X86_CACHEINFO_H
void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
#endif /* _ASM_X86_CACHEINFO_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 3c67617cb216..92c07df714cb 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -344,8 +344,8 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
-#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
+#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 96125be33ca2..4751b0787a57 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -363,6 +363,10 @@ struct x86_emulate_ctxt {
#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+#define X86EMUL_CPUID_VENDOR_HygonGenuine_ebx 0x6f677948
+#define X86EMUL_CPUID_VENDOR_HygonGenuine_ecx 0x656e6975
+#define X86EMUL_CPUID_VENDOR_HygonGenuine_edx 0x6e65476e
+
#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 166e3518b843..40f93754d5ce 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -269,6 +269,8 @@ static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
#endif
+static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); }
+
int mce_available(struct cpuinfo_x86 *c);
bool mce_is_memory_error(struct mce *m);
bool mce_is_correctable(struct mce *m);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7ea25d8700f7..0f85fa30defe 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -157,7 +157,8 @@ enum cpuid_regs_idx {
#define X86_VENDOR_CENTAUR 5
#define X86_VENDOR_TRANSMETA 7
#define X86_VENDOR_NSC 8
-#define X86_VENDOR_NUM 9
+#define X86_VENDOR_HYGON 9
+#define X86_VENDOR_NUM 10
#define X86_VENDOR_UNKNOWN 0xff
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 0116b2ee9e64..e05e0d309244 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -83,9 +83,10 @@ static inline void cpu_emergency_vmxoff(void)
*/
static inline int cpu_has_svm(const char **msg)
{
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) {
if (msg)
- *msg = "not amd";
+ *msg = "not amd or hygon";
return 0;
}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index f13f4f26e140..d30f0c7b494c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -222,6 +222,10 @@ void __init arch_init_ideal_nops(void)
}
break;
+ case X86_VENDOR_HYGON:
+ ideal_nops = p6_nops;
+ return;
+
case X86_VENDOR_AMD:
if (boot_cpu_data.x86 > 0xf) {
ideal_nops = p6_nops;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 9020947addd8..79b3c63070fb 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -61,6 +61,21 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{}
};
+static const struct pci_device_id hygon_root_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_ROOT) },
+ {}
+};
+
+const struct pci_device_id hygon_nb_misc_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+ {}
+};
+
+static const struct pci_device_id hygon_nb_link_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+ {}
+};
+
const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
{ 0x00, 0x18, 0x20 },
{ 0xff, 0x00, 0x20 },
@@ -194,8 +209,11 @@ EXPORT_SYMBOL_GPL(amd_df_indirect_read);
int amd_cache_northbridges(void)
{
- struct amd_northbridge *nb;
+ const struct pci_device_id *misc_ids = amd_nb_misc_ids;
+ const struct pci_device_id *link_ids = amd_nb_link_ids;
+ const struct pci_device_id *root_ids = amd_root_ids;
struct pci_dev *root, *misc, *link;
+ struct amd_northbridge *nb;
u16 roots_per_misc = 0;
u16 misc_count = 0;
u16 root_count = 0;
@@ -204,8 +222,14 @@ int amd_cache_northbridges(void)
if (amd_northbridges.num)
return 0;
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+ root_ids = hygon_root_ids;
+ misc_ids = hygon_nb_misc_ids;
+ link_ids = hygon_nb_link_ids;
+ }
+
misc = NULL;
- while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
+ while ((misc = next_northbridge(misc, misc_ids)) != NULL)
misc_count++;
if (!misc_count)
@@ -238,11 +262,11 @@ int amd_cache_northbridges(void)
link = misc = root = NULL;
for (i = 0; i < amd_northbridges.num; i++) {
node_to_amd_nb(i)->root = root =
- next_northbridge(root, amd_root_ids);
+ next_northbridge(root, root_ids);
node_to_amd_nb(i)->misc = misc =
- next_northbridge(misc, amd_nb_misc_ids);
+ next_northbridge(misc, misc_ids);
node_to_amd_nb(i)->link = link =
- next_northbridge(link, amd_nb_link_ids);
+ next_northbridge(link, link_ids);
/*
* If there are more PCI root devices than data fabric/
@@ -293,11 +317,19 @@ EXPORT_SYMBOL_GPL(amd_cache_northbridges);
*/
bool __init early_is_amd_nb(u32 device)
{
+ const struct pci_device_id *misc_ids = amd_nb_misc_ids;
const struct pci_device_id *id;
u32 vendor = device & 0xffff;
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+ return false;
+
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ misc_ids = hygon_nb_misc_ids;
+
device >>= 16;
- for (id = amd_nb_misc_ids; id->vendor; id++)
+ for (id = misc_ids; id->vendor; id++)
if (vendor == id->vendor && device == id->device)
return true;
return false;
@@ -309,7 +341,8 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
u64 base, msr;
unsigned int segn_busn_bits;
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return NULL;
/* assume all cpus from fam10h have mmconfig */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index a38a36d960c3..55204f453554 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -227,6 +227,11 @@ static int modern_apic(void)
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
boot_cpu_data.x86 >= 0xf)
return 1;
+
+ /* Hygon systems use modern APIC */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ return 1;
+
return lapic_get_version() >= 0x14;
}
@@ -1736,6 +1741,8 @@ static int __init detect_init_APIC(void)
(boot_cpu_data.x86 >= 15))
break;
goto no_apic;
+ case X86_VENDOR_HYGON:
+ break;
case X86_VENDOR_INTEL:
if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
(boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 01602b4383ab..071f9649463e 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -162,6 +162,7 @@ void __init default_setup_apic_routing(void)
break;
}
/* If P4 and above fall through */
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
def_to_bigsmp = 1;
}
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 6370f9fe29b4..f0c24f7aebd4 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel.o
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
+obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o
obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c1023744d228..fb7cf0323b9f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -650,6 +650,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
}
if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON &&
boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
return SPECTRE_V2_CMD_AUTO;
@@ -713,7 +714,8 @@ static void __init spectre_v2_select_mitigation(void)
return;
retpoline_auto:
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
retpoline_amd:
if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index eacd9defef58..5d4cf899264b 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -599,6 +599,10 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
else
amd_cpuid4(index, &eax, &ebx, &ecx);
amd_init_l3_cache(this_leaf, index);
+ } else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+ cpuid_count(0x8000001d, index, &eax.full,
+ &ebx.full, &ecx.full, &edx);
+ amd_init_l3_cache(this_leaf, index);
} else {
cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
}
@@ -622,7 +626,8 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
union _cpuid4_leaf_eax cache_eax;
int i = -1;
- if (c->x86_vendor == X86_VENDOR_AMD)
+ if (c->x86_vendor == X86_VENDOR_AMD ||
+ c->x86_vendor == X86_VENDOR_HYGON)
op = 0x8000001d;
else
op = 4;
@@ -675,6 +680,22 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
}
}
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+{
+ /*
+ * We may have multiple LLCs if L3 caches exist, so check if we
+ * have an L3 cache by looking at the L3 cache CPUID leaf.
+ */
+ if (!cpuid_edx(0x80000006))
+ return;
+
+ /*
+ * LLC is at the core complex level.
+ * Core complex ID is ApicId[3] for these processors.
+ */
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+}
+
void init_amd_cacheinfo(struct cpuinfo_x86 *c)
{
@@ -688,6 +709,11 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
}
}
+void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
+{
+ num_cache_leaves = find_num_cache_leaves(c);
+}
+
unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
{
/* Cache sizes */
@@ -910,7 +936,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
int index_msb, i;
struct cpuinfo_x86 *c = &cpu_data(cpu);
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (c->x86_vendor == X86_VENDOR_AMD ||
+ c->x86_vendor == X86_VENDOR_HYGON) {
if (__cache_amd_cpumap_setup(cpu, index, base))
return;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b381f6566252..a6830ed41bd0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -938,6 +938,9 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#define VULNWL_AMD(family, whitelist) \
VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
+#define VULNWL_HYGON(family, whitelist) \
+ VULNWL(HYGON, family, X86_MODEL_ANY, whitelist)
+
static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL(ANY, 4, X86_MODEL_ANY, NO_SPECULATION),
VULNWL(CENTAUR, 5, X86_MODEL_ANY, NO_SPECULATION),
@@ -974,6 +977,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
{}
};
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 53f1f8214160..f18d8c677a18 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -27,6 +27,7 @@ struct cpu_dev {
} legacy_models[5];
#endif
};
+extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c);
struct _tlb_table {
unsigned char descriptor;
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
new file mode 100644
index 000000000000..cf25405444ab
--- /dev/null
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Hygon Processor Support for Linux
+ *
+ * Copyright (C) 2018 Chengdu Haiguang IC Design Co., Ltd.
+ *
+ * Author: Pu Wen <puwen@hygon.cn>
+ */
+#include <linux/io.h>
+
+#include <asm/cpu.h>
+#include <asm/smp.h>
+#include <asm/cacheinfo.h>
+#include <asm/spec-ctrl.h>
+#include <asm/delay.h>
+#ifdef CONFIG_X86_64
+# include <asm/set_memory.h>
+#endif
+
+#include "cpu.h"
+
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config. Read the comment in
+ * srat_detect_node().
+ */
+static int nearby_node(int apicid)
+{
+ int i, node;
+
+ for (i = apicid - 1; i >= 0; i--) {
+ node = __apicid_to_node[i];
+ if (node != NUMA_NO_NODE && node_online(node))
+ return node;
+ }
+ for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+ node = __apicid_to_node[i];
+ if (node != NUMA_NO_NODE && node_online(node))
+ return node;
+ }
+ return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+
+static void hygon_get_topology_early(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_TOPOEXT))
+ smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+}
+
+/*
+ * Fixup core topology information for
+ * (1) Hygon multi-node processors
+ * Assumption: Number of cores in each internal node is the same.
+ * (2) Hygon processors supporting compute units
+ */
+static void hygon_get_topology(struct cpuinfo_x86 *c)
+{
+ u8 node_id;
+ int cpu = smp_processor_id();
+
+ /* get information required for multi-node processors */
+ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ int err;
+ u32 eax, ebx, ecx, edx;
+
+ cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+ node_id = ecx & 0xff;
+
+ c->cpu_core_id = ebx & 0xff;
+
+ if (smp_num_siblings > 1)
+ c->x86_max_cores /= smp_num_siblings;
+
+ /*
+ * In case leaf B is available, use it to derive
+ * topology information.
+ */
+ err = detect_extended_topology(c);
+ if (!err)
+ c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+
+ cacheinfo_hygon_init_llc_id(c, cpu, node_id);
+ } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
+ u64 value;
+
+ rdmsrl(MSR_FAM10H_NODE_ID, value);
+ node_id = value & 7;
+
+ per_cpu(cpu_llc_id, cpu) = node_id;
+ } else
+ return;
+
+ if (nodes_per_socket > 1)
+ set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+}
+
+/*
+ * On Hygon setup the lower bits of the APIC id distinguish the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void hygon_detect_cmp(struct cpuinfo_x86 *c)
+{
+ unsigned int bits;
+ int cpu = smp_processor_id();
+
+ bits = c->x86_coreid_bits;
+ /* Low order bits define the core id (index of core in socket) */
+ c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+ /* Convert the initial APIC ID into the socket ID */
+ c->phys_proc_id = c->initial_apicid >> bits;
+ /* use socket ID also for last level cache */
+ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+}
+
+static void srat_detect_node(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_NUMA
+ int cpu = smp_processor_id();
+ int node;
+ unsigned int apicid = c->apicid;
+
+ node = numa_cpu_node(cpu);
+ if (node == NUMA_NO_NODE)
+ node = per_cpu(cpu_llc_id, cpu);
+
+ /*
+ * On multi-fabric platform (e.g. Numascale NumaChip) a
+ * platform-specific handler needs to be called to fixup some
+ * IDs of the CPU.
+ */
+ if (x86_cpuinit.fixup_cpu_id)
+ x86_cpuinit.fixup_cpu_id(c, node);
+
+ if (!node_online(node)) {
+ /*
+ * Two possibilities here:
+ *
+ * - The CPU is missing memory and no node was created. In
+ * that case try picking one from a nearby CPU.
+ *
+ * - The APIC IDs differ from the HyperTransport node IDs.
+ * Assume they are all increased by a constant offset, but
+ * in the same order as the HT nodeids. If that doesn't
+ * result in a usable node fall back to the path for the
+ * previous case.
+ *
+ * This workaround operates directly on the mapping between
+ * APIC ID and NUMA node, assuming certain relationship
+ * between APIC ID, HT node ID and NUMA topology. As going
+ * through CPU mapping may alter the outcome, directly
+ * access __apicid_to_node[].
+ */
+ int ht_nodeid = c->initial_apicid;
+
+ if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+ node = __apicid_to_node[ht_nodeid];
+ /* Pick a nearby node */
+ if (!node_online(node))
+ node = nearby_node(apicid);
+ }
+ numa_set_node(cpu, node);
+#endif
+}
+
+static void early_init_hygon_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ unsigned int bits, ecx;
+
+ /* Multi core CPU? */
+ if (c->extended_cpuid_level < 0x80000008)
+ return;
+
+ ecx = cpuid_ecx(0x80000008);
+
+ c->x86_max_cores = (ecx & 0xff) + 1;
+
+ /* CPU telling us the core id bits shift? */
+ bits = (ecx >> 12) & 0xF;
+
+ /* Otherwise recompute */
+ if (bits == 0) {
+ while ((1 << bits) < c->x86_max_cores)
+ bits++;
+ }
+
+ c->x86_coreid_bits = bits;
+#endif
+}
+
+static void bsp_init_hygon(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+ unsigned long long tseg;
+
+ /*
+ * Split up direct mapping around the TSEG SMM area.
+ * Don't do it for gbpages because there seems very little
+ * benefit in doing so.
+ */
+ if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+ unsigned long pfn = tseg >> PAGE_SHIFT;
+
+ pr_debug("tseg: %010llx\n", tseg);
+ if (pfn_range_is_mapped(pfn, pfn + 1))
+ set_memory_4k((unsigned long)__va(tseg), 1);
+ }
+#endif
+
+ if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+ u64 val;
+
+ rdmsrl(MSR_K7_HWCR, val);
+ if (!(val & BIT(24)))
+ pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
+ }
+
+ if (cpu_has(c, X86_FEATURE_MWAITX))
+ use_mwaitx_delay();
+
+ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ u32 ecx;
+
+ ecx = cpuid_ecx(0x8000001e);
+ nodes_per_socket = ((ecx >> 8) & 7) + 1;
+ } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
+ u64 value;
+
+ rdmsrl(MSR_FAM10H_NODE_ID, value);
+ nodes_per_socket = ((value >> 3) & 7) + 1;
+ }
+
+ if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
+ !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) {
+ /*
+ * Try to cache the base value so further operations can
+ * avoid RMW. If that faults, do not enable SSBD.
+ */
+ if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
+ setup_force_cpu_cap(X86_FEATURE_SSBD);
+ x86_amd_ls_cfg_ssbd_mask = 1ULL << 10;
+ }
+ }
+}
+
+static void early_init_hygon(struct cpuinfo_x86 *c)
+{
+ u32 dummy;
+
+ early_init_hygon_mc(c);
+
+ set_cpu_cap(c, X86_FEATURE_K8);
+
+ rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
+
+ /*
+ * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
+ * with P/T states and does not stop in deep C-states
+ */
+ if (c->x86_power & (1 << 8)) {
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+ }
+
+ /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
+ if (c->x86_power & BIT(12))
+ set_cpu_cap(c, X86_FEATURE_ACC_POWER);
+
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_SYSCALL32);
+#endif
+
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
+ /*
+ * ApicID can always be treated as an 8-bit value for Hygon APIC So, we
+ * can safely set X86_FEATURE_EXTD_APICID unconditionally.
+ */
+ if (boot_cpu_has(X86_FEATURE_APIC))
+ set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+#endif
+
+ /*
+ * This is only needed to tell the kernel whether to use VMCALL
+ * and VMMCALL. VMMCALL is never executed except under virt, so
+ * we can set it unconditionally.
+ */
+ set_cpu_cap(c, X86_FEATURE_VMMCALL);
+
+ hygon_get_topology_early(c);
+}
+
+static void init_hygon(struct cpuinfo_x86 *c)
+{
+ early_init_hygon(c);
+
+ /*
+ * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
+ */
+ clear_cpu_cap(c, 0*32+31);
+
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+ /* get apicid instead of initial apic id from cpuid */
+ c->apicid = hard_smp_processor_id();
+
+ set_cpu_cap(c, X86_FEATURE_ZEN);
+ set_cpu_cap(c, X86_FEATURE_CPB);
+
+ cpu_detect_cache_sizes(c);
+
+ hygon_detect_cmp(c);
+ hygon_get_topology(c);
+ srat_detect_node(c);
+
+ init_hygon_cacheinfo(c);
+
+ if (cpu_has(c, X86_FEATURE_XMM2)) {
+ unsigned long long val;
+ int ret;
+
+ /*
+ * A serializing LFENCE has less overhead than MFENCE, so
+ * use it for execution serialization. On families which
+ * don't have that MSR, LFENCE is already serializing.
+ * msr_set_bit() uses the safe accessors, too, even if the MSR
+ * is not present.
+ */
+ msr_set_bit(MSR_F10H_DECFG,
+ MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+ /*
+ * Verify that the MSR write was successful (could be running
+ * under a hypervisor) and only then assume that LFENCE is
+ * serializing.
+ */
+ ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+ if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+ } else {
+ /* MFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+ }
+ }
+
+ /*
+ * Hygon processors have APIC timer running in deep C states.
+ */
+ set_cpu_cap(c, X86_FEATURE_ARAT);
+
+ /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */
+ if (!cpu_has(c, X86_FEATURE_XENPV))
+ set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+}
+
+static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
+{
+ u32 ebx, eax, ecx, edx;
+ u16 mask = 0xfff;
+
+ if (c->extended_cpuid_level < 0x80000006)
+ return;
+
+ cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
+
+ tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
+ tlb_lli_4k[ENTRIES] = ebx & mask;
+
+ /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!((eax >> 16) & mask))
+ tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+ else
+ tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+
+ /* a 4M entry uses two 2M entries */
+ tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+
+ /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!(eax & mask)) {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ tlb_lli_2m[ENTRIES] = eax & 0xff;
+ } else
+ tlb_lli_2m[ENTRIES] = eax & mask;
+
+ tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+}
+
+static const struct cpu_dev hygon_cpu_dev = {
+ .c_vendor = "Hygon",
+ .c_ident = { "HygonGenuine" },
+ .c_early_init = early_init_hygon,
+ .c_detect_tlb = cpu_detect_tlb_hygon,
+ .c_bsp_init = bsp_init_hygon,
+ .c_init = init_hygon,
+ .c_x86_vendor = X86_VENDOR_HYGON,
+};
+
+cpu_dev_register(hygon_cpu_dev);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 20d133ec3ef9..e594e28b7552 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -333,7 +333,8 @@ int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) =
void __init mcheck_vendor_init_severity(void)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
mce_severity = mce_severity_amd;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 161edcb766c5..7073fec18cd1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -508,9 +508,9 @@ EXPORT_SYMBOL_GPL(mce_usable_address);
bool mce_is_memory_error(struct mce *m)
{
- if (m->cpuvendor == X86_VENDOR_AMD) {
+ if (m->cpuvendor == X86_VENDOR_AMD ||
+ m->cpuvendor == X86_VENDOR_HYGON) {
return amd_mce_is_memory_error(m);
-
} else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -539,6 +539,9 @@ bool mce_is_correctable(struct mce *m)
if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
return false;
+ if (m->cpuvendor == X86_VENDOR_HYGON && m->status & MCI_STATUS_DEFERRED)
+ return false;
+
if (m->status & MCI_STATUS_UC)
return false;
@@ -1691,7 +1694,7 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
*/
static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
{
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) {
mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR);
mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA);
@@ -1718,6 +1721,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
break;
}
+ case X86_VENDOR_HYGON:
+ mce_hygon_feature_init(c);
+ break;
+
+
default:
break;
}
@@ -1940,12 +1948,15 @@ static void mce_disable_error_reporting(void)
static void vendor_disable_error_reporting(void)
{
/*
- * Don't clear on Intel CPUs. Some of these MSRs are socket-wide.
+ * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
+ * are socket-wide.
* Disabling them for just a single offlined CPU is bad, since it will
* inhibit reporting for all shared resources on the socket like the
* last level cache (LLC), the integrated memory controller (iMC), etc.
*/
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
return;
mce_disable_error_reporting();
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 765afd599039..3668c5df90c6 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -831,7 +831,8 @@ int __init amd_special_default_mtrr(void)
{
u32 l, h;
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return 0;
if (boot_cpu_data.x86 < 0xf)
return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 2bce84d91c2b..e1184b23cdda 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -126,7 +126,7 @@ static void __init set_num_var_ranges(void)
if (use_intel())
rdmsr(MSR_MTRRcap, config, dummy);
- else if (is_cpu(AMD))
+ else if (is_cpu(AMD) || is_cpu(HYGON))
config = 2;
else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
config = 8;
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 181eabecae25..eb31d1183db2 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -45,6 +45,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
{
/* returns the bit offset of the performance counter register */
switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTR)
return (msr - MSR_F15H_PERF_CTR) >> 1;
@@ -73,6 +74,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
{
/* returns the bit offset of the event selection register */
switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTL)
return (msr - MSR_F15H_PERF_CTL) >> 1;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 04467eada72f..58fd09cc9fb2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -675,6 +675,7 @@ static void __init smp_quirk_init_udelay(void)
/* if modern processor, use no delay */
if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+ ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
init_udelay = 0;
return;
@@ -1622,7 +1623,8 @@ static inline void mwait_play_dead(void)
void *mwait_ptr;
int i;
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
return;
if (!this_cpu_has(X86_FEATURE_MWAIT))
return;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2faea8008577..db8b1e927455 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2722,7 +2722,16 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
return true;
- /* default: (not Intel, not AMD), apply Intel's stricter rules... */
+ /* Hygon ("HygonGenuine") */
+ if (ebx == X86EMUL_CPUID_VENDOR_HygonGenuine_ebx &&
+ ecx == X86EMUL_CPUID_VENDOR_HygonGenuine_ecx &&
+ edx == X86EMUL_CPUID_VENDOR_HygonGenuine_edx)
+ return true;
+
+ /*
+ * default: (not Intel, not AMD, not Hygon), apply Intel's
+ * stricter rules...
+ */
return false;
}
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index ae387e5ee6f7..f4180ce45843 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -92,7 +92,8 @@ static int __init early_root_info_init(void)
vendor = id & 0xffff;
device = (id>>16) & 0xffff;
- if (vendor != PCI_VENDOR_ID_AMD)
+ if (vendor != PCI_VENDOR_ID_AMD &&
+ vendor != PCI_VENDOR_ID_HYGON)
continue;
if (hb_probes[i].device == device) {
@@ -389,7 +390,8 @@ static int __init pci_io_ecs_init(void)
static int __init amd_postcore_init(void)
{
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return 0;
early_root_info_init();
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index a99f747acac7..10690f1c9459 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -90,6 +90,12 @@ static void xen_pmu_arch_init(void)
k7_counters_mirrored = 0;
break;
}
+ } else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+ amd_num_counters = F10H_NUM_COUNTERS;
+ amd_counters_base = MSR_K7_PERFCTR0;
+ amd_ctrls_base = MSR_K7_EVNTSEL0;
+ amd_msr_step = 1;
+ k7_counters_mirrored = 0;
} else {
uint32_t eax, ebx, ecx, edx;
@@ -285,7 +291,7 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
if (is_amd_pmu_msr(msr)) {
if (!xen_amd_pmu_emulate(msr, val, 1))
*val = native_read_msr_safe(msr, err);
@@ -308,7 +314,7 @@ bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err)
{
uint64_t val = ((uint64_t)high << 32) | low;
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
if (is_amd_pmu_msr(msr)) {
if (!xen_amd_pmu_emulate(msr, &val, 0))
*err = native_write_msr_safe(msr, low, high);
@@ -379,7 +385,7 @@ static unsigned long long xen_intel_read_pmc(int counter)
unsigned long long xen_read_pmc(int counter)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return xen_amd_read_pmc(counter);
else
return xen_intel_read_pmc(counter);
diff --git a/block/bio.c b/block/bio.c
index 94d5ea431a85..3107026bbcf2 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1285,8 +1285,11 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
}
}
- if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
+ if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+ if (!map_data)
+ __free_page(page);
break;
+ }
len -= bytes;
offset = 0;
diff --git a/block/genhd.c b/block/genhd.c
index 99acc0928d0d..d3fc8bbe13f2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -518,6 +518,18 @@ void blk_free_devt(dev_t devt)
}
}
+/**
+ * We invalidate devt by assigning NULL pointer for devt in idr.
+ */
+void blk_invalidate_devt(dev_t devt)
+{
+ if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
+ spin_lock_bh(&ext_devt_lock);
+ idr_replace(&ext_devt_idr, NULL, blk_mangle_minor(MINOR(devt)));
+ spin_unlock_bh(&ext_devt_lock);
+ }
+}
+
static char *bdevt_str(dev_t devt, char *buf)
{
if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) {
@@ -778,6 +790,13 @@ void del_gendisk(struct gendisk *disk)
if (!(disk->flags & GENHD_FL_HIDDEN))
blk_unregister_region(disk_devt(disk), disk->minors);
+ /*
+ * Remove gendisk pointer from idr so that it cannot be looked up
+ * while RCU period before freeing gendisk is running to prevent
+ * use-after-free issues. Note that the device number stays
+ * "in-use" until we really free the gendisk.
+ */
+ blk_invalidate_devt(disk_devt(disk));
kobject_put(disk->part0.holder_dir);
kobject_put(disk->slave_dir);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index cc9def1f4dd4..146f2380a79d 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -281,6 +281,13 @@ void delete_partition(struct gendisk *disk, int partno)
kobject_put(part->holder_dir);
device_del(part_to_dev(part));
+ /*
+ * Remove gendisk pointer from idr so that it cannot be looked up
+ * while RCU period before freeing gendisk is running to prevent
+ * use-after-free issues. Note that the device number stays
+ * "in-use" until we really free the gendisk.
+ */
+ blk_invalidate_devt(part_devt(part));
hd_struct_kill(part);
}
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 2d443de2d5ab..ee4e1d51413d 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -72,6 +72,7 @@ static void power_saving_mwait_init(void)
#if defined(CONFIG_X86)
switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
/*
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index e9fb0bf3c8d2..78f9de260d5f 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -417,6 +417,10 @@ acpi_ds_eval_region_operands(struct acpi_walk_state *walk_state,
ACPI_FORMAT_UINT64(obj_desc->region.address),
obj_desc->region.length));
+ status = acpi_ut_add_address_range(obj_desc->region.space_id,
+ obj_desc->region.address,
+ obj_desc->region.length, node);
+
/* Now the address and length are valid for this opregion */
obj_desc->region.flags |= AOPOBJ_DATA_VALID;
diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c
index 8638f43cfc3d..79d86da1c892 100644
--- a/drivers/acpi/acpica/nsobject.c
+++ b/drivers/acpi/acpica/nsobject.c
@@ -186,6 +186,10 @@ void acpi_ns_detach_object(struct acpi_namespace_node *node)
}
}
+ if (obj_desc->common.type == ACPI_TYPE_REGION) {
+ acpi_ut_remove_address_range(obj_desc->region.space_id, node);
+ }
+
/* Clear the Node entry in all cases */
node->object = NULL;
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 86ea6840525d..28eb273f53bd 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -442,8 +442,11 @@ static int acpi_button_resume(struct device *dev)
struct acpi_button *button = acpi_driver_data(device);
button->suspended = false;
- if (button->type == ACPI_BUTTON_TYPE_LID)
+ if (button->type == ACPI_BUTTON_TYPE_LID) {
+ button->last_state = !!acpi_lid_evaluate_state(device);
+ button->last_time = ktime_get();
acpi_lid_initialize_state(device);
+ }
return 0;
}
#endif
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 5c8aa9cf62d7..f260c62b6287 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -203,6 +203,7 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr,
static void tsc_check_state(int state)
{
switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
/*
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index a012c623e332..c855a0cf3f75 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -760,6 +760,8 @@ static int acpi_freeze_prepare(void)
if (acpi_sci_irq_valid())
enable_irq_wake(acpi_sci_irq);
+ acpi_enable_wakeup_devices(ACPI_STATE_S0);
+
/* Change the configuration of GPEs to avoid spurious wakeup. */
acpi_enable_all_wakeup_gpes();
acpi_os_wait_events_complete();
@@ -797,6 +799,8 @@ static void acpi_freeze_restore(void)
{
acpi_enable_all_runtime_gpes();
+ acpi_disable_wakeup_devices(ACPI_STATE_S0);
+
if (acpi_sci_irq_valid())
disable_irq_wake(acpi_sci_irq);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 0a9e5979aaa9..5021f6b71cd7 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -798,6 +798,7 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
dev = bus_find_device(&acpi_bus_type, NULL, &match,
acpi_dev_present_cb);
+ put_device(dev);
return !!dev;
}
EXPORT_SYMBOL(acpi_dev_present);
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 44fa4b7afc41..9b495725da13 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -25,8 +25,14 @@ struct devres_node {
struct devres {
struct devres_node node;
- /* -- 3 pointers */
- unsigned long long data[]; /* guarantee ull alignment */
+ /*
+ * Some archs want to perform DMA into kmalloc caches
+ * and need a guaranteed alignment larger than
+ * the alignment of a 64-bit integer.
+ * Thus we use ARCH_KMALLOC_MINALIGN here and get exactly the same
+ * buffer alignment as if it was allocated by plain kmalloc().
+ */
+ u8 __aligned(ARCH_KMALLOC_MINALIGN) data[];
};
struct devres_group {
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index c052d457d2db..021c6d6baed7 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -215,6 +215,9 @@ struct ipmi_user {
/* Does this interface receive IPMI events? */
bool gets_events;
+
+ /* Free must run in process context for RCU cleanup. */
+ struct work_struct remove_work;
};
static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
@@ -904,7 +907,7 @@ static int deliver_response(struct ipmi_smi *intf, struct ipmi_recv_msg *msg)
if (user) {
user->handler->ipmi_recv_hndl(msg, user->handler_data);
- release_ipmi_user(msg->user, index);
+ release_ipmi_user(user, index);
} else {
/* User went away, give up. */
ipmi_free_recv_msg(msg);
@@ -1088,6 +1091,14 @@ static int intf_err_seq(struct ipmi_smi *intf,
return rv;
}
+static void free_user_work(struct work_struct *work)
+{
+ struct ipmi_user *user = container_of(work, struct ipmi_user,
+ remove_work);
+
+ cleanup_srcu_struct(&user->release_barrier);
+ kfree(user);
+}
int ipmi_create_user(unsigned int if_num,
const struct ipmi_user_hndl *handler,
@@ -1141,6 +1152,8 @@ int ipmi_create_user(unsigned int if_num,
goto out_kfree;
found:
+ INIT_WORK(&new_user->remove_work, free_user_work);
+
rv = init_srcu_struct(&new_user->release_barrier);
if (rv)
goto out_kfree;
@@ -1203,8 +1216,9 @@ EXPORT_SYMBOL(ipmi_get_smi_info);
static void free_user(struct kref *ref)
{
struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
- cleanup_srcu_struct(&user->release_barrier);
- kfree(user);
+
+ /* SRCU cleanup must happen in task context. */
+ schedule_work(&user->remove_work);
}
static void _ipmi_destroy_user(struct ipmi_user *user)
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 3a2ca0f79daf..4796aa11ccc5 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -61,6 +61,7 @@ enum {
#define INTEL_MSR_RANGE (0xffff)
#define AMD_MSR_RANGE (0x7)
+#define HYGON_MSR_RANGE (0x7)
#define MSR_K7_HWCR_CPB_DIS (1ULL << 25)
@@ -95,6 +96,7 @@ static bool boost_state(unsigned int cpu)
rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi);
msr = lo | ((u64)hi << 32);
return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
msr = lo | ((u64)hi << 32);
@@ -113,6 +115,7 @@ static int boost_set_msr(bool enable)
msr_addr = MSR_IA32_MISC_ENABLE;
msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE;
break;
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
msr_addr = MSR_K7_HWCR;
msr_mask = MSR_K7_HWCR_CPB_DIS;
@@ -225,6 +228,8 @@ static unsigned extract_msr(struct cpufreq_policy *policy, u32 msr)
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
msr &= AMD_MSR_RANGE;
+ else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ msr &= HYGON_MSR_RANGE;
else
msr &= INTEL_MSR_RANGE;
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index 042023bbbf62..4ac7c3cf34be 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -14,6 +14,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
+#include <linux/pci.h>
#include <linux/percpu-defs.h>
#include <linux/init.h>
#include <linux/mod_devicetable.h>
@@ -109,12 +110,23 @@ out:
static int __init amd_freq_sensitivity_init(void)
{
u64 val;
-
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ struct pci_dev *pcidev;
+ unsigned int pci_vendor;
+
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ pci_vendor = PCI_VENDOR_ID_AMD;
+ else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ pci_vendor = PCI_VENDOR_ID_HYGON;
+ else
return -ENODEV;
- if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK))
- return -ENODEV;
+ pcidev = pci_get_device(pci_vendor,
+ PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, NULL);
+
+ if (!pcidev) {
+ if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK))
+ return -ENODEV;
+ }
if (rdmsrl_safe(MSR_AMD64_FREQ_SENSITIVITY_ACTUAL, &val))
return -ENODEV;
diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c
index 18987fcfe654..700d944f8407 100644
--- a/drivers/crypto/caam/error.c
+++ b/drivers/crypto/caam/error.c
@@ -21,7 +21,7 @@ void caam_dump_sg(const char *level, const char *prefix_str, int prefix_type,
size_t len;
void *buf;
- for (it = sg; it && tlen > 0 ; it = sg_next(sg)) {
+ for (it = sg; it && tlen > 0 ; it = sg_next(it)) {
/*
* make sure the scatterlist's page
* has a valid virtual memory mapping
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index de78282b8f44..9c6b5c1d6a1a 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -1357,7 +1357,7 @@ Loop_ctr32_enc:
addi $idx,$idx,16
bdnz Loop_ctr32_enc
- vadduwm $ivec,$ivec,$one
+ vadduqm $ivec,$ivec,$one
vmr $dat,$inptail
lvx $inptail,0,$inp
addi $inp,$inp,16
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 529bcbf9c53b..3e91eb45e9dc 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -211,7 +211,7 @@ static int __set_scrub_rate(struct amd64_pvt *pvt, u32 new_bw, u32 min_rate)
scrubval = scrubrates[i].scrubval;
- if (pvt->fam == 0x17) {
+ if (pvt->fam == 0x17 || pvt->fam == 0x18) {
__f17h_set_scrubval(pvt, scrubval);
} else if (pvt->fam == 0x15 && pvt->model == 0x60) {
f15h_select_dct(pvt, 0);
@@ -264,6 +264,7 @@ static int get_scrub_rate(struct mem_ctl_info *mci)
break;
case 0x17:
+ case 0x18:
amd64_read_pci_cfg(pvt->F6, F17H_SCR_BASE_ADDR, &scrubval);
if (scrubval & BIT(0)) {
amd64_read_pci_cfg(pvt->F6, F17H_SCR_LIMIT_ADDR, &scrubval);
@@ -1044,6 +1045,7 @@ static void determine_memory_type(struct amd64_pvt *pvt)
goto ddr3;
case 0x17:
+ case 0x18:
if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(5))
pvt->dram_type = MEM_LRDDR4;
else if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(4))
@@ -3189,8 +3191,13 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
break;
case 0x17:
+ /* fall through */
+ case 0x18:
fam_type = &family_types[F17_CPUS];
pvt->ops = &family_types[F17_CPUS].ops;
+
+ if (pvt->fam == 0x18)
+ family_types[F17_CPUS].ctl_name = "F18h";
break;
default:
@@ -3429,6 +3436,7 @@ static const struct x86_cpu_id amd64_cpuids[] = {
{ X86_VENDOR_AMD, 0x15, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
{ X86_VENDOR_AMD, 0x16, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
{ X86_VENDOR_AMD, 0x17, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
+ { X86_VENDOR_HYGON, 0x18, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
{ }
};
MODULE_DEVICE_TABLE(x86cpu, amd64_cpuids);
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 9fe7350bb044..ee6f5535edb4 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -1154,7 +1154,8 @@ static int __init mce_amd_init(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
- if (c->x86_vendor != X86_VENDOR_AMD)
+ if (c->x86_vendor != X86_VENDOR_AMD &&
+ c->x86_vendor != X86_VENDOR_HYGON)
return -ENODEV;
fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL);
@@ -1208,6 +1209,7 @@ static int __init mce_amd_init(void)
break;
case 0x17:
+ case 0x18:
xec_mask = 0x3f;
if (!boot_cpu_has(X86_FEATURE_SMCA)) {
printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n");
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index bb0cda727605..e3f5e5d6f0c1 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1213,6 +1213,11 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
return UPDATE_TYPE_FULL;
}
+ if (u->surface->force_full_update) {
+ update_flags->bits.full_update = 1;
+ return UPDATE_TYPE_FULL;
+ }
+
type = get_plane_info_update_type(u);
elevate_update_type(&overall_type, type);
@@ -1467,6 +1472,14 @@ void dc_commit_updates_for_stream(struct dc *dc,
}
dc_resource_state_copy_construct(state, context);
+
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+ if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
+ new_pipe->plane_state->force_full_update = true;
+ }
}
@@ -1510,6 +1523,12 @@ void dc_commit_updates_for_stream(struct dc *dc,
dc->current_state = context;
dc_release_state(old);
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+ if (pipe_ctx->plane_state && pipe_ctx->stream == stream)
+ pipe_ctx->plane_state->force_full_update = false;
+ }
}
/*let's use current_state to update watermark etc*/
if (update_type >= UPDATE_TYPE_FULL)
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 6c9990bef267..4094b4f50111 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -505,6 +505,9 @@ struct dc_plane_state {
struct dc_plane_status status;
struct dc_context *ctx;
+ /* HACK: Workaround for forcing full reprogramming under some conditions */
+ bool force_full_update;
+
/* private to dc_surface.c */
enum dc_irq_source irq_source;
struct kref refcount;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index 3f5b2e6f7553..df936edac5c7 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -189,6 +189,12 @@ static void submit_channel_request(
1,
0);
}
+
+ REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
+
+ REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
+ 10, aux110->timeout_period/10);
+
/* set the delay and the number of bytes to write */
/* The length include
@@ -241,9 +247,6 @@ static void submit_channel_request(
}
}
- REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
- REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
- 10, aux110->timeout_period/10);
REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index f7caab85dc80..2c6f50b4245a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -69,11 +69,11 @@ enum { /* This is the timeout as defined in DP 1.2a,
* at most within ~240usec. That means,
* increasing this timeout will not affect normal operation,
* and we'll timeout after
- * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec.
+ * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 2400usec.
* This timeout is especially important for
- * resume from S3 and CTS.
+ * converters, resume from S3, and CTS.
*/
- SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4
+ SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 6
};
struct aux_engine_dce110 {
struct aux_engine base;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 85c2d407a52e..e7ddd3e3db92 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -747,11 +747,11 @@ static void adv7511_mode_set(struct adv7511 *adv7511,
vsync_polarity = 1;
}
- if (mode->vrefresh <= 24000)
+ if (drm_mode_vrefresh(mode) <= 24)
low_refresh_rate = ADV7511_LOW_REFRESH_RATE_24HZ;
- else if (mode->vrefresh <= 25000)
+ else if (drm_mode_vrefresh(mode) <= 25)
low_refresh_rate = ADV7511_LOW_REFRESH_RATE_25HZ;
- else if (mode->vrefresh <= 30000)
+ else if (drm_mode_vrefresh(mode) <= 30)
low_refresh_rate = ADV7511_LOW_REFRESH_RATE_30HZ;
else
low_refresh_rate = ADV7511_LOW_REFRESH_RATE_NONE;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7ebf1b708e5b..6fe1d3491686 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1732,6 +1732,8 @@ struct drm_i915_private {
struct intel_cdclk_state actual;
/* The current hardware cdclk state */
struct intel_cdclk_state hw;
+
+ int force_min_cdclk;
} cdclk;
/**
@@ -1852,6 +1854,7 @@ struct drm_i915_private {
*
*/
struct mutex av_mutex;
+ int audio_power_refcount;
struct {
struct mutex mutex;
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index ee3ca2de983b..b0847d24c192 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -742,13 +742,70 @@ void intel_init_audio_hooks(struct drm_i915_private *dev_priv)
}
}
+static void glk_force_audio_cdclk(struct drm_i915_private *dev_priv,
+ bool enable)
+{
+ struct drm_modeset_acquire_ctx ctx;
+ struct drm_atomic_state *state;
+ int ret;
+
+ drm_modeset_acquire_init(&ctx, 0);
+ state = drm_atomic_state_alloc(&dev_priv->drm);
+ if (WARN_ON(!state))
+ return;
+
+ state->acquire_ctx = &ctx;
+
+retry:
+ to_intel_atomic_state(state)->cdclk.force_min_cdclk_changed = true;
+ to_intel_atomic_state(state)->cdclk.force_min_cdclk =
+ enable ? 2 * 96000 : 0;
+
+ /*
+ * Protects dev_priv->cdclk.force_min_cdclk
+ * Need to lock this here in case we have no active pipes
+ * and thus wouldn't lock it during the commit otherwise.
+ */
+ ret = drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex,
+ &ctx);
+ if (!ret)
+ ret = drm_atomic_commit(state);
+
+ if (ret == -EDEADLK) {
+ drm_atomic_state_clear(state);
+ drm_modeset_backoff(&ctx);
+ goto retry;
+ }
+
+ WARN_ON(ret);
+
+ drm_atomic_state_put(state);
+
+ drm_modeset_drop_locks(&ctx);
+ drm_modeset_acquire_fini(&ctx);
+}
+
static void i915_audio_component_get_power(struct device *kdev)
{
+ struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
+
intel_display_power_get(kdev_to_i915(kdev), POWER_DOMAIN_AUDIO);
+
+ /* Force CDCLK to 2*BCLK as long as we need audio to be powered. */
+ if (dev_priv->audio_power_refcount++ == 0)
+ if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+ glk_force_audio_cdclk(dev_priv, true);
}
static void i915_audio_component_put_power(struct device *kdev)
{
+ struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
+
+ /* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */
+ if (--dev_priv->audio_power_refcount == 0)
+ if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+ glk_force_audio_cdclk(dev_priv, false);
+
intel_display_power_put(kdev_to_i915(kdev), POWER_DOMAIN_AUDIO);
}
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 8d74276029e6..30f5881f6e0e 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -2185,19 +2185,8 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
/*
* According to BSpec, "The CD clock frequency must be at least twice
* the frequency of the Azalia BCLK." and BCLK is 96 MHz by default.
- *
- * FIXME: Check the actual, not default, BCLK being used.
- *
- * FIXME: This does not depend on ->has_audio because the higher CDCLK
- * is required for audio probe, also when there are no audio capable
- * displays connected at probe time. This leads to unnecessarily high
- * CDCLK when audio is not required.
- *
- * FIXME: This limit is only applied when there are displays connected
- * at probe time. If we probe without displays, we'll still end up using
- * the platform minimum CDCLK, failing audio probe.
*/
- if (INTEL_GEN(dev_priv) >= 9)
+ if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
min_cdclk = max(2 * 96000, min_cdclk);
/*
@@ -2237,7 +2226,7 @@ static int intel_compute_min_cdclk(struct drm_atomic_state *state)
intel_state->min_cdclk[i] = min_cdclk;
}
- min_cdclk = 0;
+ min_cdclk = intel_state->cdclk.force_min_cdclk;
for_each_pipe(dev_priv, pipe)
min_cdclk = max(intel_state->min_cdclk[pipe], min_cdclk);
@@ -2298,7 +2287,8 @@ static int vlv_modeset_calc_cdclk(struct drm_atomic_state *state)
vlv_calc_voltage_level(dev_priv, cdclk);
if (!intel_state->active_crtcs) {
- cdclk = vlv_calc_cdclk(dev_priv, 0);
+ cdclk = vlv_calc_cdclk(dev_priv,
+ intel_state->cdclk.force_min_cdclk);
intel_state->cdclk.actual.cdclk = cdclk;
intel_state->cdclk.actual.voltage_level =
@@ -2331,7 +2321,7 @@ static int bdw_modeset_calc_cdclk(struct drm_atomic_state *state)
bdw_calc_voltage_level(cdclk);
if (!intel_state->active_crtcs) {
- cdclk = bdw_calc_cdclk(0);
+ cdclk = bdw_calc_cdclk(intel_state->cdclk.force_min_cdclk);
intel_state->cdclk.actual.cdclk = cdclk;
intel_state->cdclk.actual.voltage_level =
@@ -2403,7 +2393,7 @@ static int skl_modeset_calc_cdclk(struct drm_atomic_state *state)
skl_calc_voltage_level(cdclk);
if (!intel_state->active_crtcs) {
- cdclk = skl_calc_cdclk(0, vco);
+ cdclk = skl_calc_cdclk(intel_state->cdclk.force_min_cdclk, vco);
intel_state->cdclk.actual.vco = vco;
intel_state->cdclk.actual.cdclk = cdclk;
@@ -2442,10 +2432,10 @@ static int bxt_modeset_calc_cdclk(struct drm_atomic_state *state)
if (!intel_state->active_crtcs) {
if (IS_GEMINILAKE(dev_priv)) {
- cdclk = glk_calc_cdclk(0);
+ cdclk = glk_calc_cdclk(intel_state->cdclk.force_min_cdclk);
vco = glk_de_pll_vco(dev_priv, cdclk);
} else {
- cdclk = bxt_calc_cdclk(0);
+ cdclk = bxt_calc_cdclk(intel_state->cdclk.force_min_cdclk);
vco = bxt_de_pll_vco(dev_priv, cdclk);
}
@@ -2481,7 +2471,7 @@ static int cnl_modeset_calc_cdclk(struct drm_atomic_state *state)
cnl_compute_min_voltage_level(intel_state));
if (!intel_state->active_crtcs) {
- cdclk = cnl_calc_cdclk(0);
+ cdclk = cnl_calc_cdclk(intel_state->cdclk.force_min_cdclk);
vco = cnl_cdclk_pll_vco(dev_priv, cdclk);
intel_state->cdclk.actual.vco = vco;
@@ -2517,7 +2507,7 @@ static int icl_modeset_calc_cdclk(struct drm_atomic_state *state)
cnl_compute_min_voltage_level(intel_state));
if (!intel_state->active_crtcs) {
- cdclk = icl_calc_cdclk(0, ref);
+ cdclk = icl_calc_cdclk(intel_state->cdclk.force_min_cdclk, ref);
vco = icl_calc_cdclk_pll_vco(dev_priv, cdclk);
intel_state->cdclk.actual.vco = vco;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 4641c4c4a726..a6d0a62da836 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12305,6 +12305,11 @@ static int intel_modeset_checks(struct drm_atomic_state *state)
return -EINVAL;
}
+ /* keep the current setting */
+ if (!intel_state->cdclk.force_min_cdclk_changed)
+ intel_state->cdclk.force_min_cdclk =
+ dev_priv->cdclk.force_min_cdclk;
+
intel_state->modeset = true;
intel_state->active_crtcs = dev_priv->active_crtcs;
intel_state->cdclk.logical = dev_priv->cdclk.logical;
@@ -12400,7 +12405,7 @@ static int intel_atomic_check(struct drm_device *dev,
struct drm_crtc *crtc;
struct drm_crtc_state *old_crtc_state, *crtc_state;
int ret, i;
- bool any_ms = false;
+ bool any_ms = intel_state->cdclk.force_min_cdclk_changed;
/* Catch I915_MODE_FLAG_INHERITED */
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
@@ -12959,6 +12964,8 @@ static int intel_atomic_commit(struct drm_device *dev,
dev_priv->active_crtcs = intel_state->active_crtcs;
dev_priv->cdclk.logical = intel_state->cdclk.logical;
dev_priv->cdclk.actual = intel_state->cdclk.actual;
+ dev_priv->cdclk.force_min_cdclk =
+ intel_state->cdclk.force_min_cdclk;
}
drm_atomic_state_get(state);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 24c92095eb88..0b5acec9a014 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -467,6 +467,9 @@ struct intel_atomic_state {
* state only when all crtc's are DPMS off.
*/
struct intel_cdclk_state actual;
+
+ int force_min_cdclk;
+ bool force_min_cdclk_changed;
} cdclk;
bool dpll_set, modeset;
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 01d1d2088f04..728a20e1f638 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -1267,6 +1267,10 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
if (!HAS_FBC(dev_priv))
return 0;
+ /* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */
+ if (IS_GEMINILAKE(dev_priv))
+ return 0;
+
if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
return 1;
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 7d4b710b837a..11e2dcdd6b18 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -78,7 +78,7 @@ static void ipu_crtc_disable_planes(struct ipu_crtc *ipu_crtc,
if (disable_partial)
ipu_plane_disable(ipu_crtc->plane[1], true);
if (disable_full)
- ipu_plane_disable(ipu_crtc->plane[0], false);
+ ipu_plane_disable(ipu_crtc->plane[0], true);
}
static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 754f6b25f265..6d9f78612dee 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -531,14 +531,15 @@ pl111_init_clock_divider(struct drm_device *drm)
dev_err(drm->dev, "CLCD: unable to get clcdclk.\n");
return PTR_ERR(parent);
}
+
+ spin_lock_init(&priv->tim2_lock);
+
/* If the clock divider is broken, use the parent directly */
if (priv->variant->broken_clockdivider) {
priv->clk = parent;
return 0;
}
parent_name = __clk_get_name(parent);
-
- spin_lock_init(&priv->tim2_lock);
div->init = &init;
ret = devm_clk_hw_register(drm->dev, div);
diff --git a/drivers/gpu/ipu-v3/ipu-dp.c b/drivers/gpu/ipu-v3/ipu-dp.c
index 9b2b3fa479c4..5e44ff1f2085 100644
--- a/drivers/gpu/ipu-v3/ipu-dp.c
+++ b/drivers/gpu/ipu-v3/ipu-dp.c
@@ -195,7 +195,8 @@ int ipu_dp_setup_channel(struct ipu_dp *dp,
ipu_dp_csc_init(flow, flow->foreground.in_cs, flow->out_cs,
DP_COM_CONF_CSC_DEF_BOTH);
} else {
- if (flow->foreground.in_cs == flow->out_cs)
+ if (flow->foreground.in_cs == IPUV3_COLORSPACE_UNKNOWN ||
+ flow->foreground.in_cs == flow->out_cs)
/*
* foreground identical to output, apply color
* conversion on background
@@ -261,6 +262,8 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync)
struct ipu_dp_priv *priv = flow->priv;
u32 reg, csc;
+ dp->in_cs = IPUV3_COLORSPACE_UNKNOWN;
+
if (!dp->foreground)
return;
@@ -268,8 +271,9 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync)
reg = readl(flow->base + DP_COM_CONF);
csc = reg & DP_COM_CONF_CSC_DEF_MASK;
- if (csc == DP_COM_CONF_CSC_DEF_FG)
- reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+ reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+ if (csc == DP_COM_CONF_CSC_DEF_BOTH || csc == DP_COM_CONF_CSC_DEF_BG)
+ reg |= DP_COM_CONF_CSC_DEF_BG;
reg &= ~DP_COM_CONF_FG_EN;
writel(reg, flow->base + DP_COM_CONF);
@@ -347,6 +351,8 @@ int ipu_dp_init(struct ipu_soc *ipu, struct device *dev, unsigned long base)
mutex_init(&priv->mutex);
for (i = 0; i < IPUV3_NUM_FLOWS; i++) {
+ priv->flow[i].background.in_cs = IPUV3_COLORSPACE_UNKNOWN;
+ priv->flow[i].foreground.in_cs = IPUV3_COLORSPACE_UNKNOWN;
priv->flow[i].foreground.foreground = true;
priv->flow[i].base = priv->base + ipu_dp_flow_base[i];
priv->flow[i].priv = priv;
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 676b9fa7748e..aabf12a00e1f 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -608,6 +608,14 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
break;
}
+ if ((usage->hid & 0xf0) == 0xb0) { /* SC - Display */
+ switch (usage->hid & 0xf) {
+ case 0x05: map_key_clear(KEY_SWITCHVIDEOMODE); break;
+ default: goto ignore;
+ }
+ break;
+ }
+
/*
* Some lazy vendors declare 255 usages for System Control,
* leading to the creation of ABS_X|Y axis and too many others.
@@ -803,6 +811,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
case 0x074: map_key_clear(KEY_BRIGHTNESS_MAX); break;
case 0x075: map_key_clear(KEY_BRIGHTNESS_AUTO); break;
+ case 0x079: map_key_clear(KEY_KBDILLUMUP); break;
+ case 0x07a: map_key_clear(KEY_KBDILLUMDOWN); break;
+ case 0x07c: map_key_clear(KEY_KBDILLUMTOGGLE); break;
+
case 0x082: map_key_clear(KEY_VIDEO_NEXT); break;
case 0x083: map_key_clear(KEY_LAST); break;
case 0x084: map_key_clear(KEY_ENTER); break;
@@ -934,6 +946,8 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
case 0x2cb: map_key_clear(KEY_KBDINPUTASSIST_ACCEPT); break;
case 0x2cc: map_key_clear(KEY_KBDINPUTASSIST_CANCEL); break;
+ case 0x29f: map_key_clear(KEY_SCALE); break;
+
default: map_key_clear(KEY_UNKNOWN);
}
break;
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index 56cf5907a5f0..143894a315d9 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -1299,7 +1299,7 @@ static int xadc_remove(struct platform_device *pdev)
}
free_irq(irq, indio_dev);
clk_disable_unprepare(xadc->clk);
- cancel_delayed_work(&xadc->zynq_unmask_work);
+ cancel_delayed_work_sync(&xadc->zynq_unmask_work);
kfree(xadc->data);
kfree(indio_dev->channels);
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index e820bcfa2fed..2b30d16655e6 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1225,22 +1225,47 @@ static const struct acpi_device_id elan_acpi_id[] = {
{ "ELAN0600", 0 },
{ "ELAN0601", 0 },
{ "ELAN0602", 0 },
+ { "ELAN0603", 0 },
+ { "ELAN0604", 0 },
{ "ELAN0605", 0 },
+ { "ELAN0606", 0 },
+ { "ELAN0607", 0 },
{ "ELAN0608", 0 },
{ "ELAN0605", 0 },
{ "ELAN0609", 0 },
{ "ELAN060B", 0 },
{ "ELAN060C", 0 },
+ { "ELAN060F", 0 },
+ { "ELAN0610", 0 },
{ "ELAN0611", 0 },
{ "ELAN0612", 0 },
+ { "ELAN0615", 0 },
+ { "ELAN0616", 0 },
{ "ELAN0617", 0 },
{ "ELAN0618", 0 },
+ { "ELAN0619", 0 },
+ { "ELAN061A", 0 },
+ { "ELAN061B", 0 },
{ "ELAN061C", 0 },
{ "ELAN061D", 0 },
{ "ELAN061E", 0 },
+ { "ELAN061F", 0 },
{ "ELAN0620", 0 },
{ "ELAN0621", 0 },
{ "ELAN0622", 0 },
+ { "ELAN0623", 0 },
+ { "ELAN0624", 0 },
+ { "ELAN0625", 0 },
+ { "ELAN0626", 0 },
+ { "ELAN0627", 0 },
+ { "ELAN0628", 0 },
+ { "ELAN0629", 0 },
+ { "ELAN062A", 0 },
+ { "ELAN062B", 0 },
+ { "ELAN062C", 0 },
+ { "ELAN062D", 0 },
+ { "ELAN0631", 0 },
+ { "ELAN0632", 0 },
{ "ELAN1000", 0 },
{ }
};
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index f5954981e9ee..997ccae7ee05 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -883,7 +883,7 @@ static int rmi_create_function(struct rmi_device *rmi_dev,
error = rmi_register_function(fn);
if (error)
- goto err_put_fn;
+ return error;
if (pdt->function_number == 0x01)
data->f01_container = fn;
@@ -893,10 +893,6 @@ static int rmi_create_function(struct rmi_device *rmi_dev,
list_add_tail(&fn->node, &data->function_list);
return RMI_SCAN_CONTINUE;
-
-err_put_fn:
- put_device(&fn->dev);
- return error;
}
void rmi_enable_irq(struct rmi_device *rmi_dev, bool clear_wake)
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 312617cdad54..1ce36898c0c0 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -721,10 +721,10 @@ base_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
struct sock *sk = sock->sk;
int err = 0;
- if (!maddr || maddr->family != AF_ISDN)
+ if (addr_len < sizeof(struct sockaddr_mISDN))
return -EINVAL;
- if (addr_len < sizeof(struct sockaddr_mISDN))
+ if (!maddr || maddr->family != AF_ISDN)
return -EINVAL;
lock_sock(sk);
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index 8d456dc6c5bf..83f9bbe57e02 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -101,8 +101,9 @@ static int led_pwm_add(struct device *dev, struct led_pwm_priv *priv,
led_data->pwm = devm_pwm_get(dev, led->name);
if (IS_ERR(led_data->pwm)) {
ret = PTR_ERR(led_data->pwm);
- dev_err(dev, "unable to request PWM for %s: %d\n",
- led->name, ret);
+ if (ret != -EPROBE_DEFER)
+ dev_err(dev, "unable to request PWM for %s: %d\n",
+ led->name, ret);
return ret;
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index bd369b5d399e..19de429e7849 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1797,6 +1797,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
} else
set_bit(In_sync, &rdev->flags);
rdev->raid_disk = role;
+ if (role >= mddev->raid_disks) {
+ rdev->saved_raid_disk = -1;
+ rdev->raid_disk = -1;
+ }
break;
}
if (sb->devflags & WriteMostly1)
diff --git a/drivers/media/platform/atmel/atmel-isc.c b/drivers/media/platform/atmel/atmel-isc.c
index c4b2115559a5..caf8f7842d1c 100644
--- a/drivers/media/platform/atmel/atmel-isc.c
+++ b/drivers/media/platform/atmel/atmel-isc.c
@@ -1553,6 +1553,8 @@ static int isc_async_complete(struct v4l2_async_notifier *notifier)
struct vb2_queue *q = &isc->vb2_vidq;
int ret;
+ INIT_WORK(&isc->awb_work, isc_awb_work);
+
ret = v4l2_device_register_subdev_nodes(&isc->v4l2_dev);
if (ret < 0) {
v4l2_err(&isc->v4l2_dev, "Failed to register subdev nodes\n");
@@ -1612,8 +1614,6 @@ static int isc_async_complete(struct v4l2_async_notifier *notifier)
return ret;
}
- INIT_WORK(&isc->awb_work, isc_awb_work);
-
/* Register video device */
strlcpy(vdev->name, ATMEL_ISC_NAME, sizeof(vdev->name));
vdev->release = video_device_release_empty;
diff --git a/drivers/media/platform/davinci/vpbe.c b/drivers/media/platform/davinci/vpbe.c
index e5c295f11d0e..b3e29b40cf30 100644
--- a/drivers/media/platform/davinci/vpbe.c
+++ b/drivers/media/platform/davinci/vpbe.c
@@ -126,7 +126,7 @@ static int vpbe_enum_outputs(struct vpbe_device *vpbe_dev,
struct v4l2_output *output)
{
struct vpbe_config *cfg = vpbe_dev->cfg;
- int temp_index = output->index;
+ unsigned int temp_index = output->index;
if (temp_index >= cfg->num_outputs)
return -EINVAL;
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index 6f1b0c799e58..eb201a184f5a 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -1528,23 +1528,20 @@ static int vidioc_dqbuf(struct file *file, void *fh, struct v4l2_buffer *b)
unsigned long size;
struct videobuf_buffer *vb;
- vb = q->bufs[b->index];
-
if (!vout->streaming)
return -EINVAL;
- if (file->f_flags & O_NONBLOCK)
- /* Call videobuf_dqbuf for non blocking mode */
- ret = videobuf_dqbuf(q, (struct v4l2_buffer *)b, 1);
- else
- /* Call videobuf_dqbuf for blocking mode */
- ret = videobuf_dqbuf(q, (struct v4l2_buffer *)b, 0);
+ ret = videobuf_dqbuf(q, b, !!(file->f_flags & O_NONBLOCK));
+ if (ret)
+ return ret;
+
+ vb = q->bufs[b->index];
addr = (unsigned long) vout->buf_phy_addr[vb->i];
size = (unsigned long) vb->size;
dma_unmap_single(vout->vid_dev->v4l2_dev.dev, addr,
size, DMA_TO_DEVICE);
- return ret;
+ return 0;
}
static int vidioc_streamon(struct file *file, void *fh, enum v4l2_buf_type i)
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index 9497f18eaba0..e95a7567bb23 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -156,8 +156,6 @@ static void dayna_block_output(struct net_device *dev, int count,
#define memcpy_fromio(a, b, c) memcpy((a), (void *)(b), (c))
#define memcpy_toio(a, b, c) memcpy((void *)(a), (b), (c))
-#define memcmp_withio(a, b, c) memcmp((a), (void *)(b), (c))
-
/* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
static void slow_sane_get_8390_hdr(struct net_device *dev,
struct e8390_pkt_hdr *hdr, int ring_page);
@@ -237,19 +235,26 @@ static enum mac8390_type __init mac8390_ident(struct nubus_dev *dev)
static enum mac8390_access __init mac8390_testio(volatile unsigned long membase)
{
- unsigned long outdata = 0xA5A0B5B0;
- unsigned long indata = 0x00000000;
+ u32 outdata = 0xA5A0B5B0;
+ u32 indata = 0;
+
/* Try writing 32 bits */
- memcpy_toio(membase, &outdata, 4);
- /* Now compare them */
- if (memcmp_withio(&outdata, membase, 4) == 0)
+ nubus_writel(outdata, membase);
+ /* Now read it back */
+ indata = nubus_readl(membase);
+ if (outdata == indata)
return ACCESS_32;
+
+ outdata = 0xC5C0D5D0;
+ indata = 0;
+
/* Write 16 bit output */
word_memcpy_tocard(membase, &outdata, 4);
/* Now read it back */
word_memcpy_fromcard(&indata, membase, 4);
if (outdata == indata)
return ACCESS_16;
+
return ACCESS_UNKNOWN;
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a64b68656d32..295bc249db07 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1129,6 +1129,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
tpa_info = &rxr->rx_tpa[agg_id];
if (unlikely(cons != rxr->rx_next_cons)) {
+ netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+ cons, rxr->rx_next_cons);
bnxt_sched_reset(bp, rxr);
return;
}
@@ -1581,15 +1583,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
}
cons = rxcmp->rx_cmp_opaque;
- rx_buf = &rxr->rx_buf_ring[cons];
- data = rx_buf->data;
- data_ptr = rx_buf->data_ptr;
if (unlikely(cons != rxr->rx_next_cons)) {
int rc1 = bnxt_discard_rx(bp, cpr, raw_cons, rxcmp);
+ netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+ cons, rxr->rx_next_cons);
bnxt_sched_reset(bp, rxr);
return rc1;
}
+ rx_buf = &rxr->rx_buf_ring[cons];
+ data = rx_buf->data;
+ data_ptr = rx_buf->data_ptr;
prefetch(data_ptr);
misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
@@ -1606,11 +1610,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
rx_buf->data = NULL;
if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+ u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
bnxt_reuse_rx_data(rxr, cons, data);
if (agg_bufs)
bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);
rc = -EIO;
+ if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+ netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+ bnxt_sched_reset(bp, rxr);
+ }
goto next_rx;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 3078491cc0d0..1539cf3de5dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
if (err)
return err;
+ mutex_lock(&mdev->mlx5e_res.td.list_lock);
list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+ mutex_unlock(&mdev->mlx5e_res.td.list_lock);
return 0;
}
@@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
struct mlx5e_tir *tir)
{
+ mutex_lock(&mdev->mlx5e_res.td.list_lock);
mlx5_core_destroy_tir(mdev, tir->tirn);
list_del(&tir->list);
+ mutex_unlock(&mdev->mlx5e_res.td.list_lock);
}
static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
@@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
}
INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+ mutex_init(&mdev->mlx5e_res.td.list_lock);
return 0;
@@ -141,15 +146,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
{
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_tir *tir;
- int err = -ENOMEM;
+ int err = 0;
u32 tirn = 0;
int inlen;
void *in;
inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
in = kvzalloc(inlen, GFP_KERNEL);
- if (!in)
+ if (!in) {
+ err = -ENOMEM;
goto out;
+ }
if (enable_uc_lb)
MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -157,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
+ mutex_lock(&mdev->mlx5e_res.td.list_lock);
list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
tirn = tir->tirn;
err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
@@ -168,6 +176,7 @@ out:
kvfree(in);
if (err)
netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+ mutex_unlock(&mdev->mlx5e_res.td.list_lock);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 77f0fae39340..1e5015c6677f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -162,26 +162,6 @@ static struct mlx5_profile profile[] = {
.size = 8,
.limit = 4
},
- .mr_cache[16] = {
- .size = 8,
- .limit = 4
- },
- .mr_cache[17] = {
- .size = 8,
- .limit = 4
- },
- .mr_cache[18] = {
- .size = 8,
- .limit = 4
- },
- .mr_cache[19] = {
- .size = 4,
- .limit = 2
- },
- .mr_cache[20] = {
- .size = 4,
- .limit = 2
- },
},
};
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 7a9f5a1c35c9..82baee142c8e 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -375,6 +375,7 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb)
.flowi4_oif = dev->ifindex,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC,
+ .flowi4_mark = skb->mark,
.daddr = ip4h->daddr,
.saddr = ip4h->saddr,
};
@@ -409,7 +410,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
struct dst_entry *dst;
int err, ret = NET_XMIT_DROP;
struct flowi6 fl6 = {
- .flowi6_iif = dev->ifindex,
+ .flowi6_oif = dev->ifindex,
.daddr = ip6h->daddr,
.saddr = ip6h->saddr,
.flowi6_flags = FLOWI_FLAG_ANYSRC,
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 05c5cc366886..5d1a9558b94f 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -648,6 +648,7 @@ void ipvlan_link_setup(struct net_device *dev)
{
ether_setup(dev);
+ dev->max_mtu = ETH_MAX_MTU;
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
dev->netdev_ops = &ipvlan_netdev_ops;
diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c
index 1e2d4f1179da..45df03673e01 100644
--- a/drivers/net/phy/spi_ks8995.c
+++ b/drivers/net/phy/spi_ks8995.c
@@ -162,6 +162,14 @@ static const struct spi_device_id ks8995_id[] = {
};
MODULE_DEVICE_TABLE(spi, ks8995_id);
+static const struct of_device_id ks8895_spi_of_match[] = {
+ { .compatible = "micrel,ks8995" },
+ { .compatible = "micrel,ksz8864" },
+ { .compatible = "micrel,ksz8795" },
+ { },
+ };
+MODULE_DEVICE_TABLE(of, ks8895_spi_of_match);
+
static inline u8 get_chip_id(u8 val)
{
return (val >> ID1_CHIPID_S) & ID1_CHIPID_M;
@@ -529,6 +537,7 @@ static int ks8995_remove(struct spi_device *spi)
static struct spi_driver ks8995_driver = {
.driver = {
.name = "spi-ks8995",
+ .of_match_table = of_match_ptr(ks8895_spi_of_match),
},
.probe = ks8995_probe,
.remove = ks8995_remove,
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 096a4e1d0bc4..9ff530ed3db7 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1247,6 +1247,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
goto err_option_port_add;
}
+ /* set promiscuity level to new slave */
+ if (dev->flags & IFF_PROMISC) {
+ err = dev_set_promiscuity(port_dev, 1);
+ if (err)
+ goto err_set_slave_promisc;
+ }
+
+ /* set allmulti level to new slave */
+ if (dev->flags & IFF_ALLMULTI) {
+ err = dev_set_allmulti(port_dev, 1);
+ if (err) {
+ if (dev->flags & IFF_PROMISC)
+ dev_set_promiscuity(port_dev, -1);
+ goto err_set_slave_promisc;
+ }
+ }
+
netif_addr_lock_bh(dev);
dev_uc_sync_multiple(port_dev, dev);
dev_mc_sync_multiple(port_dev, dev);
@@ -1263,6 +1280,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
return 0;
+err_set_slave_promisc:
+ __team_option_inst_del_port(team, port);
+
err_option_port_add:
team_upper_dev_unlink(team, port);
@@ -1308,6 +1328,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
team_port_disable(team, port);
list_del_rcu(&port->list);
+
+ if (dev->flags & IFF_PROMISC)
+ dev_set_promiscuity(port_dev, -1);
+ if (dev->flags & IFF_ALLMULTI)
+ dev_set_allmulti(port_dev, -1);
+
team_upper_dev_unlink(team, port);
netdev_rx_handler_unregister(port_dev);
team_port_disable_netpoll(port);
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index fa1843a7e0fd..e2d78f77edb7 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1190,7 +1190,7 @@ static int ath10k_wcn3990_clk_init(struct ath10k *ar)
return 0;
err_clock_config:
- for (; i >= 0; i--) {
+ for (i = i - 1; i >= 0; i--) {
clk_info = &ar_snoc->clk[i];
if (!clk_info->handle)
diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c
index 2b26f762fbc3..01acb6e53365 100644
--- a/drivers/nfc/st95hf/core.c
+++ b/drivers/nfc/st95hf/core.c
@@ -1074,6 +1074,12 @@ static const struct spi_device_id st95hf_id[] = {
};
MODULE_DEVICE_TABLE(spi, st95hf_id);
+static const struct of_device_id st95hf_spi_of_match[] = {
+ { .compatible = "st,st95hf" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, st95hf_spi_of_match);
+
static int st95hf_probe(struct spi_device *nfc_spi_dev)
{
int ret;
@@ -1260,6 +1266,7 @@ static struct spi_driver st95hf_driver = {
.driver = {
.name = "st95hf",
.owner = THIS_MODULE,
+ .of_match_table = of_match_ptr(st95hf_spi_of_match),
},
.id_table = st95hf_id,
.probe = st95hf_probe,
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 6dcb50cd9eb5..a1e218ea51a0 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -214,7 +214,7 @@ static LIST_HEAD(nvme_fc_lport_list);
static DEFINE_IDA(nvme_fc_local_port_cnt);
static DEFINE_IDA(nvme_fc_ctrl_cnt);
-
+static struct workqueue_struct *nvme_fc_wq;
/*
* These items are short-term. They will eventually be moved into
@@ -2066,7 +2066,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
*/
if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
active = atomic_xchg(&ctrl->err_work_active, 1);
- if (!active && !schedule_work(&ctrl->err_work)) {
+ if (!active && !queue_work(nvme_fc_wq, &ctrl->err_work)) {
atomic_set(&ctrl->err_work_active, 0);
WARN_ON(1);
}
@@ -3419,6 +3419,10 @@ static int __init nvme_fc_init_module(void)
{
int ret;
+ nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0);
+ if (!nvme_fc_wq)
+ return -ENOMEM;
+
/*
* NOTE:
* It is expected that in the future the kernel will combine
@@ -3436,7 +3440,7 @@ static int __init nvme_fc_init_module(void)
ret = class_register(&fc_class);
if (ret) {
pr_err("couldn't register class fc\n");
- return ret;
+ goto out_destroy_wq;
}
/*
@@ -3460,6 +3464,9 @@ out_destroy_device:
device_destroy(&fc_class, MKDEV(0, 0));
out_destroy_class:
class_unregister(&fc_class);
+out_destroy_wq:
+ destroy_workqueue(nvme_fc_wq);
+
return ret;
}
@@ -3476,6 +3483,7 @@ static void __exit nvme_fc_exit_module(void)
device_destroy(&fc_class, MKDEV(0, 0));
class_unregister(&fc_class);
+ destroy_workqueue(nvme_fc_wq);
}
module_init(nvme_fc_init_module);
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 16d360899463..5f8b5c95dfc2 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -183,11 +183,12 @@ void pciehp_get_power_status(struct controller *ctrl, u8 *status);
void pciehp_set_attention_status(struct controller *ctrl, u8 status);
void pciehp_get_latch_status(struct controller *ctrl, u8 *status);
-void pciehp_get_adapter_status(struct controller *ctrl, u8 *status);
int pciehp_query_power_fault(struct controller *ctrl);
void pciehp_green_led_on(struct controller *ctrl);
void pciehp_green_led_off(struct controller *ctrl);
void pciehp_green_led_blink(struct controller *ctrl);
+bool pciehp_card_present(struct controller *ctrl);
+bool pciehp_card_present_or_link_active(struct controller *ctrl);
int pciehp_check_link_status(struct controller *ctrl);
bool pciehp_check_link_active(struct controller *ctrl);
void pciehp_release_ctrl(struct controller *ctrl);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 7000e74f95b8..7ac9b66f4819 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -173,7 +173,7 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
struct pci_dev *pdev = ctrl->pcie->port;
pci_config_pm_runtime_get(pdev);
- pciehp_get_adapter_status(ctrl, value);
+ *value = pciehp_card_present_or_link_active(ctrl);
pci_config_pm_runtime_put(pdev);
return 0;
}
@@ -190,12 +190,12 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
*/
static void pciehp_check_presence(struct controller *ctrl)
{
- u8 occupied;
+ bool occupied;
down_read(&ctrl->reset_lock);
mutex_lock(&ctrl->lock);
- pciehp_get_adapter_status(ctrl, &occupied);
+ occupied = pciehp_card_present_or_link_active(ctrl);
if ((occupied && (ctrl->state == OFF_STATE ||
ctrl->state == BLINKINGON_STATE)) ||
(!occupied && (ctrl->state == ON_STATE ||
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index cbcb1211c34b..00c7e46af0bb 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -240,8 +240,7 @@ void pciehp_handle_disable_request(struct controller *ctrl)
void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
{
- bool link_active;
- u8 present;
+ bool present, link_active;
/*
* If the slot is on and presence or link has changed, turn it off.
@@ -268,7 +267,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
/* Turn the slot on if it's occupied or link is up */
mutex_lock(&ctrl->lock);
- pciehp_get_adapter_status(ctrl, &present);
+ present = pciehp_card_present(ctrl);
link_active = pciehp_check_link_active(ctrl);
if (!present && !link_active) {
mutex_unlock(&ctrl->lock);
@@ -301,11 +300,6 @@ static int __pciehp_enable_slot(struct controller *ctrl)
{
u8 getstatus = 0;
- pciehp_get_adapter_status(ctrl, &getstatus);
- if (!getstatus) {
- ctrl_info(ctrl, "Slot(%s): No adapter\n", slot_name(ctrl));
- return -ENODEV;
- }
if (MRL_SENS(ctrl)) {
pciehp_get_latch_status(ctrl, &getstatus);
if (getstatus) {
@@ -331,15 +325,15 @@ int pciehp_enable_slot(struct controller *ctrl)
{
int ret;
- pm_runtime_get_sync(&ctrl->pcie->port->dev);
+ mutex_lock(&ctrl->lock);
ret = __pciehp_enable_slot(ctrl);
- pm_runtime_put(&ctrl->pcie->port->dev);
+ mutex_unlock(&ctrl->lock);
if (ret && ATTN_BUTTN(ctrl))
pciehp_green_led_off(ctrl); /* may be blinking */
mutex_lock(&ctrl->lock);
- ctrl->state = ret ? OFF_STATE : ON_STATE;
+ ctrl->state = ON_STATE;
mutex_unlock(&ctrl->lock);
return ret;
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 53a0b21fd61f..4753226fbd57 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -404,13 +404,27 @@ void pciehp_get_latch_status(struct controller *ctrl, u8 *status)
*status = !!(slot_status & PCI_EXP_SLTSTA_MRLSS);
}
-void pciehp_get_adapter_status(struct controller *ctrl, u8 *status)
+bool pciehp_card_present(struct controller *ctrl)
{
struct pci_dev *pdev = ctrl_dev(ctrl);
u16 slot_status;
pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status);
- *status = !!(slot_status & PCI_EXP_SLTSTA_PDS);
+ return slot_status & PCI_EXP_SLTSTA_PDS;
+}
+
+/**
+ * pciehp_card_present_or_link_active() - whether given slot is occupied
+ * @ctrl: PCIe hotplug controller
+ *
+ * Unlike pciehp_card_present(), which determines presence solely from the
+ * Presence Detect State bit, this helper also returns true if the Link Active
+ * bit is set. This is a concession to broken hotplug ports which hardwire
+ * Presence Detect State to zero, such as Wilocity's [1ae9:0200].
+ */
+bool pciehp_card_present_or_link_active(struct controller *ctrl)
+{
+ return pciehp_card_present(ctrl) || pciehp_check_link_active(ctrl);
}
int pciehp_query_power_fault(struct controller *ctrl)
@@ -817,7 +831,7 @@ struct controller *pcie_init(struct pcie_device *dev)
{
struct controller *ctrl;
u32 slot_cap, link_cap;
- u8 occupied, poweron;
+ u8 poweron;
struct pci_dev *pdev = dev->port;
struct pci_bus *subordinate = pdev->subordinate;
@@ -881,9 +895,8 @@ struct controller *pcie_init(struct pcie_device *dev)
* requested yet, so avoid triggering a notification with this command.
*/
if (POWER_CTRL(ctrl)) {
- pciehp_get_adapter_status(ctrl, &occupied);
pciehp_get_power_status(ctrl, &poweron);
- if (!occupied && poweron) {
+ if (!pciehp_card_present_or_link_active(ctrl) && poweron) {
pcie_disable_notification(ctrl);
pciehp_power_off_slot(ctrl);
}
diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c
index 2397c482656e..d5f7da37aa9e 100644
--- a/drivers/power/supply/axp20x_usb_power.c
+++ b/drivers/power/supply/axp20x_usb_power.c
@@ -35,10 +35,10 @@
#define AXP20X_VBUS_VHOLD_MASK GENMASK(5, 3)
#define AXP20X_VBUS_VHOLD_OFFSET 3
#define AXP20X_VBUS_CLIMIT_MASK 3
-#define AXP20X_VBUC_CLIMIT_900mA 0
-#define AXP20X_VBUC_CLIMIT_500mA 1
-#define AXP20X_VBUC_CLIMIT_100mA 2
-#define AXP20X_VBUC_CLIMIT_NONE 3
+#define AXP20X_VBUS_CLIMIT_900mA 0
+#define AXP20X_VBUS_CLIMIT_500mA 1
+#define AXP20X_VBUS_CLIMIT_100mA 2
+#define AXP20X_VBUS_CLIMIT_NONE 3
#define AXP20X_ADC_EN1_VBUS_CURR BIT(2)
#define AXP20X_ADC_EN1_VBUS_VOLT BIT(3)
@@ -106,19 +106,19 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
return ret;
switch (v & AXP20X_VBUS_CLIMIT_MASK) {
- case AXP20X_VBUC_CLIMIT_100mA:
+ case AXP20X_VBUS_CLIMIT_100mA:
if (power->axp20x_id == AXP221_ID)
val->intval = -1; /* No 100mA limit */
else
val->intval = 100000;
break;
- case AXP20X_VBUC_CLIMIT_500mA:
+ case AXP20X_VBUS_CLIMIT_500mA:
val->intval = 500000;
break;
- case AXP20X_VBUC_CLIMIT_900mA:
+ case AXP20X_VBUS_CLIMIT_900mA:
val->intval = 900000;
break;
- case AXP20X_VBUC_CLIMIT_NONE:
+ case AXP20X_VBUS_CLIMIT_NONE:
val->intval = -1;
break;
}
diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index 4d016fbc3527..b8f7da57c78a 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -881,6 +881,10 @@ static int axp288_charger_probe(struct platform_device *pdev)
/* Register charger interrupts */
for (i = 0; i < CHRG_INTR_END; i++) {
pirq = platform_get_irq(info->pdev, i);
+ if (pirq < 0) {
+ dev_err(&pdev->dev, "Failed to get IRQ: %d\n", pirq);
+ return pirq;
+ }
info->irq[i] = regmap_irq_get_virq(info->regmap_irqc, pirq);
if (info->irq[i] < 0) {
dev_warn(&info->pdev->dev,
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index c7afdbded26b..6105822e0998 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -1216,8 +1216,10 @@ no_cleanup:
qdio_shutdown_thinint(irq_ptr);
/* restore interrupt handler */
- if ((void *)cdev->handler == (void *)qdio_int_handler)
+ if ((void *)cdev->handler == (void *)qdio_int_handler) {
cdev->handler = irq_ptr->orig_handler;
+ cdev->private->intparm = 0;
+ }
spin_unlock_irq(get_ccwdev_lock(cdev));
qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE);
diff --git a/drivers/scsi/smartpqi/Makefile b/drivers/scsi/smartpqi/Makefile
index e6b779930230..f9c57e3a8c62 100644
--- a/drivers/scsi/smartpqi/Makefile
+++ b/drivers/scsi/smartpqi/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
ccflags-y += -I.
obj-$(CONFIG_SCSI_SMARTPQI) += smartpqi.o
smartpqi-objs := smartpqi_init.o smartpqi_sis.o smartpqi_sas_transport.o
diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index e97bf2670315..e8e768849c70 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -1,18 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* driver for Microsemi PQI-based storage controllers
- * Copyright (c) 2016-2017 Microsemi Corporation
+ * Copyright (c) 2019 Microchip Technology Inc. and its subsidiaries
+ * Copyright (c) 2016-2018 Microsemi Corporation
* Copyright (c) 2016 PMC-Sierra, Inc.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more details.
- *
- * Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
+ * Questions/Comments/Bugfixes to storagedev@microchip.com
*
*/
@@ -21,6 +14,9 @@
#if !defined(_SMARTPQI_H)
#define _SMARTPQI_H
+#include <scsi/scsi_host.h>
+#include <linux/bsg-lib.h>
+
#pragma pack(1)
#define PQI_DEVICE_SIGNATURE "PQI DREG"
@@ -97,6 +93,12 @@ struct pqi_ctrl_registers {
struct pqi_device_registers pqi_registers; /* 4000h */
};
+#if ((HZ) < 1000)
+#define PQI_HZ 1000
+#else
+#define PQI_HZ (HZ)
+#endif
+
#define PQI_DEVICE_REGISTERS_OFFSET 0x4000
enum pqi_io_path {
@@ -347,6 +349,10 @@ struct pqi_event_config {
#define PQI_MAX_EVENT_DESCRIPTORS 255
+#define PQI_EVENT_OFA_MEMORY_ALLOCATION 0x0
+#define PQI_EVENT_OFA_QUIESCE 0x1
+#define PQI_EVENT_OFA_CANCELLED 0x2
+
struct pqi_event_response {
struct pqi_iu_header header;
u8 event_type;
@@ -354,7 +360,17 @@ struct pqi_event_response {
u8 request_acknowlege : 1;
__le16 event_id;
__le32 additional_event_id;
- u8 data[16];
+ union {
+ struct {
+ __le32 bytes_requested;
+ u8 reserved[12];
+ } ofa_memory_allocation;
+
+ struct {
+ __le16 reason; /* reason for cancellation */
+ u8 reserved[14];
+ } ofa_cancelled;
+ } data;
};
struct pqi_event_acknowledge_request {
@@ -389,6 +405,54 @@ struct pqi_task_management_response {
u8 response_code;
};
+struct pqi_vendor_general_request {
+ struct pqi_iu_header header;
+ __le16 request_id;
+ __le16 function_code;
+ union {
+ struct {
+ __le16 first_section;
+ __le16 last_section;
+ u8 reserved[48];
+ } config_table_update;
+
+ struct {
+ __le64 buffer_address;
+ __le32 buffer_length;
+ u8 reserved[40];
+ } ofa_memory_allocation;
+ } data;
+};
+
+struct pqi_vendor_general_response {
+ struct pqi_iu_header header;
+ __le16 request_id;
+ __le16 function_code;
+ __le16 status;
+ u8 reserved[2];
+};
+
+#define PQI_VENDOR_GENERAL_CONFIG_TABLE_UPDATE 0
+#define PQI_VENDOR_GENERAL_HOST_MEMORY_UPDATE 1
+
+#define PQI_OFA_VERSION 1
+#define PQI_OFA_SIGNATURE "OFA_QRM"
+#define PQI_OFA_MAX_SG_DESCRIPTORS 64
+
+#define PQI_OFA_MEMORY_DESCRIPTOR_LENGTH \
+ (offsetof(struct pqi_ofa_memory, sg_descriptor) + \
+ (PQI_OFA_MAX_SG_DESCRIPTORS * sizeof(struct pqi_sg_descriptor)))
+
+struct pqi_ofa_memory {
+ __le64 signature; /* "OFA_QRM" */
+ __le16 version; /* version of this struct(1 = 1st version) */
+ u8 reserved[62];
+ __le32 bytes_allocated; /* total allocated memory in bytes */
+ __le16 num_memory_descriptors;
+ u8 reserved1[2];
+ struct pqi_sg_descriptor sg_descriptor[1];
+};
+
struct pqi_aio_error_info {
u8 status;
u8 service_response;
@@ -419,6 +483,7 @@ struct pqi_raid_error_info {
#define PQI_REQUEST_IU_GENERAL_ADMIN 0x60
#define PQI_REQUEST_IU_REPORT_VENDOR_EVENT_CONFIG 0x72
#define PQI_REQUEST_IU_SET_VENDOR_EVENT_CONFIG 0x73
+#define PQI_REQUEST_IU_VENDOR_GENERAL 0x75
#define PQI_REQUEST_IU_ACKNOWLEDGE_VENDOR_EVENT 0xf6
#define PQI_RESPONSE_IU_GENERAL_MANAGEMENT 0x81
@@ -430,6 +495,7 @@ struct pqi_raid_error_info {
#define PQI_RESPONSE_IU_AIO_PATH_IO_ERROR 0xf3
#define PQI_RESPONSE_IU_AIO_PATH_DISABLED 0xf4
#define PQI_RESPONSE_IU_VENDOR_EVENT 0xf5
+#define PQI_RESPONSE_IU_VENDOR_GENERAL 0xf7
#define PQI_GENERAL_ADMIN_FUNCTION_REPORT_DEVICE_CAPABILITY 0x0
#define PQI_GENERAL_ADMIN_FUNCTION_CREATE_IQ 0x10
@@ -492,6 +558,7 @@ struct pqi_raid_error_info {
#define PQI_EVENT_TYPE_HARDWARE 0x2
#define PQI_EVENT_TYPE_PHYSICAL_DEVICE 0x4
#define PQI_EVENT_TYPE_LOGICAL_DEVICE 0x5
+#define PQI_EVENT_TYPE_OFA 0xfb
#define PQI_EVENT_TYPE_AIO_STATE_CHANGE 0xfd
#define PQI_EVENT_TYPE_AIO_CONFIG_CHANGE 0xfe
@@ -556,6 +623,7 @@ typedef u32 pqi_index_t;
#define SOP_TASK_ATTRIBUTE_ACA 4
#define SOP_TMF_COMPLETE 0x0
+#define SOP_TMF_REJECTED 0x4
#define SOP_TMF_FUNCTION_SUCCEEDED 0x8
/* additional CDB bytes usage field codes */
@@ -644,11 +712,13 @@ struct pqi_encryption_info {
#define PQI_CONFIG_TABLE_MAX_LENGTH ((u16)~0)
/* configuration table section IDs */
+#define PQI_CONFIG_TABLE_ALL_SECTIONS (-1)
#define PQI_CONFIG_TABLE_SECTION_GENERAL_INFO 0
#define PQI_CONFIG_TABLE_SECTION_FIRMWARE_FEATURES 1
#define PQI_CONFIG_TABLE_SECTION_FIRMWARE_ERRATA 2
#define PQI_CONFIG_TABLE_SECTION_DEBUG 3
#define PQI_CONFIG_TABLE_SECTION_HEARTBEAT 4
+#define PQI_CONFIG_TABLE_SECTION_SOFT_RESET 5
struct pqi_config_table {
u8 signature[8]; /* "CFGTABLE" */
@@ -680,6 +750,18 @@ struct pqi_config_table_general_info {
/* command */
};
+struct pqi_config_table_firmware_features {
+ struct pqi_config_table_section_header header;
+ __le16 num_elements;
+ u8 features_supported[];
+/* u8 features_requested_by_host[]; */
+/* u8 features_enabled[]; */
+};
+
+#define PQI_FIRMWARE_FEATURE_OFA 0
+#define PQI_FIRMWARE_FEATURE_SMP 1
+#define PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE 11
+
struct pqi_config_table_debug {
struct pqi_config_table_section_header header;
__le32 scratchpad;
@@ -690,6 +772,22 @@ struct pqi_config_table_heartbeat {
__le32 heartbeat_counter;
};
+struct pqi_config_table_soft_reset {
+ struct pqi_config_table_section_header header;
+ u8 soft_reset_status;
+};
+
+#define PQI_SOFT_RESET_INITIATE 0x1
+#define PQI_SOFT_RESET_ABORT 0x2
+
+enum pqi_soft_reset_status {
+ RESET_INITIATE_FIRMWARE,
+ RESET_INITIATE_DRIVER,
+ RESET_ABORT,
+ RESET_NORESPONSE,
+ RESET_TIMEDOUT
+};
+
union pqi_reset_register {
struct {
u32 reset_type : 3;
@@ -808,8 +906,10 @@ struct pqi_scsi_dev {
u8 scsi3addr[8];
__be64 wwid;
u8 volume_id[16];
+ u8 unique_id[16];
u8 is_physical_device : 1;
u8 is_external_raid_device : 1;
+ u8 is_expander_smp_device : 1;
u8 target_lun_valid : 1;
u8 device_gone : 1;
u8 new_device : 1;
@@ -817,6 +917,7 @@ struct pqi_scsi_dev {
u8 volume_offline : 1;
bool aio_enabled; /* only valid for physical disks */
bool in_reset;
+ bool in_remove;
bool device_offline;
u8 vendor[8]; /* bytes 8-15 of inquiry data */
u8 model[16]; /* bytes 16-31 of inquiry data */
@@ -854,6 +955,8 @@ struct pqi_scsi_dev {
#define CISS_VPD_LV_DEVICE_GEOMETRY 0xc1 /* vendor-specific page */
#define CISS_VPD_LV_BYPASS_STATUS 0xc2 /* vendor-specific page */
#define CISS_VPD_LV_STATUS 0xc3 /* vendor-specific page */
+#define SCSI_VPD_HEADER_SZ 4
+#define SCSI_VPD_DEVICE_ID_IDX 8 /* Index of page id in page */
#define VPD_PAGE (1 << 8)
@@ -916,6 +1019,7 @@ struct pqi_sas_node {
struct pqi_sas_port {
struct list_head port_list_entry;
u64 sas_address;
+ struct pqi_scsi_dev *device;
struct sas_port *port;
int next_phy_index;
struct list_head phy_list_head;
@@ -947,13 +1051,15 @@ struct pqi_io_request {
struct list_head request_list_entry;
};
-#define PQI_NUM_SUPPORTED_EVENTS 6
+#define PQI_NUM_SUPPORTED_EVENTS 7
struct pqi_event {
bool pending;
u8 event_type;
__le16 event_id;
__le32 additional_event_id;
+ __le32 ofa_bytes_requested;
+ __le16 ofa_cancel_reason;
};
#define PQI_RESERVED_IO_SLOTS_LUN_RESET 1
@@ -1014,12 +1120,16 @@ struct pqi_ctrl_info {
struct mutex scan_mutex;
struct mutex lun_reset_mutex;
+ struct mutex ofa_mutex; /* serialize ofa */
bool controller_online;
bool block_requests;
+ bool in_shutdown;
+ bool in_ofa;
u8 inbound_spanning_supported : 1;
u8 outbound_spanning_supported : 1;
u8 pqi_mode_enabled : 1;
u8 pqi_reset_quiesce_supported : 1;
+ u8 soft_reset_handshake_supported : 1;
struct list_head scsi_device_list;
spinlock_t scsi_device_list_lock;
@@ -1040,6 +1150,7 @@ struct pqi_ctrl_info {
int previous_num_interrupts;
u32 previous_heartbeat_count;
__le32 __iomem *heartbeat_counter;
+ u8 __iomem *soft_reset_status;
struct timer_list heartbeat_timer;
struct work_struct ctrl_offline_work;
@@ -1051,6 +1162,10 @@ struct pqi_ctrl_info {
struct list_head raid_bypass_retry_list;
spinlock_t raid_bypass_retry_list_lock;
struct work_struct raid_bypass_retry_work;
+
+ struct pqi_ofa_memory *pqi_ofa_mem_virt_addr;
+ dma_addr_t pqi_ofa_mem_dma_handle;
+ void **pqi_ofa_chunk_virt_addr;
};
enum pqi_ctrl_mode {
@@ -1080,8 +1195,13 @@ enum pqi_ctrl_mode {
#define BMIC_WRITE 0x27
#define BMIC_SENSE_CONTROLLER_PARAMETERS 0x64
#define BMIC_SENSE_SUBSYSTEM_INFORMATION 0x66
+#define BMIC_CSMI_PASSTHRU 0x68
#define BMIC_WRITE_HOST_WELLNESS 0xa5
#define BMIC_FLUSH_CACHE 0xc2
+#define BMIC_SET_DIAG_OPTIONS 0xf4
+#define BMIC_SENSE_DIAG_OPTIONS 0xf5
+
+#define CSMI_CC_SAS_SMP_PASSTHRU 0X17
#define SA_FLUSH_CACHE 0x1
@@ -1109,6 +1229,10 @@ struct bmic_identify_controller {
u8 reserved3[32];
};
+#define SA_EXPANDER_SMP_DEVICE 0x05
+/*SCSI Invalid Device Type for SAS devices*/
+#define PQI_SAS_SCSI_INVALID_DEVTYPE 0xff
+
struct bmic_identify_physical_device {
u8 scsi_bus; /* SCSI Bus number on controller */
u8 scsi_id; /* SCSI ID on this bus */
@@ -1189,6 +1313,50 @@ struct bmic_identify_physical_device {
u8 padding_to_multiple_of_512[9];
};
+struct bmic_smp_request {
+ u8 frame_type;
+ u8 function;
+ u8 allocated_response_length;
+ u8 request_length;
+ u8 additional_request_bytes[1016];
+};
+
+struct bmic_smp_response {
+ u8 frame_type;
+ u8 function;
+ u8 function_result;
+ u8 response_length;
+ u8 additional_response_bytes[1016];
+};
+
+struct bmic_csmi_ioctl_header {
+ __le32 header_length;
+ u8 signature[8];
+ __le32 timeout;
+ __le32 control_code;
+ __le32 return_code;
+ __le32 length;
+};
+
+struct bmic_csmi_smp_passthru {
+ u8 phy_identifier;
+ u8 port_identifier;
+ u8 connection_rate;
+ u8 reserved;
+ __be64 destination_sas_address;
+ __le32 request_length;
+ struct bmic_smp_request request;
+ u8 connection_status;
+ u8 reserved1[3];
+ __le32 response_length;
+ struct bmic_smp_response response;
+};
+
+struct bmic_csmi_smp_passthru_buffer {
+ struct bmic_csmi_ioctl_header ioctl_header;
+ struct bmic_csmi_smp_passthru parameters;
+};
+
struct bmic_flush_cache {
u8 disable_flag;
u8 system_power_action;
@@ -1206,8 +1374,42 @@ enum bmic_flush_cache_shutdown_event {
RESTART = 4
};
+struct bmic_diag_options {
+ __le32 options;
+};
+
#pragma pack()
+static inline struct pqi_ctrl_info *shost_to_hba(struct Scsi_Host *shost)
+{
+ void *hostdata = shost_priv(shost);
+
+ return *((struct pqi_ctrl_info **)hostdata);
+}
+
+static inline bool pqi_ctrl_offline(struct pqi_ctrl_info *ctrl_info)
+{
+ return !ctrl_info->controller_online;
+}
+
+static inline void pqi_ctrl_busy(struct pqi_ctrl_info *ctrl_info)
+{
+ atomic_inc(&ctrl_info->num_busy_threads);
+}
+
+static inline void pqi_ctrl_unbusy(struct pqi_ctrl_info *ctrl_info)
+{
+ atomic_dec(&ctrl_info->num_busy_threads);
+}
+
+static inline bool pqi_ctrl_blocked(struct pqi_ctrl_info *ctrl_info)
+{
+ return ctrl_info->block_requests;
+}
+
+void pqi_sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
+ struct sas_rphy *rphy);
+
int pqi_add_sas_host(struct Scsi_Host *shost, struct pqi_ctrl_info *ctrl_info);
void pqi_delete_sas_host(struct pqi_ctrl_info *ctrl_info);
int pqi_add_sas_device(struct pqi_sas_node *pqi_sas_node,
@@ -1216,6 +1418,9 @@ void pqi_remove_sas_device(struct pqi_scsi_dev *device);
struct pqi_scsi_dev *pqi_find_device_by_sas_rphy(
struct pqi_ctrl_info *ctrl_info, struct sas_rphy *rphy);
void pqi_prep_for_scsi_done(struct scsi_cmnd *scmd);
+int pqi_csmi_smp_passthru(struct pqi_ctrl_info *ctrl_info,
+ struct bmic_csmi_smp_passthru_buffer *buffer, size_t buffer_length,
+ struct pqi_raid_error_info *error_info);
extern struct sas_function_template pqi_sas_transport_functions;
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index a84ac40f35ad..655b066501e1 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -1,18 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* driver for Microsemi PQI-based storage controllers
- * Copyright (c) 2016-2017 Microsemi Corporation
+ * Copyright (c) 2019 Microchip Technology Inc. and its subsidiaries
+ * Copyright (c) 2016-2018 Microsemi Corporation
* Copyright (c) 2016 PMC-Sierra, Inc.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more details.
- *
- * Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
+ * Questions/Comments/Bugfixes to storagedev@microchip.com
*
*/
@@ -40,11 +33,11 @@
#define BUILD_TIMESTAMP
#endif
-#define DRIVER_VERSION "1.1.4-130"
+#define DRIVER_VERSION "1.2.6-015"
#define DRIVER_MAJOR 1
-#define DRIVER_MINOR 1
-#define DRIVER_RELEASE 4
-#define DRIVER_REVISION 130
+#define DRIVER_MINOR 2
+#define DRIVER_RELEASE 6
+#define DRIVER_REVISION 15
#define DRIVER_NAME "Microsemi PQI Driver (v" \
DRIVER_VERSION BUILD_TIMESTAMP ")"
@@ -74,6 +67,15 @@ static int pqi_aio_submit_io(struct pqi_ctrl_info *ctrl_info,
struct scsi_cmnd *scmd, u32 aio_handle, u8 *cdb,
unsigned int cdb_length, struct pqi_queue_group *queue_group,
struct pqi_encryption_info *encryption_info, bool raid_bypass);
+static void pqi_ofa_ctrl_quiesce(struct pqi_ctrl_info *ctrl_info);
+static void pqi_ofa_ctrl_unquiesce(struct pqi_ctrl_info *ctrl_info);
+static int pqi_ofa_ctrl_restart(struct pqi_ctrl_info *ctrl_info);
+static void pqi_ofa_setup_host_buffer(struct pqi_ctrl_info *ctrl_info,
+ u32 bytes_requested);
+static void pqi_ofa_free_host_buffer(struct pqi_ctrl_info *ctrl_info);
+static int pqi_ofa_host_memory_update(struct pqi_ctrl_info *ctrl_info);
+static int pqi_device_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_scsi_dev *device, unsigned long timeout_secs);
/* for flags argument to pqi_submit_raid_request_synchronous() */
#define PQI_SYNC_FLAGS_INTERRUPTABLE 0x1
@@ -113,6 +115,7 @@ static unsigned int pqi_supported_event_types[] = {
PQI_EVENT_TYPE_HARDWARE,
PQI_EVENT_TYPE_PHYSICAL_DEVICE,
PQI_EVENT_TYPE_LOGICAL_DEVICE,
+ PQI_EVENT_TYPE_OFA,
PQI_EVENT_TYPE_AIO_STATE_CHANGE,
PQI_EVENT_TYPE_AIO_CONFIG_CHANGE,
};
@@ -176,16 +179,14 @@ static inline void pqi_scsi_done(struct scsi_cmnd *scmd)
scmd->scsi_done(scmd);
}
-static inline bool pqi_scsi3addr_equal(u8 *scsi3addr1, u8 *scsi3addr2)
+static inline void pqi_disable_write_same(struct scsi_device *sdev)
{
- return memcmp(scsi3addr1, scsi3addr2, 8) == 0;
+ sdev->no_write_same = 1;
}
-static inline struct pqi_ctrl_info *shost_to_hba(struct Scsi_Host *shost)
+static inline bool pqi_scsi3addr_equal(u8 *scsi3addr1, u8 *scsi3addr2)
{
- void *hostdata = shost_priv(shost);
-
- return *((struct pqi_ctrl_info **)hostdata);
+ return memcmp(scsi3addr1, scsi3addr2, 8) == 0;
}
static inline bool pqi_is_logical_device(struct pqi_scsi_dev *device)
@@ -198,11 +199,6 @@ static inline bool pqi_is_external_raid_addr(u8 *scsi3addr)
return scsi3addr[2] != 0;
}
-static inline bool pqi_ctrl_offline(struct pqi_ctrl_info *ctrl_info)
-{
- return !ctrl_info->controller_online;
-}
-
static inline void pqi_check_ctrl_health(struct pqi_ctrl_info *ctrl_info)
{
if (ctrl_info->controller_online)
@@ -241,11 +237,6 @@ static inline void pqi_ctrl_unblock_requests(struct pqi_ctrl_info *ctrl_info)
scsi_unblock_requests(ctrl_info->scsi_host);
}
-static inline bool pqi_ctrl_blocked(struct pqi_ctrl_info *ctrl_info)
-{
- return ctrl_info->block_requests;
-}
-
static unsigned long pqi_wait_if_ctrl_blocked(struct pqi_ctrl_info *ctrl_info,
unsigned long timeout_msecs)
{
@@ -275,16 +266,6 @@ static unsigned long pqi_wait_if_ctrl_blocked(struct pqi_ctrl_info *ctrl_info,
return remaining_msecs;
}
-static inline void pqi_ctrl_busy(struct pqi_ctrl_info *ctrl_info)
-{
- atomic_inc(&ctrl_info->num_busy_threads);
-}
-
-static inline void pqi_ctrl_unbusy(struct pqi_ctrl_info *ctrl_info)
-{
- atomic_dec(&ctrl_info->num_busy_threads);
-}
-
static inline void pqi_ctrl_wait_until_quiesced(struct pqi_ctrl_info *ctrl_info)
{
while (atomic_read(&ctrl_info->num_busy_threads) >
@@ -312,11 +293,39 @@ static inline bool pqi_device_in_reset(struct pqi_scsi_dev *device)
return device->in_reset;
}
+static inline void pqi_ctrl_ofa_start(struct pqi_ctrl_info *ctrl_info)
+{
+ ctrl_info->in_ofa = true;
+}
+
+static inline void pqi_ctrl_ofa_done(struct pqi_ctrl_info *ctrl_info)
+{
+ ctrl_info->in_ofa = false;
+}
+
+static inline bool pqi_ctrl_in_ofa(struct pqi_ctrl_info *ctrl_info)
+{
+ return ctrl_info->in_ofa;
+}
+
+static inline void pqi_device_remove_start(struct pqi_scsi_dev *device)
+{
+ device->in_remove = true;
+}
+
+static inline bool pqi_device_in_remove(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_scsi_dev *device)
+{
+ return device->in_remove && !ctrl_info->in_shutdown;
+}
+
static inline void pqi_schedule_rescan_worker_with_delay(
struct pqi_ctrl_info *ctrl_info, unsigned long delay)
{
if (pqi_ctrl_offline(ctrl_info))
return;
+ if (pqi_ctrl_in_ofa(ctrl_info))
+ return;
schedule_delayed_work(&ctrl_info->rescan_work, delay);
}
@@ -326,7 +335,7 @@ static inline void pqi_schedule_rescan_worker(struct pqi_ctrl_info *ctrl_info)
pqi_schedule_rescan_worker_with_delay(ctrl_info, 0);
}
-#define PQI_RESCAN_WORK_DELAY (10 * HZ)
+#define PQI_RESCAN_WORK_DELAY (10 * PQI_HZ)
static inline void pqi_schedule_rescan_worker_delayed(
struct pqi_ctrl_info *ctrl_info)
@@ -347,18 +356,39 @@ static inline u32 pqi_read_heartbeat_counter(struct pqi_ctrl_info *ctrl_info)
return readl(ctrl_info->heartbeat_counter);
}
+static inline u8 pqi_read_soft_reset_status(struct pqi_ctrl_info *ctrl_info)
+{
+ if (!ctrl_info->soft_reset_status)
+ return 0;
+
+ return readb(ctrl_info->soft_reset_status);
+}
+
+static inline void pqi_clear_soft_reset_status(struct pqi_ctrl_info *ctrl_info,
+ u8 clear)
+{
+ u8 status;
+
+ if (!ctrl_info->soft_reset_status)
+ return;
+
+ status = pqi_read_soft_reset_status(ctrl_info);
+ status &= ~clear;
+ writeb(status, ctrl_info->soft_reset_status);
+}
+
static int pqi_map_single(struct pci_dev *pci_dev,
struct pqi_sg_descriptor *sg_descriptor, void *buffer,
- size_t buffer_length, int data_direction)
+ size_t buffer_length, enum dma_data_direction data_direction)
{
dma_addr_t bus_address;
- if (!buffer || buffer_length == 0 || data_direction == PCI_DMA_NONE)
+ if (!buffer || buffer_length == 0 || data_direction == DMA_NONE)
return 0;
- bus_address = pci_map_single(pci_dev, buffer, buffer_length,
+ bus_address = dma_map_single(&pci_dev->dev, buffer, buffer_length,
data_direction);
- if (pci_dma_mapping_error(pci_dev, bus_address))
+ if (dma_mapping_error(&pci_dev->dev, bus_address))
return -ENOMEM;
put_unaligned_le64((u64)bus_address, &sg_descriptor->address);
@@ -370,15 +400,15 @@ static int pqi_map_single(struct pci_dev *pci_dev,
static void pqi_pci_unmap(struct pci_dev *pci_dev,
struct pqi_sg_descriptor *descriptors, int num_descriptors,
- int data_direction)
+ enum dma_data_direction data_direction)
{
int i;
- if (data_direction == PCI_DMA_NONE)
+ if (data_direction == DMA_NONE)
return;
for (i = 0; i < num_descriptors; i++)
- pci_unmap_single(pci_dev,
+ dma_unmap_single(&pci_dev->dev,
(dma_addr_t)get_unaligned_le64(&descriptors[i].address),
get_unaligned_le32(&descriptors[i].length),
data_direction);
@@ -387,10 +417,10 @@ static void pqi_pci_unmap(struct pci_dev *pci_dev,
static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info,
struct pqi_raid_path_request *request, u8 cmd,
u8 *scsi3addr, void *buffer, size_t buffer_length,
- u16 vpd_page, int *pci_direction)
+ u16 vpd_page, enum dma_data_direction *dir)
{
u8 *cdb;
- int pci_dir;
+ size_t cdb_length = buffer_length;
memset(request, 0, sizeof(*request));
@@ -413,7 +443,7 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info,
cdb[1] = 0x1;
cdb[2] = (u8)vpd_page;
}
- cdb[4] = (u8)buffer_length;
+ cdb[4] = (u8)cdb_length;
break;
case CISS_REPORT_LOG:
case CISS_REPORT_PHYS:
@@ -423,32 +453,45 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info,
cdb[1] = CISS_REPORT_PHYS_EXTENDED;
else
cdb[1] = CISS_REPORT_LOG_EXTENDED;
- put_unaligned_be32(buffer_length, &cdb[6]);
+ put_unaligned_be32(cdb_length, &cdb[6]);
break;
case CISS_GET_RAID_MAP:
request->data_direction = SOP_READ_FLAG;
cdb[0] = CISS_READ;
cdb[1] = CISS_GET_RAID_MAP;
- put_unaligned_be32(buffer_length, &cdb[6]);
+ put_unaligned_be32(cdb_length, &cdb[6]);
break;
case SA_FLUSH_CACHE:
request->data_direction = SOP_WRITE_FLAG;
cdb[0] = BMIC_WRITE;
cdb[6] = BMIC_FLUSH_CACHE;
- put_unaligned_be16(buffer_length, &cdb[7]);
+ put_unaligned_be16(cdb_length, &cdb[7]);
break;
+ case BMIC_SENSE_DIAG_OPTIONS:
+ cdb_length = 0;
+ /* fall through */
case BMIC_IDENTIFY_CONTROLLER:
case BMIC_IDENTIFY_PHYSICAL_DEVICE:
request->data_direction = SOP_READ_FLAG;
cdb[0] = BMIC_READ;
cdb[6] = cmd;
- put_unaligned_be16(buffer_length, &cdb[7]);
+ put_unaligned_be16(cdb_length, &cdb[7]);
break;
+ case BMIC_SET_DIAG_OPTIONS:
+ cdb_length = 0;
+ /* fall through */
case BMIC_WRITE_HOST_WELLNESS:
request->data_direction = SOP_WRITE_FLAG;
cdb[0] = BMIC_WRITE;
cdb[6] = cmd;
- put_unaligned_be16(buffer_length, &cdb[7]);
+ put_unaligned_be16(cdb_length, &cdb[7]);
+ break;
+ case BMIC_CSMI_PASSTHRU:
+ request->data_direction = SOP_BIDIRECTIONAL;
+ cdb[0] = BMIC_WRITE;
+ cdb[5] = CSMI_CC_SAS_SMP_PASSTHRU;
+ cdb[6] = cmd;
+ put_unaligned_be16(cdb_length, &cdb[7]);
break;
default:
dev_err(&ctrl_info->pci_dev->dev, "unknown command 0x%c\n",
@@ -458,23 +501,21 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info,
switch (request->data_direction) {
case SOP_READ_FLAG:
- pci_dir = PCI_DMA_FROMDEVICE;
+ *dir = DMA_FROM_DEVICE;
break;
case SOP_WRITE_FLAG:
- pci_dir = PCI_DMA_TODEVICE;
+ *dir = DMA_TO_DEVICE;
break;
case SOP_NO_DIRECTION_FLAG:
- pci_dir = PCI_DMA_NONE;
+ *dir = DMA_NONE;
break;
default:
- pci_dir = PCI_DMA_BIDIRECTIONAL;
+ *dir = DMA_BIDIRECTIONAL;
break;
}
- *pci_direction = pci_dir;
-
return pqi_map_single(ctrl_info->pci_dev, &request->sg_descriptors[0],
- buffer, buffer_length, pci_dir);
+ buffer, buffer_length, *dir);
}
static inline void pqi_reinit_io_request(struct pqi_io_request *io_request)
@@ -512,46 +553,129 @@ static void pqi_free_io_request(struct pqi_io_request *io_request)
atomic_dec(&io_request->refcount);
}
-static int pqi_identify_controller(struct pqi_ctrl_info *ctrl_info,
- struct bmic_identify_controller *buffer)
+static int pqi_send_scsi_raid_request(struct pqi_ctrl_info *ctrl_info, u8 cmd,
+ u8 *scsi3addr, void *buffer, size_t buffer_length, u16 vpd_page,
+ struct pqi_raid_error_info *error_info,
+ unsigned long timeout_msecs)
{
int rc;
- int pci_direction;
+ enum dma_data_direction dir;
struct pqi_raid_path_request request;
rc = pqi_build_raid_path_request(ctrl_info, &request,
- BMIC_IDENTIFY_CONTROLLER, RAID_CTLR_LUNID, buffer,
- sizeof(*buffer), 0, &pci_direction);
+ cmd, scsi3addr, buffer,
+ buffer_length, vpd_page, &dir);
if (rc)
return rc;
- rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, 0,
- NULL, NO_TIMEOUT);
-
- pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- pci_direction);
+ rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
+ 0, error_info, timeout_msecs);
+ pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1, dir);
return rc;
}
-static int pqi_scsi_inquiry(struct pqi_ctrl_info *ctrl_info,
+/* Helper functions for pqi_send_scsi_raid_request */
+
+static inline int pqi_send_ctrl_raid_request(struct pqi_ctrl_info *ctrl_info,
+ u8 cmd, void *buffer, size_t buffer_length)
+{
+ return pqi_send_scsi_raid_request(ctrl_info, cmd, RAID_CTLR_LUNID,
+ buffer, buffer_length, 0, NULL, NO_TIMEOUT);
+}
+
+static inline int pqi_send_ctrl_raid_with_error(struct pqi_ctrl_info *ctrl_info,
+ u8 cmd, void *buffer, size_t buffer_length,
+ struct pqi_raid_error_info *error_info)
+{
+ return pqi_send_scsi_raid_request(ctrl_info, cmd, RAID_CTLR_LUNID,
+ buffer, buffer_length, 0, error_info, NO_TIMEOUT);
+}
+
+
+static inline int pqi_identify_controller(struct pqi_ctrl_info *ctrl_info,
+ struct bmic_identify_controller *buffer)
+{
+ return pqi_send_ctrl_raid_request(ctrl_info, BMIC_IDENTIFY_CONTROLLER,
+ buffer, sizeof(*buffer));
+}
+
+static inline int pqi_scsi_inquiry(struct pqi_ctrl_info *ctrl_info,
u8 *scsi3addr, u16 vpd_page, void *buffer, size_t buffer_length)
{
+ return pqi_send_scsi_raid_request(ctrl_info, INQUIRY, scsi3addr,
+ buffer, buffer_length, vpd_page, NULL, NO_TIMEOUT);
+}
+
+static bool pqi_vpd_page_supported(struct pqi_ctrl_info *ctrl_info,
+ u8 *scsi3addr, u16 vpd_page)
+{
int rc;
- int pci_direction;
- struct pqi_raid_path_request request;
+ int i;
+ int pages;
+ unsigned char *buf, bufsize;
- rc = pqi_build_raid_path_request(ctrl_info, &request,
- INQUIRY, scsi3addr, buffer, buffer_length, vpd_page,
- &pci_direction);
- if (rc)
- return rc;
+ buf = kzalloc(256, GFP_KERNEL);
+ if (!buf)
+ return false;
- rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, 0,
- NULL, NO_TIMEOUT);
+ /* Get the size of the page list first */
+ rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
+ VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES,
+ buf, SCSI_VPD_HEADER_SZ);
+ if (rc != 0)
+ goto exit_unsupported;
+
+ pages = buf[3];
+ if ((pages + SCSI_VPD_HEADER_SZ) <= 255)
+ bufsize = pages + SCSI_VPD_HEADER_SZ;
+ else
+ bufsize = 255;
+
+ /* Get the whole VPD page list */
+ rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
+ VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES,
+ buf, bufsize);
+ if (rc != 0)
+ goto exit_unsupported;
+
+ pages = buf[3];
+ for (i = 1; i <= pages; i++)
+ if (buf[3 + i] == vpd_page)
+ goto exit_supported;
+
+exit_unsupported:
+ kfree(buf);
+ return false;
+
+exit_supported:
+ kfree(buf);
+ return true;
+}
+
+static int pqi_get_device_id(struct pqi_ctrl_info *ctrl_info,
+ u8 *scsi3addr, u8 *device_id, int buflen)
+{
+ int rc;
+ unsigned char *buf;
+
+ if (!pqi_vpd_page_supported(ctrl_info, scsi3addr, SCSI_VPD_DEVICE_ID))
+ return 1; /* function not supported */
+
+ buf = kzalloc(64, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
+ VPD_PAGE | SCSI_VPD_DEVICE_ID,
+ buf, 64);
+ if (rc == 0) {
+ if (buflen > 16)
+ buflen = 16;
+ memcpy(device_id, &buf[SCSI_VPD_DEVICE_ID_IDX], buflen);
+ }
- pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- pci_direction);
+ kfree(buf);
return rc;
}
@@ -562,13 +686,13 @@ static int pqi_identify_physical_device(struct pqi_ctrl_info *ctrl_info,
size_t buffer_length)
{
int rc;
- int pci_direction;
+ enum dma_data_direction dir;
u16 bmic_device_index;
struct pqi_raid_path_request request;
rc = pqi_build_raid_path_request(ctrl_info, &request,
BMIC_IDENTIFY_PHYSICAL_DEVICE, RAID_CTLR_LUNID, buffer,
- buffer_length, 0, &pci_direction);
+ buffer_length, 0, &dir);
if (rc)
return rc;
@@ -579,9 +703,7 @@ static int pqi_identify_physical_device(struct pqi_ctrl_info *ctrl_info,
rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
0, NULL, NO_TIMEOUT);
- pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- pci_direction);
-
+ pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1, dir);
return rc;
}
@@ -589,8 +711,6 @@ static int pqi_flush_cache(struct pqi_ctrl_info *ctrl_info,
enum bmic_flush_cache_shutdown_event shutdown_event)
{
int rc;
- struct pqi_raid_path_request request;
- int pci_direction;
struct bmic_flush_cache *flush_cache;
/*
@@ -606,46 +726,55 @@ static int pqi_flush_cache(struct pqi_ctrl_info *ctrl_info,
flush_cache->shutdown_event = shutdown_event;
- rc = pqi_build_raid_path_request(ctrl_info, &request,
- SA_FLUSH_CACHE, RAID_CTLR_LUNID, flush_cache,
- sizeof(*flush_cache), 0, &pci_direction);
- if (rc)
- goto out;
-
- rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
- 0, NULL, NO_TIMEOUT);
-
- pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- pci_direction);
+ rc = pqi_send_ctrl_raid_request(ctrl_info, SA_FLUSH_CACHE, flush_cache,
+ sizeof(*flush_cache));
-out:
kfree(flush_cache);
return rc;
}
-static int pqi_write_host_wellness(struct pqi_ctrl_info *ctrl_info,
- void *buffer, size_t buffer_length)
+int pqi_csmi_smp_passthru(struct pqi_ctrl_info *ctrl_info,
+ struct bmic_csmi_smp_passthru_buffer *buffer, size_t buffer_length,
+ struct pqi_raid_error_info *error_info)
+{
+ return pqi_send_ctrl_raid_with_error(ctrl_info, BMIC_CSMI_PASSTHRU,
+ buffer, buffer_length, error_info);
+}
+
+#define PQI_FETCH_PTRAID_DATA (1UL<<31)
+
+static int pqi_set_diag_rescan(struct pqi_ctrl_info *ctrl_info)
{
int rc;
- struct pqi_raid_path_request request;
- int pci_direction;
+ struct bmic_diag_options *diag;
- rc = pqi_build_raid_path_request(ctrl_info, &request,
- BMIC_WRITE_HOST_WELLNESS, RAID_CTLR_LUNID, buffer,
- buffer_length, 0, &pci_direction);
+ diag = kzalloc(sizeof(*diag), GFP_KERNEL);
+ if (!diag)
+ return -ENOMEM;
+
+ rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SENSE_DIAG_OPTIONS,
+ diag, sizeof(*diag));
if (rc)
- return rc;
+ goto out;
- rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
- 0, NULL, NO_TIMEOUT);
+ diag->options |= cpu_to_le32(PQI_FETCH_PTRAID_DATA);
- pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- pci_direction);
+ rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SET_DIAG_OPTIONS,
+ diag, sizeof(*diag));
+out:
+ kfree(diag);
return rc;
}
+static inline int pqi_write_host_wellness(struct pqi_ctrl_info *ctrl_info,
+ void *buffer, size_t buffer_length)
+{
+ return pqi_send_ctrl_raid_request(ctrl_info, BMIC_WRITE_HOST_WELLNESS,
+ buffer, buffer_length);
+}
+
#pragma pack(1)
struct bmic_host_wellness_driver_version {
@@ -653,6 +782,7 @@ struct bmic_host_wellness_driver_version {
u8 driver_version_tag[2];
__le16 driver_version_length;
char driver_version[32];
+ u8 dont_write_tag[2];
u8 end_tag[2];
};
@@ -682,6 +812,8 @@ static int pqi_write_driver_version_to_host_wellness(
strncpy(buffer->driver_version, "Linux " DRIVER_VERSION,
sizeof(buffer->driver_version) - 1);
buffer->driver_version[sizeof(buffer->driver_version) - 1] = '\0';
+ buffer->dont_write_tag[0] = 'D';
+ buffer->dont_write_tag[1] = 'W';
buffer->end_tag[0] = 'Z';
buffer->end_tag[1] = 'Z';
@@ -755,7 +887,7 @@ static int pqi_write_current_time_to_host_wellness(
return rc;
}
-#define PQI_UPDATE_TIME_WORK_INTERVAL (24UL * 60 * 60 * HZ)
+#define PQI_UPDATE_TIME_WORK_INTERVAL (24UL * 60 * 60 * PQI_HZ)
static void pqi_update_time_worker(struct work_struct *work)
{
@@ -789,25 +921,11 @@ static inline void pqi_cancel_update_time_worker(
cancel_delayed_work_sync(&ctrl_info->update_time_work);
}
-static int pqi_report_luns(struct pqi_ctrl_info *ctrl_info, u8 cmd,
+static inline int pqi_report_luns(struct pqi_ctrl_info *ctrl_info, u8 cmd,
void *buffer, size_t buffer_length)
{
- int rc;
- int pci_direction;
- struct pqi_raid_path_request request;
-
- rc = pqi_build_raid_path_request(ctrl_info, &request,
- cmd, RAID_CTLR_LUNID, buffer, buffer_length, 0, &pci_direction);
- if (rc)
- return rc;
-
- rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, 0,
- NULL, NO_TIMEOUT);
-
- pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- pci_direction);
-
- return rc;
+ return pqi_send_ctrl_raid_request(ctrl_info, cmd, buffer,
+ buffer_length);
}
static int pqi_report_phys_logical_luns(struct pqi_ctrl_info *ctrl_info, u8 cmd,
@@ -1025,8 +1143,6 @@ static int pqi_validate_raid_map(struct pqi_ctrl_info *ctrl_info,
char *err_msg;
u32 raid_map_size;
u32 r5or6_blocks_per_row;
- unsigned int num_phys_disks;
- unsigned int num_raid_map_entries;
raid_map_size = get_unaligned_le32(&raid_map->structure_size);
@@ -1035,22 +1151,6 @@ static int pqi_validate_raid_map(struct pqi_ctrl_info *ctrl_info,
goto bad_raid_map;
}
- if (raid_map_size > sizeof(*raid_map)) {
- err_msg = "RAID map too large";
- goto bad_raid_map;
- }
-
- num_phys_disks = get_unaligned_le16(&raid_map->layout_map_count) *
- (get_unaligned_le16(&raid_map->data_disks_per_row) +
- get_unaligned_le16(&raid_map->metadata_disks_per_row));
- num_raid_map_entries = num_phys_disks *
- get_unaligned_le16(&raid_map->row_cnt);
-
- if (num_raid_map_entries > RAID_MAP_MAX_ENTRIES) {
- err_msg = "invalid number of map entries in RAID map";
- goto bad_raid_map;
- }
-
if (device->raid_level == SA_RAID_1) {
if (get_unaligned_le16(&raid_map->layout_map_count) != 2) {
err_msg = "invalid RAID-1 map";
@@ -1089,28 +1189,45 @@ static int pqi_get_raid_map(struct pqi_ctrl_info *ctrl_info,
struct pqi_scsi_dev *device)
{
int rc;
- int pci_direction;
- struct pqi_raid_path_request request;
+ u32 raid_map_size;
struct raid_map *raid_map;
raid_map = kmalloc(sizeof(*raid_map), GFP_KERNEL);
if (!raid_map)
return -ENOMEM;
- rc = pqi_build_raid_path_request(ctrl_info, &request,
- CISS_GET_RAID_MAP, device->scsi3addr, raid_map,
- sizeof(*raid_map), 0, &pci_direction);
+ rc = pqi_send_scsi_raid_request(ctrl_info, CISS_GET_RAID_MAP,
+ device->scsi3addr, raid_map, sizeof(*raid_map),
+ 0, NULL, NO_TIMEOUT);
+
if (rc)
goto error;
- rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, 0,
- NULL, NO_TIMEOUT);
+ raid_map_size = get_unaligned_le32(&raid_map->structure_size);
- pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- pci_direction);
+ if (raid_map_size > sizeof(*raid_map)) {
- if (rc)
- goto error;
+ kfree(raid_map);
+
+ raid_map = kmalloc(raid_map_size, GFP_KERNEL);
+ if (!raid_map)
+ return -ENOMEM;
+
+ rc = pqi_send_scsi_raid_request(ctrl_info, CISS_GET_RAID_MAP,
+ device->scsi3addr, raid_map, raid_map_size,
+ 0, NULL, NO_TIMEOUT);
+ if (rc)
+ goto error;
+
+ if (get_unaligned_le32(&raid_map->structure_size)
+ != raid_map_size) {
+ dev_warn(&ctrl_info->pci_dev->dev,
+ "Requested %d bytes, received %d bytes",
+ raid_map_size,
+ get_unaligned_le32(&raid_map->structure_size));
+ goto error;
+ }
+ }
rc = pqi_validate_raid_map(ctrl_info, device, raid_map);
if (rc)
@@ -1181,6 +1298,9 @@ static void pqi_get_volume_status(struct pqi_ctrl_info *ctrl_info,
if (rc)
goto out;
+ if (vpd->page_code != CISS_VPD_LV_STATUS)
+ goto out;
+
page_length = offsetof(struct ciss_vpd_logical_volume_status,
volume_status) + vpd->page_length;
if (page_length < sizeof(*vpd))
@@ -1206,6 +1326,9 @@ static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
u8 *buffer;
unsigned int retries;
+ if (device->is_expander_smp_device)
+ return 0;
+
buffer = kmalloc(64, GFP_KERNEL);
if (!buffer)
return -ENOMEM;
@@ -1241,6 +1364,14 @@ static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
}
}
+ if (pqi_get_device_id(ctrl_info, device->scsi3addr,
+ device->unique_id, sizeof(device->unique_id)) < 0)
+ dev_warn(&ctrl_info->pci_dev->dev,
+ "Can't get device id for scsi %d:%d:%d:%d\n",
+ ctrl_info->scsi_host->host_no,
+ device->bus, device->target,
+ device->lun);
+
out:
kfree(buffer);
@@ -1403,9 +1534,24 @@ static int pqi_add_device(struct pqi_ctrl_info *ctrl_info,
return rc;
}
+#define PQI_PENDING_IO_TIMEOUT_SECS 20
+
static inline void pqi_remove_device(struct pqi_ctrl_info *ctrl_info,
struct pqi_scsi_dev *device)
{
+ int rc;
+
+ pqi_device_remove_start(device);
+
+ rc = pqi_device_wait_for_pending_io(ctrl_info, device,
+ PQI_PENDING_IO_TIMEOUT_SECS);
+ if (rc)
+ dev_err(&ctrl_info->pci_dev->dev,
+ "scsi %d:%d:%d:%d removing device with %d outstanding commands\n",
+ ctrl_info->scsi_host->host_no, device->bus,
+ device->target, device->lun,
+ atomic_read(&device->scsi_cmds_outstanding));
+
if (pqi_is_logical_device(device))
scsi_remove_device(device->sdev);
else
@@ -1470,6 +1616,14 @@ static enum pqi_find_result pqi_scsi_find_entry(struct pqi_ctrl_info *ctrl_info,
return DEVICE_NOT_FOUND;
}
+static inline const char *pqi_device_type(struct pqi_scsi_dev *device)
+{
+ if (device->is_expander_smp_device)
+ return "Enclosure SMP ";
+
+ return scsi_device_type(device->devtype);
+}
+
#define PQI_DEV_INFO_BUFFER_LENGTH 128
static void pqi_dev_info(struct pqi_ctrl_info *ctrl_info,
@@ -1505,7 +1659,7 @@ static void pqi_dev_info(struct pqi_ctrl_info *ctrl_info,
count += snprintf(buffer + count, PQI_DEV_INFO_BUFFER_LENGTH - count,
" %s %.8s %.16s ",
- scsi_device_type(device->devtype),
+ pqi_device_type(device),
device->vendor,
device->model);
@@ -1550,6 +1704,8 @@ static void pqi_scsi_update_device(struct pqi_scsi_dev *existing_device,
existing_device->is_physical_device = new_device->is_physical_device;
existing_device->is_external_raid_device =
new_device->is_external_raid_device;
+ existing_device->is_expander_smp_device =
+ new_device->is_expander_smp_device;
existing_device->aio_enabled = new_device->aio_enabled;
memcpy(existing_device->vendor, new_device->vendor,
sizeof(existing_device->vendor));
@@ -1574,6 +1730,7 @@ static void pqi_scsi_update_device(struct pqi_scsi_dev *existing_device,
new_device->raid_bypass_configured;
existing_device->raid_bypass_enabled =
new_device->raid_bypass_enabled;
+ existing_device->device_offline = false;
/* To prevent this from being freed later. */
new_device->raid_map = NULL;
@@ -1605,6 +1762,14 @@ static inline void pqi_fixup_botched_add(struct pqi_ctrl_info *ctrl_info,
device->keep_device = false;
}
+static inline bool pqi_is_device_added(struct pqi_scsi_dev *device)
+{
+ if (device->is_expander_smp_device)
+ return device->sas_port != NULL;
+
+ return device->sdev != NULL;
+}
+
static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
struct pqi_scsi_dev *new_device_list[], unsigned int num_new_devices)
{
@@ -1690,6 +1855,9 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+ if (pqi_ctrl_in_ofa(ctrl_info))
+ pqi_ctrl_ofa_done(ctrl_info);
+
/* Remove all devices that have gone away. */
list_for_each_entry_safe(device, next, &delete_list,
delete_list_entry) {
@@ -1699,7 +1867,7 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
} else {
pqi_dev_info(ctrl_info, "removed", device);
}
- if (device->sdev)
+ if (pqi_is_device_added(device))
pqi_remove_device(ctrl_info, device);
list_del(&device->delete_list_entry);
pqi_free_device(device);
@@ -1721,7 +1889,7 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
/* Expose any new devices. */
list_for_each_entry_safe(device, next, &add_list, add_list_entry) {
- if (!device->sdev) {
+ if (!pqi_is_device_added(device)) {
pqi_dev_info(ctrl_info, "added", device);
rc = pqi_add_device(ctrl_info, device);
if (rc) {
@@ -1738,7 +1906,12 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
static bool pqi_is_supported_device(struct pqi_scsi_dev *device)
{
- bool is_supported = false;
+ bool is_supported;
+
+ if (device->is_expander_smp_device)
+ return true;
+
+ is_supported = false;
switch (device->devtype) {
case TYPE_DISK:
@@ -1772,6 +1945,30 @@ static inline bool pqi_skip_device(u8 *scsi3addr)
return false;
}
+static inline bool pqi_is_device_with_sas_address(struct pqi_scsi_dev *device)
+{
+ if (!device->is_physical_device)
+ return false;
+
+ if (device->is_expander_smp_device)
+ return true;
+
+ switch (device->devtype) {
+ case TYPE_DISK:
+ case TYPE_ZBC:
+ case TYPE_ENCLOSURE:
+ return true;
+ }
+
+ return false;
+}
+
+static inline bool pqi_expose_device(struct pqi_scsi_dev *device)
+{
+ return !device->is_physical_device ||
+ !pqi_skip_device(device->scsi3addr);
+}
+
static int pqi_update_scsi_devices(struct pqi_ctrl_info *ctrl_info)
{
int i;
@@ -1879,9 +2076,14 @@ static int pqi_update_scsi_devices(struct pqi_ctrl_info *ctrl_info)
memcpy(device->scsi3addr, scsi3addr, sizeof(device->scsi3addr));
device->is_physical_device = is_physical_device;
- if (!is_physical_device)
+ if (is_physical_device) {
+ if (phys_lun_ext_entry->device_type ==
+ SA_EXPANDER_SMP_DEVICE)
+ device->is_expander_smp_device = true;
+ } else {
device->is_external_raid_device =
pqi_is_external_raid_addr(scsi3addr);
+ }
/* Gather information about the device. */
rc = pqi_get_device_info(ctrl_info, device);
@@ -1914,30 +2116,23 @@ static int pqi_update_scsi_devices(struct pqi_ctrl_info *ctrl_info)
device->wwid = phys_lun_ext_entry->wwid;
if ((phys_lun_ext_entry->device_flags &
REPORT_PHYS_LUN_DEV_FLAG_AIO_ENABLED) &&
- phys_lun_ext_entry->aio_handle)
+ phys_lun_ext_entry->aio_handle) {
device->aio_enabled = true;
+ device->aio_handle =
+ phys_lun_ext_entry->aio_handle;
+ }
+ if (device->devtype == TYPE_DISK ||
+ device->devtype == TYPE_ZBC) {
+ pqi_get_physical_disk_info(ctrl_info,
+ device, id_phys);
+ }
} else {
memcpy(device->volume_id, log_lun_ext_entry->volume_id,
sizeof(device->volume_id));
}
- switch (device->devtype) {
- case TYPE_DISK:
- case TYPE_ZBC:
- case TYPE_ENCLOSURE:
- if (device->is_physical_device) {
- device->sas_address =
- get_unaligned_be64(&device->wwid);
- if (device->devtype == TYPE_DISK ||
- device->devtype == TYPE_ZBC) {
- device->aio_handle =
- phys_lun_ext_entry->aio_handle;
- pqi_get_physical_disk_info(ctrl_info,
- device, id_phys);
- }
- }
- break;
- }
+ if (pqi_is_device_with_sas_address(device))
+ device->sas_address = get_unaligned_be64(&device->wwid);
new_device_list[num_valid_devices++] = device;
}
@@ -1980,7 +2175,7 @@ static void pqi_remove_all_scsi_devices(struct pqi_ctrl_info *ctrl_info)
if (!device)
break;
- if (device->sdev)
+ if (pqi_is_device_added(device))
pqi_remove_device(ctrl_info, device);
pqi_free_device(device);
}
@@ -2006,7 +2201,13 @@ static int pqi_scan_scsi_devices(struct pqi_ctrl_info *ctrl_info)
static void pqi_scan_start(struct Scsi_Host *shost)
{
- pqi_scan_scsi_devices(shost_to_hba(shost));
+ struct pqi_ctrl_info *ctrl_info;
+
+ ctrl_info = shost_to_hba(shost);
+ if (pqi_ctrl_in_ofa(ctrl_info))
+ return;
+
+ pqi_scan_scsi_devices(ctrl_info);
}
/* Returns TRUE if scan is finished. */
@@ -2033,6 +2234,12 @@ static void pqi_wait_until_lun_reset_finished(struct pqi_ctrl_info *ctrl_info)
mutex_unlock(&ctrl_info->lun_reset_mutex);
}
+static void pqi_wait_until_ofa_finished(struct pqi_ctrl_info *ctrl_info)
+{
+ mutex_lock(&ctrl_info->ofa_mutex);
+ mutex_unlock(&ctrl_info->ofa_mutex);
+}
+
static inline void pqi_set_encryption_info(
struct pqi_encryption_info *encryption_info, struct raid_map *raid_map,
u64 first_block)
@@ -2340,9 +2547,6 @@ static int pqi_raid_bypass_submit_scsi_cmd(struct pqi_ctrl_info *ctrl_info,
(map_row * total_disks_per_row) + first_column;
}
- if (unlikely(map_index >= RAID_MAP_MAX_ENTRIES))
- return PQI_RAID_BYPASS_INELIGIBLE;
-
aio_handle = raid_map->disk_data[map_index].aio_handle;
disk_block = get_unaligned_le64(&raid_map->disk_starting_blk) +
first_row * strip_size +
@@ -2412,7 +2616,7 @@ static int pqi_wait_for_pqi_mode_ready(struct pqi_ctrl_info *ctrl_info)
u8 status;
pqi_registers = ctrl_info->pqi_registers;
- timeout = (PQI_MODE_READY_TIMEOUT_SECS * HZ) + jiffies;
+ timeout = (PQI_MODE_READY_TIMEOUT_SECS * PQI_HZ) + jiffies;
while (1) {
signature = readq(&pqi_registers->signature);
@@ -2473,10 +2677,9 @@ static inline void pqi_take_device_offline(struct scsi_device *sdev, char *path)
return;
device->device_offline = true;
- scsi_device_set_state(sdev, SDEV_OFFLINE);
ctrl_info = shost_to_hba(sdev->host);
pqi_schedule_rescan_worker(ctrl_info);
- dev_err(&ctrl_info->pci_dev->dev, "offlined %s scsi %d:%d:%d:%d\n",
+ dev_err(&ctrl_info->pci_dev->dev, "re-scanning %s scsi %d:%d:%d:%d\n",
path, ctrl_info->scsi_host->host_no, device->bus,
device->target, device->lun);
}
@@ -2553,6 +2756,12 @@ static void pqi_process_raid_io_error(struct pqi_io_request *io_request)
sshdr.sense_key == HARDWARE_ERROR &&
sshdr.asc == 0x3e &&
sshdr.ascq == 0x1) {
+ struct pqi_ctrl_info *ctrl_info = shost_to_hba(scmd->device->host);
+ struct pqi_scsi_dev *device = scmd->device->hostdata;
+
+ if (printk_ratelimit())
+ scmd_printk(KERN_ERR, scmd, "received 'logical unit failure' from controller for scsi %d:%d:%d:%d\n",
+ ctrl_info->scsi_host->host_no, device->bus, device->target, device->lun);
pqi_take_device_offline(scmd->device, "RAID");
host_byte = DID_NO_CONNECT;
}
@@ -2680,6 +2889,9 @@ static int pqi_interpret_task_management_response(
case SOP_TMF_FUNCTION_SUCCEEDED:
rc = 0;
break;
+ case SOP_TMF_REJECTED:
+ rc = -EAGAIN;
+ break;
default:
rc = -EIO;
break;
@@ -2719,8 +2931,17 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info,
switch (response->header.iu_type) {
case PQI_RESPONSE_IU_RAID_PATH_IO_SUCCESS:
case PQI_RESPONSE_IU_AIO_PATH_IO_SUCCESS:
+ if (io_request->scmd)
+ io_request->scmd->result = 0;
+ /* fall through */
case PQI_RESPONSE_IU_GENERAL_MANAGEMENT:
break;
+ case PQI_RESPONSE_IU_VENDOR_GENERAL:
+ io_request->status =
+ get_unaligned_le16(
+ &((struct pqi_vendor_general_response *)
+ response)->status);
+ break;
case PQI_RESPONSE_IU_TASK_MANAGEMENT:
io_request->status =
pqi_interpret_task_management_response(
@@ -2840,6 +3061,111 @@ static void pqi_acknowledge_event(struct pqi_ctrl_info *ctrl_info,
pqi_send_event_ack(ctrl_info, &request, sizeof(request));
}
+#define PQI_SOFT_RESET_STATUS_TIMEOUT_SECS 30
+#define PQI_SOFT_RESET_STATUS_POLL_INTERVAL_SECS 1
+
+static enum pqi_soft_reset_status pqi_poll_for_soft_reset_status(
+ struct pqi_ctrl_info *ctrl_info)
+{
+ unsigned long timeout;
+ u8 status;
+
+ timeout = (PQI_SOFT_RESET_STATUS_TIMEOUT_SECS * PQI_HZ) + jiffies;
+
+ while (1) {
+ status = pqi_read_soft_reset_status(ctrl_info);
+ if (status & PQI_SOFT_RESET_INITIATE)
+ return RESET_INITIATE_DRIVER;
+
+ if (status & PQI_SOFT_RESET_ABORT)
+ return RESET_ABORT;
+
+ if (time_after(jiffies, timeout)) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "timed out waiting for soft reset status\n");
+ return RESET_TIMEDOUT;
+ }
+
+ if (!sis_is_firmware_running(ctrl_info))
+ return RESET_NORESPONSE;
+
+ ssleep(PQI_SOFT_RESET_STATUS_POLL_INTERVAL_SECS);
+ }
+}
+
+static void pqi_process_soft_reset(struct pqi_ctrl_info *ctrl_info,
+ enum pqi_soft_reset_status reset_status)
+{
+ int rc;
+
+ switch (reset_status) {
+ case RESET_INITIATE_DRIVER:
+ /* fall through */
+ case RESET_TIMEDOUT:
+ dev_info(&ctrl_info->pci_dev->dev,
+ "resetting controller %u\n", ctrl_info->ctrl_id);
+ sis_soft_reset(ctrl_info);
+ /* fall through */
+ case RESET_INITIATE_FIRMWARE:
+ rc = pqi_ofa_ctrl_restart(ctrl_info);
+ pqi_ofa_free_host_buffer(ctrl_info);
+ dev_info(&ctrl_info->pci_dev->dev,
+ "Online Firmware Activation for controller %u: %s\n",
+ ctrl_info->ctrl_id, rc == 0 ? "SUCCESS" : "FAILED");
+ break;
+ case RESET_ABORT:
+ pqi_ofa_ctrl_unquiesce(ctrl_info);
+ dev_info(&ctrl_info->pci_dev->dev,
+ "Online Firmware Activation for controller %u: %s\n",
+ ctrl_info->ctrl_id, "ABORTED");
+ break;
+ case RESET_NORESPONSE:
+ pqi_ofa_free_host_buffer(ctrl_info);
+ pqi_take_ctrl_offline(ctrl_info);
+ break;
+ }
+}
+
+static void pqi_ofa_process_event(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_event *event)
+{
+ u16 event_id;
+ enum pqi_soft_reset_status status;
+
+ event_id = get_unaligned_le16(&event->event_id);
+
+ mutex_lock(&ctrl_info->ofa_mutex);
+
+ if (event_id == PQI_EVENT_OFA_QUIESCE) {
+ dev_info(&ctrl_info->pci_dev->dev,
+ "Received Online Firmware Activation quiesce event for controller %u\n",
+ ctrl_info->ctrl_id);
+ pqi_ofa_ctrl_quiesce(ctrl_info);
+ pqi_acknowledge_event(ctrl_info, event);
+ if (ctrl_info->soft_reset_handshake_supported) {
+ status = pqi_poll_for_soft_reset_status(ctrl_info);
+ pqi_process_soft_reset(ctrl_info, status);
+ } else {
+ pqi_process_soft_reset(ctrl_info,
+ RESET_INITIATE_FIRMWARE);
+ }
+
+ } else if (event_id == PQI_EVENT_OFA_MEMORY_ALLOCATION) {
+ pqi_acknowledge_event(ctrl_info, event);
+ pqi_ofa_setup_host_buffer(ctrl_info,
+ le32_to_cpu(event->ofa_bytes_requested));
+ pqi_ofa_host_memory_update(ctrl_info);
+ } else if (event_id == PQI_EVENT_OFA_CANCELLED) {
+ pqi_ofa_free_host_buffer(ctrl_info);
+ pqi_acknowledge_event(ctrl_info, event);
+ dev_info(&ctrl_info->pci_dev->dev,
+ "Online Firmware Activation(%u) cancel reason : %u\n",
+ ctrl_info->ctrl_id, event->ofa_cancel_reason);
+ }
+
+ mutex_unlock(&ctrl_info->ofa_mutex);
+}
+
static void pqi_event_worker(struct work_struct *work)
{
unsigned int i;
@@ -2859,6 +3185,11 @@ static void pqi_event_worker(struct work_struct *work)
for (i = 0; i < PQI_NUM_SUPPORTED_EVENTS; i++) {
if (event->pending) {
event->pending = false;
+ if (event->event_type == PQI_EVENT_TYPE_OFA) {
+ pqi_ctrl_unbusy(ctrl_info);
+ pqi_ofa_process_event(ctrl_info, event);
+ return;
+ }
pqi_acknowledge_event(ctrl_info, event);
}
event++;
@@ -2868,7 +3199,7 @@ out:
pqi_ctrl_unbusy(ctrl_info);
}
-#define PQI_HEARTBEAT_TIMER_INTERVAL (10 * HZ)
+#define PQI_HEARTBEAT_TIMER_INTERVAL (10 * PQI_HZ)
static void pqi_heartbeat_timer_handler(unsigned long data)
{
@@ -2938,6 +3269,24 @@ static inline bool pqi_is_supported_event(unsigned int event_type)
return pqi_event_type_to_event_index(event_type) != -1;
}
+static void pqi_ofa_capture_event_payload(struct pqi_event *event,
+ struct pqi_event_response *response)
+{
+ u16 event_id;
+
+ event_id = get_unaligned_le16(&event->event_id);
+
+ if (event->event_type == PQI_EVENT_TYPE_OFA) {
+ if (event_id == PQI_EVENT_OFA_MEMORY_ALLOCATION) {
+ event->ofa_bytes_requested =
+ response->data.ofa_memory_allocation.bytes_requested;
+ } else if (event_id == PQI_EVENT_OFA_CANCELLED) {
+ event->ofa_cancel_reason =
+ response->data.ofa_cancelled.reason;
+ }
+ }
+}
+
static unsigned int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info)
{
unsigned int num_events;
@@ -2972,6 +3321,7 @@ static unsigned int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info)
event->event_id = response->event_id;
event->additional_event_id =
response->additional_event_id;
+ pqi_ofa_capture_event_payload(event, response);
}
}
@@ -3405,7 +3755,7 @@ static int pqi_alloc_admin_queues(struct pqi_ctrl_info *ctrl_info)
return 0;
}
-#define PQI_ADMIN_QUEUE_CREATE_TIMEOUT_JIFFIES HZ
+#define PQI_ADMIN_QUEUE_CREATE_TIMEOUT_JIFFIES PQI_HZ
#define PQI_ADMIN_QUEUE_CREATE_POLL_INTERVAL_MSECS 1
static int pqi_create_admin_queues(struct pqi_ctrl_info *ctrl_info)
@@ -3498,7 +3848,7 @@ static int pqi_poll_for_admin_response(struct pqi_ctrl_info *ctrl_info,
admin_queues = &ctrl_info->admin_queues;
oq_ci = admin_queues->oq_ci_copy;
- timeout = (PQI_ADMIN_REQUEST_TIMEOUT_SECS * HZ) + jiffies;
+ timeout = (PQI_ADMIN_REQUEST_TIMEOUT_SECS * PQI_HZ) + jiffies;
while (1) {
oq_pi = readl(admin_queues->oq_pi);
@@ -3613,7 +3963,7 @@ static int pqi_wait_for_completion_io(struct pqi_ctrl_info *ctrl_info,
while (1) {
if (wait_for_completion_io_timeout(wait,
- PQI_WAIT_FOR_COMPLETION_IO_TIMEOUT_SECS * HZ)) {
+ PQI_WAIT_FOR_COMPLETION_IO_TIMEOUT_SECS * PQI_HZ)) {
rc = 0;
break;
}
@@ -3822,7 +4172,7 @@ static int pqi_report_device_capability(struct pqi_ctrl_info *ctrl_info)
rc = pqi_map_single(ctrl_info->pci_dev,
&request.data.report_device_capability.sg_descriptor,
capability, sizeof(*capability),
- PCI_DMA_FROMDEVICE);
+ DMA_FROM_DEVICE);
if (rc)
goto out;
@@ -3831,7 +4181,7 @@ static int pqi_report_device_capability(struct pqi_ctrl_info *ctrl_info)
pqi_pci_unmap(ctrl_info->pci_dev,
&request.data.report_device_capability.sg_descriptor, 1,
- PCI_DMA_FROMDEVICE);
+ DMA_FROM_DEVICE);
if (rc)
goto out;
@@ -4158,7 +4508,7 @@ static int pqi_configure_events(struct pqi_ctrl_info *ctrl_info,
rc = pqi_map_single(ctrl_info->pci_dev,
request.data.report_event_configuration.sg_descriptors,
event_config, PQI_REPORT_EVENT_CONFIG_BUFFER_LENGTH,
- PCI_DMA_FROMDEVICE);
+ DMA_FROM_DEVICE);
if (rc)
goto out;
@@ -4167,7 +4517,7 @@ static int pqi_configure_events(struct pqi_ctrl_info *ctrl_info,
pqi_pci_unmap(ctrl_info->pci_dev,
request.data.report_event_configuration.sg_descriptors, 1,
- PCI_DMA_FROMDEVICE);
+ DMA_FROM_DEVICE);
if (rc)
goto out;
@@ -4194,7 +4544,7 @@ static int pqi_configure_events(struct pqi_ctrl_info *ctrl_info,
rc = pqi_map_single(ctrl_info->pci_dev,
request.data.report_event_configuration.sg_descriptors,
event_config, PQI_REPORT_EVENT_CONFIG_BUFFER_LENGTH,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
if (rc)
goto out;
@@ -4203,7 +4553,7 @@ static int pqi_configure_events(struct pqi_ctrl_info *ctrl_info,
pqi_pci_unmap(ctrl_info->pci_dev,
request.data.report_event_configuration.sg_descriptors, 1,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
out:
kfree(event_config);
@@ -4942,7 +5292,17 @@ void pqi_prep_for_scsi_done(struct scsi_cmnd *scmd)
{
struct pqi_scsi_dev *device;
+ if (!scmd->device) {
+ set_host_byte(scmd, DID_NO_CONNECT);
+ return;
+ }
+
device = scmd->device->hostdata;
+ if (!device) {
+ set_host_byte(scmd, DID_NO_CONNECT);
+ return;
+ }
+
atomic_dec(&device->scsi_cmds_outstanding);
}
@@ -4959,16 +5319,24 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost,
device = scmd->device->hostdata;
ctrl_info = shost_to_hba(shost);
+ if (!device) {
+ set_host_byte(scmd, DID_NO_CONNECT);
+ pqi_scsi_done(scmd);
+ return 0;
+ }
+
atomic_inc(&device->scsi_cmds_outstanding);
- if (pqi_ctrl_offline(ctrl_info)) {
+ if (pqi_ctrl_offline(ctrl_info) || pqi_device_in_remove(ctrl_info,
+ device)) {
set_host_byte(scmd, DID_NO_CONNECT);
pqi_scsi_done(scmd);
return 0;
}
pqi_ctrl_busy(ctrl_info);
- if (pqi_ctrl_blocked(ctrl_info) || pqi_device_in_reset(device)) {
+ if (pqi_ctrl_blocked(ctrl_info) || pqi_device_in_reset(device) ||
+ pqi_ctrl_in_ofa(ctrl_info)) {
rc = SCSI_MLQUEUE_HOST_BUSY;
goto out;
}
@@ -5113,25 +5481,75 @@ static void pqi_fail_io_queued_for_device(struct pqi_ctrl_info *ctrl_info,
}
}
+static void pqi_fail_io_queued_for_all_devices(struct pqi_ctrl_info *ctrl_info)
+{
+ unsigned int i;
+ unsigned int path;
+ struct pqi_queue_group *queue_group;
+ unsigned long flags;
+ struct pqi_io_request *io_request;
+ struct pqi_io_request *next;
+ struct scsi_cmnd *scmd;
+
+ for (i = 0; i < ctrl_info->num_queue_groups; i++) {
+ queue_group = &ctrl_info->queue_groups[i];
+
+ for (path = 0; path < 2; path++) {
+ spin_lock_irqsave(&queue_group->submit_lock[path],
+ flags);
+
+ list_for_each_entry_safe(io_request, next,
+ &queue_group->request_list[path],
+ request_list_entry) {
+
+ scmd = io_request->scmd;
+ if (!scmd)
+ continue;
+
+ list_del(&io_request->request_list_entry);
+ set_host_byte(scmd, DID_RESET);
+ pqi_scsi_done(scmd);
+ }
+
+ spin_unlock_irqrestore(
+ &queue_group->submit_lock[path], flags);
+ }
+ }
+}
+
static int pqi_device_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info,
- struct pqi_scsi_dev *device)
+ struct pqi_scsi_dev *device, unsigned long timeout_secs)
{
+ unsigned long timeout;
+
+ timeout = (timeout_secs * PQI_HZ) + jiffies;
+
while (atomic_read(&device->scsi_cmds_outstanding)) {
pqi_check_ctrl_health(ctrl_info);
if (pqi_ctrl_offline(ctrl_info))
return -ENXIO;
+ if (timeout_secs != NO_TIMEOUT) {
+ if (time_after(jiffies, timeout)) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "timed out waiting for pending IO\n");
+ return -ETIMEDOUT;
+ }
+ }
usleep_range(1000, 2000);
}
return 0;
}
-static int pqi_ctrl_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info)
+static int pqi_ctrl_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info,
+ unsigned long timeout_secs)
{
bool io_pending;
unsigned long flags;
+ unsigned long timeout;
struct pqi_scsi_dev *device;
+ timeout = (timeout_secs * PQI_HZ) + jiffies;
while (1) {
io_pending = false;
@@ -5153,6 +5571,13 @@ static int pqi_ctrl_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info)
if (pqi_ctrl_offline(ctrl_info))
return -ENXIO;
+ if (timeout_secs != NO_TIMEOUT) {
+ if (time_after(jiffies, timeout)) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "timed out waiting for pending IO\n");
+ return -ETIMEDOUT;
+ }
+ }
usleep_range(1000, 2000);
}
@@ -5176,7 +5601,7 @@ static int pqi_wait_for_lun_reset_completion(struct pqi_ctrl_info *ctrl_info,
while (1) {
if (wait_for_completion_io_timeout(wait,
- PQI_LUN_RESET_TIMEOUT_SECS * HZ)) {
+ PQI_LUN_RESET_TIMEOUT_SECS * PQI_HZ)) {
rc = 0;
break;
}
@@ -5229,18 +5654,57 @@ static int pqi_lun_reset(struct pqi_ctrl_info *ctrl_info,
/* Performs a reset at the LUN level. */
-static int pqi_device_reset(struct pqi_ctrl_info *ctrl_info,
+#define PQI_LUN_RESET_RETRIES 3
+#define PQI_LUN_RESET_RETRY_INTERVAL_MSECS 10000
+#define PQI_LUN_RESET_PENDING_IO_TIMEOUT_SECS 120
+
+static int _pqi_device_reset(struct pqi_ctrl_info *ctrl_info,
struct pqi_scsi_dev *device)
{
int rc;
+ unsigned int retries;
+ unsigned long timeout_secs;
- rc = pqi_lun_reset(ctrl_info, device);
- if (rc == 0)
- rc = pqi_device_wait_for_pending_io(ctrl_info, device);
+ for (retries = 0;;) {
+ rc = pqi_lun_reset(ctrl_info, device);
+ if (rc != -EAGAIN || ++retries > PQI_LUN_RESET_RETRIES)
+ break;
+ msleep(PQI_LUN_RESET_RETRY_INTERVAL_MSECS);
+ }
+
+ timeout_secs = rc ? PQI_LUN_RESET_PENDING_IO_TIMEOUT_SECS : NO_TIMEOUT;
+
+ rc |= pqi_device_wait_for_pending_io(ctrl_info, device, timeout_secs);
return rc == 0 ? SUCCESS : FAILED;
}
+static int pqi_device_reset(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_scsi_dev *device)
+{
+ int rc;
+
+ mutex_lock(&ctrl_info->lun_reset_mutex);
+
+ pqi_ctrl_block_requests(ctrl_info);
+ pqi_ctrl_wait_until_quiesced(ctrl_info);
+ pqi_fail_io_queued_for_device(ctrl_info, device);
+ rc = pqi_wait_until_inbound_queues_empty(ctrl_info);
+ pqi_device_reset_start(device);
+ pqi_ctrl_unblock_requests(ctrl_info);
+
+ if (rc)
+ rc = FAILED;
+ else
+ rc = _pqi_device_reset(ctrl_info, device);
+
+ pqi_device_reset_done(device);
+
+ mutex_unlock(&ctrl_info->lun_reset_mutex);
+
+ return rc;
+}
+
static int pqi_eh_device_reset_handler(struct scsi_cmnd *scmd)
{
int rc;
@@ -5258,27 +5722,16 @@ static int pqi_eh_device_reset_handler(struct scsi_cmnd *scmd)
pqi_check_ctrl_health(ctrl_info);
if (pqi_ctrl_offline(ctrl_info)) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "controller %u offlined - cannot send device reset\n",
+ ctrl_info->ctrl_id);
rc = FAILED;
goto out;
}
- mutex_lock(&ctrl_info->lun_reset_mutex);
-
- pqi_ctrl_block_requests(ctrl_info);
- pqi_ctrl_wait_until_quiesced(ctrl_info);
- pqi_fail_io_queued_for_device(ctrl_info, device);
- rc = pqi_wait_until_inbound_queues_empty(ctrl_info);
- pqi_device_reset_start(device);
- pqi_ctrl_unblock_requests(ctrl_info);
-
- if (rc)
- rc = FAILED;
- else
- rc = pqi_device_reset(ctrl_info, device);
-
- pqi_device_reset_done(device);
+ pqi_wait_until_ofa_finished(ctrl_info);
- mutex_unlock(&ctrl_info->lun_reset_mutex);
+ rc = pqi_device_reset(ctrl_info, device);
out:
dev_err(&ctrl_info->pci_dev->dev,
@@ -5323,6 +5776,10 @@ static int pqi_slave_alloc(struct scsi_device *sdev)
scsi_change_queue_depth(sdev,
device->advertised_queue_depth);
}
+ if (pqi_is_logical_device(device))
+ pqi_disable_write_same(sdev);
+ else
+ sdev->allow_restart = 1;
}
spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
@@ -5533,7 +5990,7 @@ static int pqi_passthru_ioctl(struct pqi_ctrl_info *ctrl_info, void __user *arg)
rc = pqi_map_single(ctrl_info->pci_dev,
&request.sg_descriptors[0], kernel_buffer,
- iocommand.buf_size, PCI_DMA_BIDIRECTIONAL);
+ iocommand.buf_size, DMA_BIDIRECTIONAL);
if (rc)
goto out;
@@ -5547,7 +6004,7 @@ static int pqi_passthru_ioctl(struct pqi_ctrl_info *ctrl_info, void __user *arg)
if (iocommand.buf_size > 0)
pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1,
- PCI_DMA_BIDIRECTIONAL);
+ DMA_BIDIRECTIONAL);
memset(&iocommand.error_info, 0, sizeof(iocommand.error_info));
@@ -5594,6 +6051,9 @@ static int pqi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
ctrl_info = shost_to_hba(sdev->host);
+ if (pqi_ctrl_in_ofa(ctrl_info))
+ return -EBUSY;
+
switch (cmd) {
case CCISS_DEREGDISK:
case CCISS_REGNEWDISK:
@@ -5698,6 +6158,150 @@ static struct device_attribute *pqi_shost_attrs[] = {
NULL
};
+static ssize_t pqi_unique_id_show(struct device *dev,
+ struct device_attribute *attr, char *buffer)
+{
+ struct pqi_ctrl_info *ctrl_info;
+ struct scsi_device *sdev;
+ struct pqi_scsi_dev *device;
+ unsigned long flags;
+ unsigned char uid[16];
+
+ sdev = to_scsi_device(dev);
+ ctrl_info = shost_to_hba(sdev->host);
+
+ spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+
+ device = sdev->hostdata;
+ if (!device) {
+ spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock,
+ flags);
+ return -ENODEV;
+ }
+ memcpy(uid, device->unique_id, sizeof(uid));
+
+ spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+
+ return snprintf(buffer, PAGE_SIZE,
+ "%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X\n",
+ uid[0], uid[1], uid[2], uid[3],
+ uid[4], uid[5], uid[6], uid[7],
+ uid[8], uid[9], uid[10], uid[11],
+ uid[12], uid[13], uid[14], uid[15]);
+}
+
+static ssize_t pqi_lunid_show(struct device *dev,
+ struct device_attribute *attr, char *buffer)
+{
+ struct pqi_ctrl_info *ctrl_info;
+ struct scsi_device *sdev;
+ struct pqi_scsi_dev *device;
+ unsigned long flags;
+ u8 lunid[8];
+
+ sdev = to_scsi_device(dev);
+ ctrl_info = shost_to_hba(sdev->host);
+
+ spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+
+ device = sdev->hostdata;
+ if (!device) {
+ spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock,
+ flags);
+ return -ENODEV;
+ }
+ memcpy(lunid, device->scsi3addr, sizeof(lunid));
+
+ spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+
+ return snprintf(buffer, PAGE_SIZE, "0x%8phN\n", lunid);
+}
+
+#define MAX_PATHS 8
+static ssize_t pqi_path_info_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pqi_ctrl_info *ctrl_info;
+ struct scsi_device *sdev;
+ struct pqi_scsi_dev *device;
+ unsigned long flags;
+ int i;
+ int output_len = 0;
+ u8 box;
+ u8 bay;
+ u8 path_map_index = 0;
+ char *active;
+ unsigned char phys_connector[2];
+
+ sdev = to_scsi_device(dev);
+ ctrl_info = shost_to_hba(sdev->host);
+
+ spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
+
+ device = sdev->hostdata;
+ if (!device) {
+ spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock,
+ flags);
+ return -ENODEV;
+ }
+
+ bay = device->bay;
+ for (i = 0; i < MAX_PATHS; i++) {
+ path_map_index = 1<<i;
+ if (i == device->active_path_index)
+ active = "Active";
+ else if (device->path_map & path_map_index)
+ active = "Inactive";
+ else
+ continue;
+
+ output_len += scnprintf(buf + output_len,
+ PAGE_SIZE - output_len,
+ "[%d:%d:%d:%d] %20.20s ",
+ ctrl_info->scsi_host->host_no,
+ device->bus, device->target,
+ device->lun,
+ scsi_device_type(device->devtype));
+
+ if (device->devtype == TYPE_RAID ||
+ pqi_is_logical_device(device))
+ goto end_buffer;
+
+ memcpy(&phys_connector, &device->phys_connector[i],
+ sizeof(phys_connector));
+ if (phys_connector[0] < '0')
+ phys_connector[0] = '0';
+ if (phys_connector[1] < '0')
+ phys_connector[1] = '0';
+
+ output_len += scnprintf(buf + output_len,
+ PAGE_SIZE - output_len,
+ "PORT: %.2s ", phys_connector);
+
+ box = device->box[i];
+ if (box != 0 && box != 0xFF)
+ output_len += scnprintf(buf + output_len,
+ PAGE_SIZE - output_len,
+ "BOX: %hhu ", box);
+
+ if ((device->devtype == TYPE_DISK ||
+ device->devtype == TYPE_ZBC) &&
+ pqi_expose_device(device))
+ output_len += scnprintf(buf + output_len,
+ PAGE_SIZE - output_len,
+ "BAY: %hhu ", bay);
+
+end_buffer:
+ output_len += scnprintf(buf + output_len,
+ PAGE_SIZE - output_len,
+ "%s\n", active);
+ }
+
+ spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+ return output_len;
+}
+
+
static ssize_t pqi_sas_address_show(struct device *dev,
struct device_attribute *attr, char *buffer)
{
@@ -5774,12 +6378,18 @@ static ssize_t pqi_raid_level_show(struct device *dev,
return snprintf(buffer, PAGE_SIZE, "%s\n", raid_level);
}
+static DEVICE_ATTR(lunid, 0444, pqi_lunid_show, NULL);
+static DEVICE_ATTR(unique_id, 0444, pqi_unique_id_show, NULL);
+static DEVICE_ATTR(path_info, 0444, pqi_path_info_show, NULL);
static DEVICE_ATTR(sas_address, 0444, pqi_sas_address_show, NULL);
static DEVICE_ATTR(ssd_smart_path_enabled, 0444,
pqi_ssd_smart_path_enabled_show, NULL);
static DEVICE_ATTR(raid_level, 0444, pqi_raid_level_show, NULL);
static struct device_attribute *pqi_sdev_attrs[] = {
+ &dev_attr_lunid,
+ &dev_attr_unique_id,
+ &dev_attr_path_info,
&dev_attr_sas_address,
&dev_attr_ssd_smart_path_enabled,
&dev_attr_raid_level,
@@ -5962,6 +6572,244 @@ out:
return rc;
}
+struct pqi_config_table_section_info {
+ struct pqi_ctrl_info *ctrl_info;
+ void *section;
+ u32 section_offset;
+ void __iomem *section_iomem_addr;
+};
+
+static inline bool pqi_is_firmware_feature_supported(
+ struct pqi_config_table_firmware_features *firmware_features,
+ unsigned int bit_position)
+{
+ unsigned int byte_index;
+
+ byte_index = bit_position / BITS_PER_BYTE;
+
+ if (byte_index >= le16_to_cpu(firmware_features->num_elements))
+ return false;
+
+ return firmware_features->features_supported[byte_index] &
+ (1 << (bit_position % BITS_PER_BYTE)) ? true : false;
+}
+
+static inline bool pqi_is_firmware_feature_enabled(
+ struct pqi_config_table_firmware_features *firmware_features,
+ void __iomem *firmware_features_iomem_addr,
+ unsigned int bit_position)
+{
+ unsigned int byte_index;
+ u8 __iomem *features_enabled_iomem_addr;
+
+ byte_index = (bit_position / BITS_PER_BYTE) +
+ (le16_to_cpu(firmware_features->num_elements) * 2);
+
+ features_enabled_iomem_addr = firmware_features_iomem_addr +
+ offsetof(struct pqi_config_table_firmware_features,
+ features_supported) + byte_index;
+
+ return *((__force u8 *)features_enabled_iomem_addr) &
+ (1 << (bit_position % BITS_PER_BYTE)) ? true : false;
+}
+
+static inline void pqi_request_firmware_feature(
+ struct pqi_config_table_firmware_features *firmware_features,
+ unsigned int bit_position)
+{
+ unsigned int byte_index;
+
+ byte_index = (bit_position / BITS_PER_BYTE) +
+ le16_to_cpu(firmware_features->num_elements);
+
+ firmware_features->features_supported[byte_index] |=
+ (1 << (bit_position % BITS_PER_BYTE));
+}
+
+static int pqi_config_table_update(struct pqi_ctrl_info *ctrl_info,
+ u16 first_section, u16 last_section)
+{
+ struct pqi_vendor_general_request request;
+
+ memset(&request, 0, sizeof(request));
+
+ request.header.iu_type = PQI_REQUEST_IU_VENDOR_GENERAL;
+ put_unaligned_le16(sizeof(request) - PQI_REQUEST_HEADER_LENGTH,
+ &request.header.iu_length);
+ put_unaligned_le16(PQI_VENDOR_GENERAL_CONFIG_TABLE_UPDATE,
+ &request.function_code);
+ put_unaligned_le16(first_section,
+ &request.data.config_table_update.first_section);
+ put_unaligned_le16(last_section,
+ &request.data.config_table_update.last_section);
+
+ return pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
+ 0, NULL, NO_TIMEOUT);
+}
+
+static int pqi_enable_firmware_features(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_config_table_firmware_features *firmware_features,
+ void __iomem *firmware_features_iomem_addr)
+{
+ void *features_requested;
+ void __iomem *features_requested_iomem_addr;
+
+ features_requested = firmware_features->features_supported +
+ le16_to_cpu(firmware_features->num_elements);
+
+ features_requested_iomem_addr = firmware_features_iomem_addr +
+ (features_requested - (void *)firmware_features);
+
+ memcpy_toio(features_requested_iomem_addr, features_requested,
+ le16_to_cpu(firmware_features->num_elements));
+
+ return pqi_config_table_update(ctrl_info,
+ PQI_CONFIG_TABLE_SECTION_FIRMWARE_FEATURES,
+ PQI_CONFIG_TABLE_SECTION_FIRMWARE_FEATURES);
+}
+
+struct pqi_firmware_feature {
+ char *feature_name;
+ unsigned int feature_bit;
+ bool supported;
+ bool enabled;
+ void (*feature_status)(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_firmware_feature *firmware_feature);
+};
+
+static void pqi_firmware_feature_status(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_firmware_feature *firmware_feature)
+{
+ if (!firmware_feature->supported) {
+ dev_info(&ctrl_info->pci_dev->dev, "%s not supported by controller\n",
+ firmware_feature->feature_name);
+ return;
+ }
+
+ if (firmware_feature->enabled) {
+ dev_info(&ctrl_info->pci_dev->dev,
+ "%s enabled\n", firmware_feature->feature_name);
+ return;
+ }
+
+ dev_err(&ctrl_info->pci_dev->dev, "failed to enable %s\n",
+ firmware_feature->feature_name);
+}
+
+static inline void pqi_firmware_feature_update(struct pqi_ctrl_info *ctrl_info,
+ struct pqi_firmware_feature *firmware_feature)
+{
+ if (firmware_feature->feature_status)
+ firmware_feature->feature_status(ctrl_info, firmware_feature);
+}
+
+static DEFINE_MUTEX(pqi_firmware_features_mutex);
+
+static struct pqi_firmware_feature pqi_firmware_features[] = {
+ {
+ .feature_name = "Online Firmware Activation",
+ .feature_bit = PQI_FIRMWARE_FEATURE_OFA,
+ .feature_status = pqi_firmware_feature_status,
+ },
+ {
+ .feature_name = "Serial Management Protocol",
+ .feature_bit = PQI_FIRMWARE_FEATURE_SMP,
+ .feature_status = pqi_firmware_feature_status,
+ },
+ {
+ .feature_name = "New Soft Reset Handshake",
+ .feature_bit = PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE,
+ .feature_status = pqi_firmware_feature_status,
+ },
+};
+
+static void pqi_process_firmware_features(
+ struct pqi_config_table_section_info *section_info)
+{
+ int rc;
+ struct pqi_ctrl_info *ctrl_info;
+ struct pqi_config_table_firmware_features *firmware_features;
+ void __iomem *firmware_features_iomem_addr;
+ unsigned int i;
+ unsigned int num_features_supported;
+
+ ctrl_info = section_info->ctrl_info;
+ firmware_features = section_info->section;
+ firmware_features_iomem_addr = section_info->section_iomem_addr;
+
+ for (i = 0, num_features_supported = 0;
+ i < ARRAY_SIZE(pqi_firmware_features); i++) {
+ if (pqi_is_firmware_feature_supported(firmware_features,
+ pqi_firmware_features[i].feature_bit)) {
+ pqi_firmware_features[i].supported = true;
+ num_features_supported++;
+ } else {
+ pqi_firmware_feature_update(ctrl_info,
+ &pqi_firmware_features[i]);
+ }
+ }
+
+ if (num_features_supported == 0)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(pqi_firmware_features); i++) {
+ if (!pqi_firmware_features[i].supported)
+ continue;
+ pqi_request_firmware_feature(firmware_features,
+ pqi_firmware_features[i].feature_bit);
+ }
+
+ rc = pqi_enable_firmware_features(ctrl_info, firmware_features,
+ firmware_features_iomem_addr);
+ if (rc) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "failed to enable firmware features in PQI configuration table\n");
+ for (i = 0; i < ARRAY_SIZE(pqi_firmware_features); i++) {
+ if (!pqi_firmware_features[i].supported)
+ continue;
+ pqi_firmware_feature_update(ctrl_info,
+ &pqi_firmware_features[i]);
+ }
+ return;
+ }
+
+ ctrl_info->soft_reset_handshake_supported = false;
+ for (i = 0; i < ARRAY_SIZE(pqi_firmware_features); i++) {
+ if (!pqi_firmware_features[i].supported)
+ continue;
+ if (pqi_is_firmware_feature_enabled(firmware_features,
+ firmware_features_iomem_addr,
+ pqi_firmware_features[i].feature_bit)) {
+ pqi_firmware_features[i].enabled = true;
+ if (pqi_firmware_features[i].feature_bit ==
+ PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE)
+ ctrl_info->soft_reset_handshake_supported =
+ true;
+ }
+ pqi_firmware_feature_update(ctrl_info,
+ &pqi_firmware_features[i]);
+ }
+}
+
+static void pqi_init_firmware_features(void)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(pqi_firmware_features); i++) {
+ pqi_firmware_features[i].supported = false;
+ pqi_firmware_features[i].enabled = false;
+ }
+}
+
+static void pqi_process_firmware_features_section(
+ struct pqi_config_table_section_info *section_info)
+{
+ mutex_lock(&pqi_firmware_features_mutex);
+ pqi_init_firmware_features();
+ pqi_process_firmware_features(section_info);
+ mutex_unlock(&pqi_firmware_features_mutex);
+}
+
static int pqi_process_config_table(struct pqi_ctrl_info *ctrl_info)
{
u32 table_length;
@@ -5969,8 +6817,11 @@ static int pqi_process_config_table(struct pqi_ctrl_info *ctrl_info)
void __iomem *table_iomem_addr;
struct pqi_config_table *config_table;
struct pqi_config_table_section_header *section;
+ struct pqi_config_table_section_info section_info;
table_length = ctrl_info->config_table_length;
+ if (table_length == 0)
+ return 0;
config_table = kmalloc(table_length, GFP_KERNEL);
if (!config_table) {
@@ -5987,13 +6838,22 @@ static int pqi_process_config_table(struct pqi_ctrl_info *ctrl_info)
ctrl_info->config_table_offset;
memcpy_fromio(config_table, table_iomem_addr, table_length);
+ section_info.ctrl_info = ctrl_info;
section_offset =
get_unaligned_le32(&config_table->first_section_offset);
while (section_offset) {
section = (void *)config_table + section_offset;
+ section_info.section = section;
+ section_info.section_offset = section_offset;
+ section_info.section_iomem_addr =
+ table_iomem_addr + section_offset;
+
switch (get_unaligned_le16(&section->section_id)) {
+ case PQI_CONFIG_TABLE_SECTION_FIRMWARE_FEATURES:
+ pqi_process_firmware_features_section(&section_info);
+ break;
case PQI_CONFIG_TABLE_SECTION_HEARTBEAT:
if (pqi_disable_heartbeat)
dev_warn(&ctrl_info->pci_dev->dev,
@@ -6006,6 +6866,13 @@ static int pqi_process_config_table(struct pqi_ctrl_info *ctrl_info)
struct pqi_config_table_heartbeat,
heartbeat_counter);
break;
+ case PQI_CONFIG_TABLE_SECTION_SOFT_RESET:
+ ctrl_info->soft_reset_status =
+ table_iomem_addr +
+ section_offset +
+ offsetof(struct pqi_config_table_soft_reset,
+ soft_reset_status);
+ break;
}
section_offset =
@@ -6138,10 +7005,6 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
ctrl_info->pqi_mode_enabled = true;
pqi_save_ctrl_mode(ctrl_info, PQI_MODE);
- rc = pqi_process_config_table(ctrl_info);
- if (rc)
- return rc;
-
rc = pqi_alloc_admin_queues(ctrl_info);
if (rc) {
dev_err(&ctrl_info->pci_dev->dev,
@@ -6203,6 +7066,11 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
pqi_change_irq_mode(ctrl_info, IRQ_MODE_MSIX);
ctrl_info->controller_online = true;
+
+ rc = pqi_process_config_table(ctrl_info);
+ if (rc)
+ return rc;
+
pqi_start_heartbeat_timer(ctrl_info);
rc = pqi_enable_events(ctrl_info);
@@ -6224,6 +7092,13 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
return rc;
}
+ rc = pqi_set_diag_rescan(ctrl_info);
+ if (rc) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "error enabling multi-lun rescan\n");
+ return rc;
+ }
+
rc = pqi_write_driver_version_to_host_wellness(ctrl_info);
if (rc) {
dev_err(&ctrl_info->pci_dev->dev,
@@ -6281,6 +7156,24 @@ static int pqi_ctrl_init_resume(struct pqi_ctrl_info *ctrl_info)
return rc;
/*
+ * Get the controller properties. This allows us to determine
+ * whether or not it supports PQI mode.
+ */
+ rc = sis_get_ctrl_properties(ctrl_info);
+ if (rc) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "error obtaining controller properties\n");
+ return rc;
+ }
+
+ rc = sis_get_pqi_capabilities(ctrl_info);
+ if (rc) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "error obtaining controller capabilities\n");
+ return rc;
+ }
+
+ /*
* If the function we are about to call succeeds, the
* controller will transition from legacy SIS mode
* into PQI mode.
@@ -6320,9 +7213,14 @@ static int pqi_ctrl_init_resume(struct pqi_ctrl_info *ctrl_info)
pqi_change_irq_mode(ctrl_info, IRQ_MODE_MSIX);
ctrl_info->controller_online = true;
- pqi_start_heartbeat_timer(ctrl_info);
pqi_ctrl_unblock_requests(ctrl_info);
+ rc = pqi_process_config_table(ctrl_info);
+ if (rc)
+ return rc;
+
+ pqi_start_heartbeat_timer(ctrl_info);
+
rc = pqi_enable_events(ctrl_info);
if (rc) {
dev_err(&ctrl_info->pci_dev->dev,
@@ -6330,6 +7228,20 @@ static int pqi_ctrl_init_resume(struct pqi_ctrl_info *ctrl_info)
return rc;
}
+ rc = pqi_get_ctrl_firmware_version(ctrl_info);
+ if (rc) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "error obtaining firmware version\n");
+ return rc;
+ }
+
+ rc = pqi_set_diag_rescan(ctrl_info);
+ if (rc) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "error enabling multi-lun rescan\n");
+ return rc;
+ }
+
rc = pqi_write_driver_version_to_host_wellness(ctrl_info);
if (rc) {
dev_err(&ctrl_info->pci_dev->dev,
@@ -6440,6 +7352,7 @@ static struct pqi_ctrl_info *pqi_alloc_ctrl_info(int numa_node)
mutex_init(&ctrl_info->scan_mutex);
mutex_init(&ctrl_info->lun_reset_mutex);
+ mutex_init(&ctrl_info->ofa_mutex);
INIT_LIST_HEAD(&ctrl_info->scsi_device_list);
spin_lock_init(&ctrl_info->scsi_device_list_lock);
@@ -6516,6 +7429,217 @@ static void pqi_remove_ctrl(struct pqi_ctrl_info *ctrl_info)
pqi_free_ctrl_resources(ctrl_info);
}
+static void pqi_ofa_ctrl_quiesce(struct pqi_ctrl_info *ctrl_info)
+{
+ pqi_cancel_update_time_worker(ctrl_info);
+ pqi_cancel_rescan_worker(ctrl_info);
+ pqi_wait_until_lun_reset_finished(ctrl_info);
+ pqi_wait_until_scan_finished(ctrl_info);
+ pqi_ctrl_ofa_start(ctrl_info);
+ pqi_ctrl_block_requests(ctrl_info);
+ pqi_ctrl_wait_until_quiesced(ctrl_info);
+ pqi_ctrl_wait_for_pending_io(ctrl_info, PQI_PENDING_IO_TIMEOUT_SECS);
+ pqi_fail_io_queued_for_all_devices(ctrl_info);
+ pqi_wait_until_inbound_queues_empty(ctrl_info);
+ pqi_stop_heartbeat_timer(ctrl_info);
+ ctrl_info->pqi_mode_enabled = false;
+ pqi_save_ctrl_mode(ctrl_info, SIS_MODE);
+}
+
+static void pqi_ofa_ctrl_unquiesce(struct pqi_ctrl_info *ctrl_info)
+{
+ pqi_ofa_free_host_buffer(ctrl_info);
+ ctrl_info->pqi_mode_enabled = true;
+ pqi_save_ctrl_mode(ctrl_info, PQI_MODE);
+ ctrl_info->controller_online = true;
+ pqi_ctrl_unblock_requests(ctrl_info);
+ pqi_start_heartbeat_timer(ctrl_info);
+ pqi_schedule_update_time_worker(ctrl_info);
+ pqi_clear_soft_reset_status(ctrl_info,
+ PQI_SOFT_RESET_ABORT);
+ pqi_scan_scsi_devices(ctrl_info);
+}
+
+static int pqi_ofa_alloc_mem(struct pqi_ctrl_info *ctrl_info,
+ u32 total_size, u32 chunk_size)
+{
+ u32 sg_count;
+ u32 size;
+ int i;
+ struct pqi_sg_descriptor *mem_descriptor = NULL;
+ struct device *dev;
+ struct pqi_ofa_memory *ofap;
+
+ dev = &ctrl_info->pci_dev->dev;
+
+ sg_count = (total_size + chunk_size - 1);
+ sg_count /= chunk_size;
+
+ ofap = ctrl_info->pqi_ofa_mem_virt_addr;
+
+ if (sg_count*chunk_size < total_size)
+ goto out;
+
+ ctrl_info->pqi_ofa_chunk_virt_addr =
+ kcalloc(sg_count, sizeof(void *), GFP_KERNEL);
+ if (!ctrl_info->pqi_ofa_chunk_virt_addr)
+ goto out;
+
+ for (size = 0, i = 0; size < total_size; size += chunk_size, i++) {
+ dma_addr_t dma_handle;
+
+ ctrl_info->pqi_ofa_chunk_virt_addr[i] =
+ dma_zalloc_coherent(dev, chunk_size, &dma_handle,
+ GFP_KERNEL);
+
+ if (!ctrl_info->pqi_ofa_chunk_virt_addr[i])
+ break;
+
+ mem_descriptor = &ofap->sg_descriptor[i];
+ put_unaligned_le64 ((u64) dma_handle, &mem_descriptor->address);
+ put_unaligned_le32 (chunk_size, &mem_descriptor->length);
+ }
+
+ if (!size || size < total_size)
+ goto out_free_chunks;
+
+ put_unaligned_le32(CISS_SG_LAST, &mem_descriptor->flags);
+ put_unaligned_le16(sg_count, &ofap->num_memory_descriptors);
+ put_unaligned_le32(size, &ofap->bytes_allocated);
+
+ return 0;
+
+out_free_chunks:
+ while (--i >= 0) {
+ mem_descriptor = &ofap->sg_descriptor[i];
+ dma_free_coherent(dev, chunk_size,
+ ctrl_info->pqi_ofa_chunk_virt_addr[i],
+ get_unaligned_le64(&mem_descriptor->address));
+ }
+ kfree(ctrl_info->pqi_ofa_chunk_virt_addr);
+
+out:
+ put_unaligned_le32 (0, &ofap->bytes_allocated);
+ return -ENOMEM;
+}
+
+static int pqi_ofa_alloc_host_buffer(struct pqi_ctrl_info *ctrl_info)
+{
+ u32 total_size;
+ u32 min_chunk_size;
+ u32 chunk_sz;
+
+ total_size = le32_to_cpu(
+ ctrl_info->pqi_ofa_mem_virt_addr->bytes_allocated);
+ min_chunk_size = total_size / PQI_OFA_MAX_SG_DESCRIPTORS;
+
+ for (chunk_sz = total_size; chunk_sz >= min_chunk_size; chunk_sz /= 2)
+ if (!pqi_ofa_alloc_mem(ctrl_info, total_size, chunk_sz))
+ return 0;
+
+ return -ENOMEM;
+}
+
+static void pqi_ofa_setup_host_buffer(struct pqi_ctrl_info *ctrl_info,
+ u32 bytes_requested)
+{
+ struct pqi_ofa_memory *pqi_ofa_memory;
+ struct device *dev;
+
+ dev = &ctrl_info->pci_dev->dev;
+ pqi_ofa_memory = dma_zalloc_coherent(dev,
+ PQI_OFA_MEMORY_DESCRIPTOR_LENGTH,
+ &ctrl_info->pqi_ofa_mem_dma_handle,
+ GFP_KERNEL);
+
+ if (!pqi_ofa_memory)
+ return;
+
+ put_unaligned_le16(PQI_OFA_VERSION, &pqi_ofa_memory->version);
+ memcpy(&pqi_ofa_memory->signature, PQI_OFA_SIGNATURE,
+ sizeof(pqi_ofa_memory->signature));
+ pqi_ofa_memory->bytes_allocated = cpu_to_le32(bytes_requested);
+
+ ctrl_info->pqi_ofa_mem_virt_addr = pqi_ofa_memory;
+
+ if (pqi_ofa_alloc_host_buffer(ctrl_info) < 0) {
+ dev_err(dev, "Failed to allocate host buffer of size = %u",
+ bytes_requested);
+ }
+}
+
+static void pqi_ofa_free_host_buffer(struct pqi_ctrl_info *ctrl_info)
+{
+ int i;
+ struct pqi_sg_descriptor *mem_descriptor;
+ struct pqi_ofa_memory *ofap;
+
+ ofap = ctrl_info->pqi_ofa_mem_virt_addr;
+
+ if (!ofap)
+ return;
+
+ if (!ofap->bytes_allocated)
+ goto out;
+
+ mem_descriptor = ofap->sg_descriptor;
+
+ for (i = 0; i < get_unaligned_le16(&ofap->num_memory_descriptors);
+ i++) {
+ dma_free_coherent(&ctrl_info->pci_dev->dev,
+ get_unaligned_le32(&mem_descriptor[i].length),
+ ctrl_info->pqi_ofa_chunk_virt_addr[i],
+ get_unaligned_le64(&mem_descriptor[i].address));
+ }
+ kfree(ctrl_info->pqi_ofa_chunk_virt_addr);
+
+out:
+ dma_free_coherent(&ctrl_info->pci_dev->dev,
+ PQI_OFA_MEMORY_DESCRIPTOR_LENGTH, ofap,
+ ctrl_info->pqi_ofa_mem_dma_handle);
+ ctrl_info->pqi_ofa_mem_virt_addr = NULL;
+}
+
+static int pqi_ofa_host_memory_update(struct pqi_ctrl_info *ctrl_info)
+{
+ struct pqi_vendor_general_request request;
+ size_t size;
+ struct pqi_ofa_memory *ofap;
+
+ memset(&request, 0, sizeof(request));
+
+ ofap = ctrl_info->pqi_ofa_mem_virt_addr;
+
+ request.header.iu_type = PQI_REQUEST_IU_VENDOR_GENERAL;
+ put_unaligned_le16(sizeof(request) - PQI_REQUEST_HEADER_LENGTH,
+ &request.header.iu_length);
+ put_unaligned_le16(PQI_VENDOR_GENERAL_HOST_MEMORY_UPDATE,
+ &request.function_code);
+
+ if (ofap) {
+ size = offsetof(struct pqi_ofa_memory, sg_descriptor) +
+ get_unaligned_le16(&ofap->num_memory_descriptors) *
+ sizeof(struct pqi_sg_descriptor);
+
+ put_unaligned_le64((u64)ctrl_info->pqi_ofa_mem_dma_handle,
+ &request.data.ofa_memory_allocation.buffer_address);
+ put_unaligned_le32(size,
+ &request.data.ofa_memory_allocation.buffer_length);
+
+ }
+
+ return pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
+ 0, NULL, NO_TIMEOUT);
+}
+
+#define PQI_POST_RESET_DELAY_B4_MSGU_READY 5000
+
+static int pqi_ofa_ctrl_restart(struct pqi_ctrl_info *ctrl_info)
+{
+ msleep(PQI_POST_RESET_DELAY_B4_MSGU_READY);
+ return pqi_ctrl_init_resume(ctrl_info);
+}
+
static void pqi_perform_lockup_action(void)
{
switch (pqi_lockup_action) {
@@ -6614,7 +7738,7 @@ static int pqi_pci_probe(struct pci_dev *pci_dev,
const struct pci_device_id *id)
{
int rc;
- int node;
+ int node, cp_node;
struct pqi_ctrl_info *ctrl_info;
pqi_print_ctrl_info(pci_dev, id);
@@ -6632,8 +7756,12 @@ static int pqi_pci_probe(struct pci_dev *pci_dev,
"controller device ID matched using wildcards\n");
node = dev_to_node(&pci_dev->dev);
- if (node == NUMA_NO_NODE)
- set_dev_node(&pci_dev->dev, 0);
+ if (node == NUMA_NO_NODE) {
+ cp_node = cpu_to_node(0);
+ if (cp_node == NUMA_NO_NODE)
+ cp_node = 0;
+ set_dev_node(&pci_dev->dev, cp_node);
+ }
ctrl_info = pqi_alloc_ctrl_info(node);
if (!ctrl_info) {
@@ -6668,6 +7796,8 @@ static void pqi_pci_remove(struct pci_dev *pci_dev)
if (!ctrl_info)
return;
+ ctrl_info->in_shutdown = true;
+
pqi_remove_ctrl(ctrl_info);
}
@@ -6685,6 +7815,7 @@ static void pqi_shutdown(struct pci_dev *pci_dev)
* storage.
*/
rc = pqi_flush_cache(ctrl_info, SHUTDOWN);
+ pqi_free_interrupts(ctrl_info);
pqi_reset(ctrl_info);
if (rc == 0)
return;
@@ -6729,11 +7860,12 @@ static __maybe_unused int pqi_suspend(struct pci_dev *pci_dev, pm_message_t stat
pqi_cancel_rescan_worker(ctrl_info);
pqi_wait_until_scan_finished(ctrl_info);
pqi_wait_until_lun_reset_finished(ctrl_info);
+ pqi_wait_until_ofa_finished(ctrl_info);
pqi_flush_cache(ctrl_info, SUSPEND);
pqi_ctrl_block_requests(ctrl_info);
pqi_ctrl_wait_until_quiesced(ctrl_info);
pqi_wait_until_inbound_queues_empty(ctrl_info);
- pqi_ctrl_wait_for_pending_io(ctrl_info);
+ pqi_ctrl_wait_for_pending_io(ctrl_info, NO_TIMEOUT);
pqi_stop_heartbeat_timer(ctrl_info);
if (state.event == PM_EVENT_FREEZE)
@@ -6811,6 +7943,22 @@ static const struct pci_device_id pqi_pci_id_table[] = {
},
{
PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x193d, 0x1104)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x193d, 0x1105)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x193d, 0x1106)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x193d, 0x1107)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
0x193d, 0x8460)
},
{
@@ -6819,6 +7967,14 @@ static const struct pci_device_id pqi_pci_id_table[] = {
},
{
PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x193d, 0xc460)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x193d, 0xc461)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
0x193d, 0xf460)
},
{
@@ -6855,6 +8011,30 @@ static const struct pci_device_id pqi_pci_id_table[] = {
},
{
PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x19e5, 0xd227)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x19e5, 0xd228)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x19e5, 0xd229)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x19e5, 0xd22a)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x19e5, 0xd22b)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+ 0x19e5, 0xd22c)
+ },
+ {
+ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
PCI_VENDOR_ID_ADAPTEC2, 0x0110)
},
{
diff --git a/drivers/scsi/smartpqi/smartpqi_sas_transport.c b/drivers/scsi/smartpqi/smartpqi_sas_transport.c
index b209a35e482e..5cca1b9ef1f1 100644
--- a/drivers/scsi/smartpqi/smartpqi_sas_transport.c
+++ b/drivers/scsi/smartpqi/smartpqi_sas_transport.c
@@ -1,25 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* driver for Microsemi PQI-based storage controllers
- * Copyright (c) 2016-2017 Microsemi Corporation
+ * Copyright (c) 2019 Microchip Technology Inc. and its subsidiaries
+ * Copyright (c) 2016-2018 Microsemi Corporation
* Copyright (c) 2016 PMC-Sierra, Inc.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more details.
- *
- * Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
+ * Questions/Comments/Bugfixes to storagedev@microchip.com
*
*/
#include <linux/kernel.h>
+#include <linux/bsg-lib.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_transport_sas.h>
+#include <asm/unaligned.h>
#include "smartpqi.h"
static struct pqi_sas_phy *pqi_alloc_sas_phy(struct pqi_sas_port *pqi_sas_port)
@@ -97,14 +92,32 @@ static int pqi_sas_port_add_rphy(struct pqi_sas_port *pqi_sas_port,
identify = &rphy->identify;
identify->sas_address = pqi_sas_port->sas_address;
- identify->initiator_port_protocols = SAS_PROTOCOL_STP;
- identify->target_port_protocols = SAS_PROTOCOL_STP;
+
+ if (pqi_sas_port->device &&
+ pqi_sas_port->device->is_expander_smp_device) {
+ identify->initiator_port_protocols = SAS_PROTOCOL_SMP;
+ identify->target_port_protocols = SAS_PROTOCOL_SMP;
+ } else {
+ identify->initiator_port_protocols = SAS_PROTOCOL_STP;
+ identify->target_port_protocols = SAS_PROTOCOL_STP;
+ }
return sas_rphy_add(rphy);
}
+static struct sas_rphy *pqi_sas_rphy_alloc(struct pqi_sas_port *pqi_sas_port)
+{
+ if (pqi_sas_port->device &&
+ pqi_sas_port->device->is_expander_smp_device)
+ return sas_expander_alloc(pqi_sas_port->port,
+ SAS_FANOUT_EXPANDER_DEVICE);
+
+ return sas_end_device_alloc(pqi_sas_port->port);
+}
+
static struct pqi_sas_port *pqi_alloc_sas_port(
- struct pqi_sas_node *pqi_sas_node, u64 sas_address)
+ struct pqi_sas_node *pqi_sas_node, u64 sas_address,
+ struct pqi_scsi_dev *device)
{
int rc;
struct pqi_sas_port *pqi_sas_port;
@@ -127,6 +140,7 @@ static struct pqi_sas_port *pqi_alloc_sas_port(
pqi_sas_port->port = port;
pqi_sas_port->sas_address = sas_address;
+ pqi_sas_port->device = device;
list_add_tail(&pqi_sas_port->port_list_entry,
&pqi_sas_node->port_list_head);
@@ -146,7 +160,7 @@ static void pqi_free_sas_port(struct pqi_sas_port *pqi_sas_port)
struct pqi_sas_phy *next;
list_for_each_entry_safe(pqi_sas_phy, next,
- &pqi_sas_port->phy_list_head, phy_list_entry)
+ &pqi_sas_port->phy_list_head, phy_list_entry)
pqi_free_sas_phy(pqi_sas_phy);
sas_port_delete(pqi_sas_port->port);
@@ -176,7 +190,7 @@ static void pqi_free_sas_node(struct pqi_sas_node *pqi_sas_node)
return;
list_for_each_entry_safe(pqi_sas_port, next,
- &pqi_sas_node->port_list_head, port_list_entry)
+ &pqi_sas_node->port_list_head, port_list_entry)
pqi_free_sas_port(pqi_sas_port);
kfree(pqi_sas_node);
@@ -206,13 +220,14 @@ int pqi_add_sas_host(struct Scsi_Host *shost, struct pqi_ctrl_info *ctrl_info)
struct pqi_sas_port *pqi_sas_port;
struct pqi_sas_phy *pqi_sas_phy;
- parent_dev = &shost->shost_gendev;
+ parent_dev = &shost->shost_dev;
pqi_sas_node = pqi_alloc_sas_node(parent_dev);
if (!pqi_sas_node)
return -ENOMEM;
- pqi_sas_port = pqi_alloc_sas_port(pqi_sas_node, ctrl_info->sas_address);
+ pqi_sas_port = pqi_alloc_sas_port(pqi_sas_node,
+ ctrl_info->sas_address, NULL);
if (!pqi_sas_port) {
rc = -ENODEV;
goto free_sas_node;
@@ -254,11 +269,12 @@ int pqi_add_sas_device(struct pqi_sas_node *pqi_sas_node,
struct pqi_sas_port *pqi_sas_port;
struct sas_rphy *rphy;
- pqi_sas_port = pqi_alloc_sas_port(pqi_sas_node, device->sas_address);
+ pqi_sas_port = pqi_alloc_sas_port(pqi_sas_node,
+ device->sas_address, device);
if (!pqi_sas_port)
return -ENOMEM;
- rphy = sas_end_device_alloc(pqi_sas_port->port);
+ rphy = pqi_sas_rphy_alloc(pqi_sas_port);
if (!rphy) {
rc = -ENODEV;
goto free_sas_port;
@@ -329,6 +345,128 @@ static int pqi_sas_phy_speed(struct sas_phy *phy,
return -EINVAL;
}
+#define CSMI_IOCTL_TIMEOUT 60
+#define SMP_CRC_FIELD_LENGTH 4
+
+static struct bmic_csmi_smp_passthru_buffer *
+pqi_build_csmi_smp_passthru_buffer(struct sas_rphy *rphy,
+ struct bsg_job *job)
+{
+ struct bmic_csmi_smp_passthru_buffer *smp_buf;
+ struct bmic_csmi_ioctl_header *ioctl_header;
+ struct bmic_csmi_smp_passthru *parameters;
+ u32 req_size;
+ u32 resp_size;
+
+ smp_buf = kzalloc(sizeof(*smp_buf), GFP_KERNEL);
+ if (!smp_buf)
+ return NULL;
+
+ req_size = job->request_payload.payload_len;
+ resp_size = job->reply_payload.payload_len;
+
+ ioctl_header = &smp_buf->ioctl_header;
+ put_unaligned_le32(sizeof(smp_buf->ioctl_header),
+ &ioctl_header->header_length);
+ put_unaligned_le32(CSMI_IOCTL_TIMEOUT, &ioctl_header->timeout);
+ put_unaligned_le32(CSMI_CC_SAS_SMP_PASSTHRU,
+ &ioctl_header->control_code);
+ put_unaligned_le32(sizeof(smp_buf->parameters), &ioctl_header->length);
+
+ parameters = &smp_buf->parameters;
+ parameters->phy_identifier = rphy->identify.phy_identifier;
+ parameters->port_identifier = 0;
+ parameters->connection_rate = 0;
+ put_unaligned_be64(rphy->identify.sas_address,
+ &parameters->destination_sas_address);
+
+ if (req_size > SMP_CRC_FIELD_LENGTH)
+ req_size -= SMP_CRC_FIELD_LENGTH;
+
+ put_unaligned_le32(req_size, &parameters->request_length);
+
+ put_unaligned_le32(resp_size, &parameters->response_length);
+
+ sg_copy_to_buffer(job->request_payload.sg_list,
+ job->reply_payload.sg_cnt, &parameters->request,
+ req_size);
+
+ return smp_buf;
+}
+
+static unsigned int pqi_build_sas_smp_handler_reply(
+ struct bmic_csmi_smp_passthru_buffer *smp_buf, struct bsg_job *job,
+ struct pqi_raid_error_info *error_info)
+{
+ sg_copy_from_buffer(job->reply_payload.sg_list,
+ job->reply_payload.sg_cnt, &smp_buf->parameters.response,
+ le32_to_cpu(smp_buf->parameters.response_length));
+
+ job->reply_len = le16_to_cpu(error_info->sense_data_length);
+ memcpy(job->reply, error_info->data,
+ le16_to_cpu(error_info->sense_data_length));
+
+ return job->reply_payload.payload_len -
+ get_unaligned_le32(&error_info->data_in_transferred);
+}
+
+void pqi_sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
+ struct sas_rphy *rphy)
+{
+ int rc;
+ struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost);
+ struct bmic_csmi_smp_passthru_buffer *smp_buf;
+ struct pqi_raid_error_info error_info;
+ unsigned int reslen = 0;
+
+ pqi_ctrl_busy(ctrl_info);
+
+ if (job->reply_payload.payload_len == 0) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ if (!rphy) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (rphy->identify.device_type != SAS_FANOUT_EXPANDER_DEVICE) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (job->request_payload.sg_cnt > 1 || job->reply_payload.sg_cnt > 1) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (pqi_ctrl_offline(ctrl_info)) {
+ rc = -ENXIO;
+ goto out;
+ }
+
+ if (pqi_ctrl_blocked(ctrl_info)) {
+ rc = -EBUSY;
+ goto out;
+ }
+
+ smp_buf = pqi_build_csmi_smp_passthru_buffer(rphy, job);
+ if (!smp_buf) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ rc = pqi_csmi_smp_passthru(ctrl_info, smp_buf, sizeof(*smp_buf),
+ &error_info);
+ if (rc)
+ goto out;
+
+ reslen = pqi_build_sas_smp_handler_reply(smp_buf, job, &error_info);
+out:
+ bsg_job_done(job, rc, reslen);
+ pqi_ctrl_unbusy(ctrl_info);
+}
struct sas_function_template pqi_sas_transport_functions = {
.get_linkerrors = pqi_sas_get_linkerrors,
.get_enclosure_identifier = pqi_sas_get_enclosure_identifier,
@@ -338,4 +476,5 @@ struct sas_function_template pqi_sas_transport_functions = {
.phy_setup = pqi_sas_phy_setup,
.phy_release = pqi_sas_phy_release,
.set_phy_speed = pqi_sas_phy_speed,
+ .smp_handler = pqi_sas_smp_handler,
};
diff --git a/drivers/scsi/smartpqi/smartpqi_sis.c b/drivers/scsi/smartpqi/smartpqi_sis.c
index 5141bd4c9f06..f0d6e88ba2c1 100644
--- a/drivers/scsi/smartpqi/smartpqi_sis.c
+++ b/drivers/scsi/smartpqi/smartpqi_sis.c
@@ -1,18 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* driver for Microsemi PQI-based storage controllers
- * Copyright (c) 2016-2017 Microsemi Corporation
+ * Copyright (c) 2019 Microchip Technology Inc. and its subsidiaries
+ * Copyright (c) 2016-2018 Microsemi Corporation
* Copyright (c) 2016 PMC-Sierra, Inc.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more details.
- *
- * Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
+ * Questions/Comments/Bugfixes to storagedev@microchip.com
*
*/
@@ -34,6 +27,7 @@
#define SIS_REENABLE_SIS_MODE 0x1
#define SIS_ENABLE_MSIX 0x40
#define SIS_ENABLE_INTX 0x80
+#define SIS_SOFT_RESET 0x100
#define SIS_CMD_READY 0x200
#define SIS_TRIGGER_SHUTDOWN 0x800000
#define SIS_PQI_RESET_QUIESCE 0x1000000
@@ -59,7 +53,7 @@
#define SIS_CTRL_KERNEL_UP 0x80
#define SIS_CTRL_KERNEL_PANIC 0x100
-#define SIS_CTRL_READY_TIMEOUT_SECS 30
+#define SIS_CTRL_READY_TIMEOUT_SECS 180
#define SIS_CTRL_READY_RESUME_TIMEOUT_SECS 90
#define SIS_CTRL_READY_POLL_INTERVAL_MSECS 10
@@ -90,7 +84,7 @@ static int sis_wait_for_ctrl_ready_with_timeout(struct pqi_ctrl_info *ctrl_info,
unsigned long timeout;
u32 status;
- timeout = (timeout_secs * HZ) + jiffies;
+ timeout = (timeout_secs * PQI_HZ) + jiffies;
while (1) {
status = readl(&ctrl_info->registers->sis_firmware_status);
@@ -202,7 +196,7 @@ static int sis_send_sync_cmd(struct pqi_ctrl_info *ctrl_info,
* the top of the loop in order to give the controller time to start
* processing the command before we start polling.
*/
- timeout = (SIS_CMD_COMPLETE_TIMEOUT_SECS * HZ) + jiffies;
+ timeout = (SIS_CMD_COMPLETE_TIMEOUT_SECS * PQI_HZ) + jiffies;
while (1) {
msleep(SIS_CMD_COMPLETE_POLL_INTERVAL_MSECS);
doorbell = readl(&registers->sis_ctrl_to_host_doorbell);
@@ -316,9 +310,9 @@ int sis_init_base_struct_addr(struct pqi_ctrl_info *ctrl_info)
put_unaligned_le32(ctrl_info->max_io_slots,
&base_struct->error_buffer_num_elements);
- bus_address = pci_map_single(ctrl_info->pci_dev, base_struct,
- sizeof(*base_struct), PCI_DMA_TODEVICE);
- if (pci_dma_mapping_error(ctrl_info->pci_dev, bus_address)) {
+ bus_address = dma_map_single(&ctrl_info->pci_dev->dev, base_struct,
+ sizeof(*base_struct), DMA_TO_DEVICE);
+ if (dma_mapping_error(&ctrl_info->pci_dev->dev, bus_address)) {
rc = -ENOMEM;
goto out;
}
@@ -331,9 +325,8 @@ int sis_init_base_struct_addr(struct pqi_ctrl_info *ctrl_info)
rc = sis_send_sync_cmd(ctrl_info, SIS_CMD_INIT_BASE_STRUCT_ADDRESS,
&params);
- pci_unmap_single(ctrl_info->pci_dev, bus_address, sizeof(*base_struct),
- PCI_DMA_TODEVICE);
-
+ dma_unmap_single(&ctrl_info->pci_dev->dev, bus_address,
+ sizeof(*base_struct), DMA_TO_DEVICE);
out:
kfree(base_struct_unaligned);
@@ -349,7 +342,7 @@ static int sis_wait_for_doorbell_bit_to_clear(
u32 doorbell_register;
unsigned long timeout;
- timeout = (SIS_DOORBELL_BIT_CLEAR_TIMEOUT_SECS * HZ) + jiffies;
+ timeout = (SIS_DOORBELL_BIT_CLEAR_TIMEOUT_SECS * PQI_HZ) + jiffies;
while (1) {
doorbell_register =
@@ -421,6 +414,12 @@ u32 sis_read_driver_scratch(struct pqi_ctrl_info *ctrl_info)
return readl(&ctrl_info->registers->sis_driver_scratch);
}
+void sis_soft_reset(struct pqi_ctrl_info *ctrl_info)
+{
+ writel(SIS_SOFT_RESET,
+ &ctrl_info->registers->sis_host_to_ctrl_doorbell);
+}
+
static void __attribute__((unused)) verify_structures(void)
{
BUILD_BUG_ON(offsetof(struct sis_base_struct,
diff --git a/drivers/scsi/smartpqi/smartpqi_sis.h b/drivers/scsi/smartpqi/smartpqi_sis.h
index 2bf889dbf5ab..86b0e484d921 100644
--- a/drivers/scsi/smartpqi/smartpqi_sis.h
+++ b/drivers/scsi/smartpqi/smartpqi_sis.h
@@ -1,18 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* driver for Microsemi PQI-based storage controllers
- * Copyright (c) 2016-2017 Microsemi Corporation
+ * Copyright (c) 2019 Microchip Technology Inc. and its subsidiaries
+ * Copyright (c) 2016-2018 Microsemi Corporation
* Copyright (c) 2016 PMC-Sierra, Inc.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more details.
- *
- * Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
+ * Questions/Comments/Bugfixes to storagedev@microchip.com
*
*/
@@ -33,5 +26,6 @@ int sis_pqi_reset_quiesce(struct pqi_ctrl_info *ctrl_info);
int sis_reenable_sis_mode(struct pqi_ctrl_info *ctrl_info);
void sis_write_driver_scratch(struct pqi_ctrl_info *ctrl_info, u32 value);
u32 sis_read_driver_scratch(struct pqi_ctrl_info *ctrl_info);
+void sis_soft_reset(struct pqi_ctrl_info *ctrl_info);
#endif /* _SMARTPQI_SIS_H */
diff --git a/drivers/soc/fsl/qe/gpio.c b/drivers/soc/fsl/qe/gpio.c
index 0aaf429f31d5..b5a7107a9c0a 100644
--- a/drivers/soc/fsl/qe/gpio.c
+++ b/drivers/soc/fsl/qe/gpio.c
@@ -152,8 +152,10 @@ struct qe_pin *qe_pin_request(struct device_node *np, int index)
if (err < 0)
goto err0;
gc = gpio_to_chip(err);
- if (WARN_ON(!gc))
+ if (WARN_ON(!gc)) {
+ err = -ENODEV;
goto err0;
+ }
if (!of_device_is_compatible(gc->of_node, "fsl,mpc8323-qe-pario-bank")) {
pr_debug("%s: tried to get a non-qe pin\n", __func__);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index be29489dd247..373a7a79b53e 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -569,7 +569,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
load = 0;
total_load += load;
- if (trace_thermal_power_cpu_limit_enabled() && load_cpu)
+ if (load_cpu)
load_cpu[i] = load;
i++;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 923e2822109f..d7692eb3d185 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -143,9 +143,6 @@ static void uart_start(struct tty_struct *tty)
struct uart_port *port;
unsigned long flags;
- if (!state)
- return;
-
port = uart_port_lock(state, flags);
__uart_start(tty);
uart_port_unlock(port, flags);
@@ -1704,6 +1701,16 @@ static void uart_dtr_rts(struct tty_port *port, int onoff)
uart_port_deref(uport);
}
+static int uart_install(struct tty_driver *driver, struct tty_struct *tty)
+{
+ struct uart_driver *drv = driver->driver_state;
+ struct uart_state *state = drv->state + tty->index;
+
+ tty->driver_data = state;
+
+ return tty_standard_install(driver, tty);
+}
+
/*
* Calls to uart_open are serialised by the tty_lock in
* drivers/tty/tty_io.c:tty_open()
@@ -1716,11 +1723,8 @@ static void uart_dtr_rts(struct tty_port *port, int onoff)
*/
static int uart_open(struct tty_struct *tty, struct file *filp)
{
- struct uart_driver *drv = tty->driver->driver_state;
- int retval, line = tty->index;
- struct uart_state *state = drv->state + line;
-
- tty->driver_data = state;
+ struct uart_state *state = tty->driver_data;
+ int retval;
retval = tty_port_open(&state->port, tty, filp);
if (retval > 0)
@@ -2406,9 +2410,6 @@ static void uart_poll_put_char(struct tty_driver *driver, int line, char ch)
struct uart_state *state = drv->state + line;
struct uart_port *port;
- if (!state)
- return;
-
port = uart_port_ref(state);
if (!port)
return;
@@ -2421,6 +2422,7 @@ static void uart_poll_put_char(struct tty_driver *driver, int line, char ch)
#endif
static const struct tty_operations uart_ops = {
+ .install = uart_install,
.open = uart_open,
.close = uart_close,
.write = uart_write,
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 82ed578dd98e..c8fba05d8b5b 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -2435,8 +2435,8 @@ rescan_last_byte:
}
con_flush(vc, draw_from, draw_to, &draw_x);
console_conditional_schedule();
- console_unlock();
notify_update(vc);
+ console_unlock();
return n;
}
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index c202930086ed..f60f4c6aa416 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -60,6 +60,8 @@ enum {
Opt_cache_loose, Opt_fscache, Opt_mmap,
/* Access options */
Opt_access, Opt_posixacl,
+ /* Lock timeout option */
+ Opt_locktimeout,
/* Error token */
Opt_err
};
@@ -79,6 +81,7 @@ static const match_table_t tokens = {
{Opt_cachetag, "cachetag=%s"},
{Opt_access, "access=%s"},
{Opt_posixacl, "posixacl"},
+ {Opt_locktimeout, "locktimeout=%u"},
{Opt_err, NULL}
};
@@ -127,6 +130,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
#ifdef CONFIG_9P_FSCACHE
v9ses->cachetag = NULL;
#endif
+ v9ses->session_lock_timeout = P9_LOCK_TIMEOUT;
if (!opts)
return 0;
@@ -299,6 +303,23 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
#endif
break;
+ case Opt_locktimeout:
+ r = match_int(&args[0], &option);
+ if (r < 0) {
+ p9_debug(P9_DEBUG_ERROR,
+ "integer field, but no integer?\n");
+ ret = r;
+ continue;
+ }
+ if (option < 1) {
+ p9_debug(P9_DEBUG_ERROR,
+ "locktimeout must be a greater than zero integer.\n");
+ ret = -EINVAL;
+ continue;
+ }
+ v9ses->session_lock_timeout = (long)option * HZ;
+ break;
+
default:
continue;
}
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 76eaf49abd3a..8070f9fde4b5 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -115,6 +115,7 @@ struct v9fs_session_info {
struct p9_client *clnt; /* 9p client */
struct list_head slist; /* list of sessions registered with v9fs */
struct rw_semaphore rename_sem;
+ long session_lock_timeout; /* retry interval for blocking locks */
};
/* cache_validity flags */
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 65f2747b3c8e..b4bb84cef4a7 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -154,6 +154,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
uint8_t status = P9_LOCK_ERROR;
int res = 0;
unsigned char fl_type;
+ struct v9fs_session_info *v9ses;
fid = filp->private_data;
BUG_ON(fid == NULL);
@@ -189,6 +190,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
if (IS_SETLKW(cmd))
flock.flags = P9_LOCK_FLAGS_BLOCK;
+ v9ses = v9fs_inode2v9ses(file_inode(filp));
+
/*
* if its a blocked request and we get P9_LOCK_BLOCKED as the status
* for lock request, keep on trying
@@ -202,7 +205,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
break;
if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
break;
- if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0)
+ if (schedule_timeout_interruptible(v9ses->session_lock_timeout)
+ != 0)
break;
/*
* p9_client_lock_dotl overwrites flock.client_id with the
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9693bcdc86ee..295b378f00c2 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -306,10 +306,10 @@ static void blkdev_bio_end_io(struct bio *bio)
struct blkdev_dio *dio = bio->bi_private;
bool should_dirty = dio->should_dirty;
- if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) {
- if (bio->bi_status && !dio->bio.bi_status)
- dio->bio.bi_status = bio->bi_status;
- } else {
+ if (bio->bi_status && !dio->bio.bi_status)
+ dio->bio.bi_status = bio->bi_status;
+
+ if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
if (!dio->is_sync) {
struct kiocb *iocb = dio->iocb;
ssize_t ret;
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7f895b673c4f..19e4eecd67ce 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -160,12 +160,6 @@ struct btrfs_inode {
u64 last_unlink_trans;
/*
- * Track the transaction id of the last transaction used to create a
- * hard link for the inode. This is used by the log tree (fsync).
- */
- u64 last_link_trans;
-
- /*
* Number of bytes outstanding that are going to need csums. This is
* used in ENOSPC accounting.
*/
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e8f02a669d20..e84857d2c9a7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3669,21 +3669,6 @@ cache_index:
* inode is not a directory, logging its parent unnecessarily.
*/
BTRFS_I(inode)->last_unlink_trans = BTRFS_I(inode)->last_trans;
- /*
- * Similar reasoning for last_link_trans, needs to be set otherwise
- * for a case like the following:
- *
- * mkdir A
- * touch foo
- * ln foo A/bar
- * echo 2 > /proc/sys/vm/drop_caches
- * fsync foo
- * <power failure>
- *
- * Would result in link bar and directory A not existing after the power
- * failure.
- */
- BTRFS_I(inode)->last_link_trans = BTRFS_I(inode)->last_trans;
path->slots[0]++;
if (inode->i_nlink != 1 ||
@@ -6495,7 +6480,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
if (err)
goto fail;
}
- BTRFS_I(inode)->last_link_trans = trans->transid;
d_instantiate(dentry, inode);
ret = btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent,
true, NULL);
@@ -9205,7 +9189,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
ei->index_cnt = (u64)-1;
ei->dir_index = 0;
ei->last_unlink_trans = 0;
- ei->last_link_trans = 0;
ei->last_log_commit = 0;
ei->delayed_iput_count = 0;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 465ed3fd6d4a..d37c4f630e7e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -394,6 +394,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ /*
+ * If the fs is mounted with nologreplay, which requires it to be
+ * mounted in RO mode as well, we can not allow discard on free space
+ * inside block groups, because log trees refer to extents that are not
+ * pinned in a block group's free space cache (pinning the extents is
+ * precisely the first phase of replaying a log tree).
+ */
+ if (btrfs_test_opt(fs_info, NOLOGREPLAY))
+ return -EROFS;
+
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
dev_list) {
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index b1eba0274983..0cfad0b15c4e 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6574,6 +6574,38 @@ commit_trans:
return btrfs_commit_transaction(trans);
}
+/*
+ * Make sure any existing dellaloc is flushed for any root used by a send
+ * operation so that we do not miss any data and we do not race with writeback
+ * finishing and changing a tree while send is using the tree. This could
+ * happen if a subvolume is in RW mode, has delalloc, is turned to RO mode and
+ * a send operation then uses the subvolume.
+ * After flushing delalloc ensure_commit_roots_uptodate() must be called.
+ */
+static int flush_delalloc_roots(struct send_ctx *sctx)
+{
+ struct btrfs_root *root = sctx->parent_root;
+ int ret;
+ int i;
+
+ if (root) {
+ ret = btrfs_start_delalloc_inodes(root, 0);
+ if (ret)
+ return ret;
+ btrfs_wait_ordered_extents(root, -1, 0, U64_MAX);
+ }
+
+ for (i = 0; i < sctx->clone_roots_cnt; i++) {
+ root = sctx->clone_roots[i].root;
+ ret = btrfs_start_delalloc_inodes(root, 0);
+ if (ret)
+ return ret;
+ btrfs_wait_ordered_extents(root, -1, 0, U64_MAX);
+ }
+
+ return 0;
+}
+
static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
{
spin_lock(&root->root_item_lock);
@@ -6809,6 +6841,10 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
NULL);
sort_clone_roots = 1;
+ ret = flush_delalloc_roots(sctx);
+ if (ret)
+ goto out;
+
ret = ensure_commit_roots_uptodate(sctx);
if (ret)
goto out;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 27c47acde982..5c0fd8b848ec 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -6008,6 +6008,190 @@ out:
return ret;
}
+static int log_new_ancestors(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_log_ctx *ctx)
+{
+ struct btrfs_key found_key;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
+
+ while (true) {
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ const u64 last_committed = fs_info->last_trans_committed;
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ struct btrfs_key search_key;
+ struct inode *inode;
+ int ret = 0;
+
+ btrfs_release_path(path);
+
+ search_key.objectid = found_key.offset;
+ search_key.type = BTRFS_INODE_ITEM_KEY;
+ search_key.offset = 0;
+ inode = btrfs_iget(fs_info->sb, &search_key, root, NULL);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ if (BTRFS_I(inode)->generation > last_committed)
+ ret = btrfs_log_inode(trans, root, BTRFS_I(inode),
+ LOG_INODE_EXISTS,
+ 0, LLONG_MAX, ctx);
+ iput(inode);
+ if (ret)
+ return ret;
+
+ if (search_key.objectid == BTRFS_FIRST_FREE_OBJECTID)
+ break;
+
+ search_key.type = BTRFS_INODE_REF_KEY;
+ ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
+ if (ret < 0)
+ return ret;
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ return ret;
+ else if (ret > 0)
+ return -ENOENT;
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ }
+
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+ if (found_key.objectid != search_key.objectid ||
+ found_key.type != BTRFS_INODE_REF_KEY)
+ return -ENOENT;
+ }
+ return 0;
+}
+
+static int log_new_ancestors_fast(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct dentry *parent,
+ struct btrfs_log_ctx *ctx)
+{
+ struct btrfs_root *root = inode->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct dentry *old_parent = NULL;
+ struct super_block *sb = inode->vfs_inode.i_sb;
+ int ret = 0;
+
+ while (true) {
+ if (!parent || d_really_is_negative(parent) ||
+ sb != parent->d_sb)
+ break;
+
+ inode = BTRFS_I(d_inode(parent));
+ if (root != inode->root)
+ break;
+
+ if (inode->generation > fs_info->last_trans_committed) {
+ ret = btrfs_log_inode(trans, root, inode,
+ LOG_INODE_EXISTS, 0, LLONG_MAX, ctx);
+ if (ret)
+ break;
+ }
+ if (IS_ROOT(parent))
+ break;
+
+ parent = dget_parent(parent);
+ dput(old_parent);
+ old_parent = parent;
+ }
+ dput(old_parent);
+
+ return ret;
+}
+
+static int log_all_new_ancestors(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct dentry *parent,
+ struct btrfs_log_ctx *ctx)
+{
+ struct btrfs_root *root = inode->root;
+ const u64 ino = btrfs_ino(inode);
+ struct btrfs_path *path;
+ struct btrfs_key search_key;
+ int ret;
+
+ /*
+ * For a single hard link case, go through a fast path that does not
+ * need to iterate the fs/subvolume tree.
+ */
+ if (inode->vfs_inode.i_nlink < 2)
+ return log_new_ancestors_fast(trans, inode, parent, ctx);
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ search_key.objectid = ino;
+ search_key.type = BTRFS_INODE_REF_KEY;
+ search_key.offset = 0;
+again:
+ ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ if (ret == 0)
+ path->slots[0]++;
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ struct btrfs_key found_key;
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ else if (ret > 0)
+ break;
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+ if (found_key.objectid != ino ||
+ found_key.type > BTRFS_INODE_EXTREF_KEY)
+ break;
+
+ /*
+ * Don't deal with extended references because they are rare
+ * cases and too complex to deal with (we would need to keep
+ * track of which subitem we are processing for each item in
+ * this loop, etc). So just return some error to fallback to
+ * a transaction commit.
+ */
+ if (found_key.type == BTRFS_INODE_EXTREF_KEY) {
+ ret = -EMLINK;
+ goto out;
+ }
+
+ /*
+ * Logging ancestors needs to do more searches on the fs/subvol
+ * tree, so it releases the path as needed to avoid deadlocks.
+ * Keep track of the last inode ref key and resume from that key
+ * after logging all new ancestors for the current hard link.
+ */
+ memcpy(&search_key, &found_key, sizeof(search_key));
+
+ ret = log_new_ancestors(trans, root, path, ctx);
+ if (ret)
+ goto out;
+ btrfs_release_path(path);
+ goto again;
+ }
+ ret = 0;
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
/*
* helper function around btrfs_log_inode to make sure newly created
* parent directories also end up in the log. A minimal inode and backref
@@ -6026,11 +6210,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info = root->fs_info;
int inode_only = exists_only ? LOG_INODE_EXISTS : LOG_INODE_ALL;
struct super_block *sb;
- struct dentry *old_parent = NULL;
int ret = 0;
u64 last_committed = fs_info->last_trans_committed;
bool log_dentries = false;
- struct btrfs_inode *orig_inode = inode;
sb = inode->vfs_inode.i_sb;
@@ -6136,54 +6318,20 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
* and has a link count of 2.
*/
if (inode->last_unlink_trans > last_committed) {
- ret = btrfs_log_all_parents(trans, orig_inode, ctx);
+ ret = btrfs_log_all_parents(trans, inode, ctx);
if (ret)
goto end_trans;
}
- /*
- * If a new hard link was added to the inode in the current transaction
- * and its link count is now greater than 1, we need to fallback to a
- * transaction commit, otherwise we can end up not logging all its new
- * parents for all the hard links. Here just from the dentry used to
- * fsync, we can not visit the ancestor inodes for all the other hard
- * links to figure out if any is new, so we fallback to a transaction
- * commit (instead of adding a lot of complexity of scanning a btree,
- * since this scenario is not a common use case).
- */
- if (inode->vfs_inode.i_nlink > 1 &&
- inode->last_link_trans > last_committed) {
- ret = -EMLINK;
+ ret = log_all_new_ancestors(trans, inode, parent, ctx);
+ if (ret)
goto end_trans;
- }
-
- while (1) {
- if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
- break;
-
- inode = BTRFS_I(d_inode(parent));
- if (root != inode->root)
- break;
- if (inode->generation > last_committed) {
- ret = btrfs_log_inode(trans, root, inode,
- LOG_INODE_EXISTS, 0, LLONG_MAX, ctx);
- if (ret)
- goto end_trans;
- }
- if (IS_ROOT(parent))
- break;
-
- parent = dget_parent(parent);
- dput(old_parent);
- old_parent = parent;
- }
if (log_dentries)
- ret = log_new_dir_dentries(trans, root, orig_inode, ctx);
+ ret = log_new_dir_dentries(trans, root, inode, ctx);
else
ret = 0;
end_trans:
- dput(old_parent);
if (ret < 0) {
btrfs_set_log_full_commit(fs_info, trans);
ret = 1;
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 39843fa7e11b..920d350df37b 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1755,12 +1755,19 @@ int configfs_register_group(struct config_group *parent_group,
inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
ret = create_default_group(parent_group, group);
- if (!ret) {
- spin_lock(&configfs_dirent_lock);
- configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata);
- spin_unlock(&configfs_dirent_lock);
- }
+ if (ret)
+ goto err_out;
+
+ spin_lock(&configfs_dirent_lock);
+ configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata);
+ spin_unlock(&configfs_dirent_lock);
+ inode_unlock(d_inode(parent));
+ return 0;
+err_out:
inode_unlock(d_inode(parent));
+ mutex_lock(&subsys->su_mutex);
+ unlink_group(group);
+ mutex_unlock(&subsys->su_mutex);
return ret;
}
EXPORT_SYMBOL(configfs_register_group);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 055fbdd00390..703eadfe1725 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -167,19 +167,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root)
return 0;
}
-static void debugfs_evict_inode(struct inode *inode)
+static void debugfs_i_callback(struct rcu_head *head)
{
- truncate_inode_pages_final(&inode->i_data);
- clear_inode(inode);
+ struct inode *inode = container_of(head, struct inode, i_rcu);
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
+ free_inode_nonrcu(inode);
+}
+
+static void debugfs_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, debugfs_i_callback);
}
static const struct super_operations debugfs_super_operations = {
.statfs = simple_statfs,
.remount_fs = debugfs_remount,
.show_options = debugfs_show_options,
- .evict_inode = debugfs_evict_inode,
+ .destroy_inode = debugfs_destroy_inode,
};
static void debugfs_release_dentry(struct dentry *dentry)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 818ffb458be4..9f66b6db1c66 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1047,6 +1047,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
__le32 border;
ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */
int err = 0;
+ size_t ext_size = 0;
/* make decision: where to split? */
/* FIXME: now decision is simplest: at current extent */
@@ -1138,6 +1139,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
le16_add_cpu(&neh->eh_entries, m);
}
+ /* zero out unused area in the extent block */
+ ext_size = sizeof(struct ext4_extent_header) +
+ sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries);
+ memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size);
ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
@@ -1217,6 +1222,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
sizeof(struct ext4_extent_idx) * m);
le16_add_cpu(&neh->eh_entries, m);
}
+ /* zero out unused area in the extent block */
+ ext_size = sizeof(struct ext4_extent_header) +
+ (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries));
+ memset(bh->b_data + ext_size, 0,
+ inode->i_sb->s_blocksize - ext_size);
ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
@@ -1282,6 +1292,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
ext4_fsblk_t newblock, goal = 0;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
int err = 0;
+ size_t ext_size = 0;
/* Try to prepend new index to old one */
if (ext_depth(inode))
@@ -1307,9 +1318,11 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
goto out;
}
+ ext_size = sizeof(EXT4_I(inode)->i_data);
/* move top-level index/leaf into new block */
- memmove(bh->b_data, EXT4_I(inode)->i_data,
- sizeof(EXT4_I(inode)->i_data));
+ memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size);
+ /* zero out unused area in the extent block */
+ memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size);
/* set size of new block */
neh = ext_block_hdr(bh);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 3ed6f8d6d02d..31ab63421162 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -973,7 +973,7 @@ group_add_out:
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
- if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
+ if (!err && (o_group < EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 356b2707023e..5b59acc9a887 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3457,6 +3457,37 @@ int ext4_calculate_overhead(struct super_block *sb)
return 0;
}
+static void ext4_clamp_want_extra_isize(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+
+ /* determine the minimum size of new large inodes, if present */
+ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
+ sbi->s_want_extra_isize == 0) {
+ sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+ EXT4_GOOD_OLD_INODE_SIZE;
+ if (ext4_has_feature_extra_isize(sb)) {
+ if (sbi->s_want_extra_isize <
+ le16_to_cpu(es->s_want_extra_isize))
+ sbi->s_want_extra_isize =
+ le16_to_cpu(es->s_want_extra_isize);
+ if (sbi->s_want_extra_isize <
+ le16_to_cpu(es->s_min_extra_isize))
+ sbi->s_want_extra_isize =
+ le16_to_cpu(es->s_min_extra_isize);
+ }
+ }
+ /* Check if enough inode space is available */
+ if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
+ sbi->s_inode_size) {
+ sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+ EXT4_GOOD_OLD_INODE_SIZE;
+ ext4_msg(sb, KERN_INFO,
+ "required extra inode space not available");
+ }
+}
+
static void ext4_set_resv_clusters(struct super_block *sb)
{
ext4_fsblk_t resv_clusters;
@@ -4160,7 +4191,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"data=, fs mounted w/o journal");
goto failed_mount_wq;
}
- sbi->s_def_mount_opt &= EXT4_MOUNT_JOURNAL_CHECKSUM;
+ sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
clear_opt(sb, JOURNAL_CHECKSUM);
clear_opt(sb, DATA_FLAGS);
sbi->s_journal = NULL;
@@ -4290,30 +4321,7 @@ no_journal:
if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY))
sb->s_flags |= MS_RDONLY;
- /* determine the minimum size of new large inodes, if present */
- if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
- sbi->s_want_extra_isize == 0) {
- sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
- EXT4_GOOD_OLD_INODE_SIZE;
- if (ext4_has_feature_extra_isize(sb)) {
- if (sbi->s_want_extra_isize <
- le16_to_cpu(es->s_want_extra_isize))
- sbi->s_want_extra_isize =
- le16_to_cpu(es->s_want_extra_isize);
- if (sbi->s_want_extra_isize <
- le16_to_cpu(es->s_min_extra_isize))
- sbi->s_want_extra_isize =
- le16_to_cpu(es->s_min_extra_isize);
- }
- }
- /* Check if enough inode space is available */
- if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
- sbi->s_inode_size) {
- sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
- EXT4_GOOD_OLD_INODE_SIZE;
- ext4_msg(sb, KERN_INFO, "required extra inode space not"
- "available");
- }
+ ext4_clamp_want_extra_isize(sb);
ext4_set_resv_clusters(sb);
@@ -5115,6 +5123,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
+ ext4_clamp_want_extra_isize(sb);
+
if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
test_opt(sb, JOURNAL_CHECKSUM)) {
ext4_msg(sb, KERN_ERR, "changing journal_checksum "
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 9fc7119a1551..82d7b08c1e71 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -228,7 +228,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode)
case UFS_UID_44BSD:
return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid);
case UFS_UID_EFT:
- if (inode->ui_u1.oldids.ui_suid == 0xFFFF)
+ if (inode->ui_u1.oldids.ui_sgid == 0xFFFF)
return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid);
/* Fall through */
default:
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index eed8f5867c46..2291f4224e24 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -27,6 +27,7 @@
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_alloc.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
@@ -111,8 +112,7 @@ xfs_ag_resv_critical(
/* Critically low if less than 10% or max btree height remains. */
return XFS_TEST_ERROR(avail < orig / 10 || avail < XFS_BTREE_MAXLEVELS,
- pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL,
- XFS_RANDOM_AG_RESV_CRITICAL);
+ pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL);
}
/*
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 7b7ef0c56b47..c503501729ea 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -31,6 +31,7 @@
#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_cksum.h"
#include "xfs_trace.h"
@@ -623,7 +624,7 @@ const struct xfs_buf_ops xfs_agfl_buf_ops = {
/*
* Read in the allocation group free block array.
*/
-STATIC int /* error */
+int /* error */
xfs_alloc_read_agfl(
xfs_mount_t *mp, /* mount point structure */
xfs_trans_t *tp, /* transaction pointer */
@@ -2572,8 +2573,7 @@ xfs_agf_read_verify(
!xfs_buf_verify_cksum(bp, XFS_AGF_CRC_OFF))
xfs_buf_ioerror(bp, -EFSBADCRC);
else if (XFS_TEST_ERROR(!xfs_agf_verify(mp, bp), mp,
- XFS_ERRTAG_ALLOC_READ_AGF,
- XFS_RANDOM_ALLOC_READ_AGF))
+ XFS_ERRTAG_ALLOC_READ_AGF))
xfs_buf_ioerror(bp, -EFSCORRUPTED);
if (bp->b_error)
@@ -2961,8 +2961,7 @@ xfs_free_extent(
ASSERT(type != XFS_AG_RESV_AGFL);
if (XFS_TEST_ERROR(false, mp,
- XFS_ERRTAG_FREE_EXTENT,
- XFS_RANDOM_FREE_EXTENT))
+ XFS_ERRTAG_FREE_EXTENT))
return -EIO;
error = xfs_free_extent_fix_freelist(tp, agno, &agbp);
@@ -3044,3 +3043,52 @@ xfs_alloc_query_all(
query.fn = fn;
return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query);
}
+
+/* Find the size of the AG, in blocks. */
+xfs_agblock_t
+xfs_ag_block_count(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno)
+{
+ ASSERT(agno < mp->m_sb.sb_agcount);
+
+ if (agno < mp->m_sb.sb_agcount - 1)
+ return mp->m_sb.sb_agblocks;
+ return mp->m_sb.sb_dblocks - (agno * mp->m_sb.sb_agblocks);
+}
+
+/*
+ * Verify that an AG block number pointer neither points outside the AG
+ * nor points at static metadata.
+ */
+bool
+xfs_verify_agbno(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_agblock_t agbno)
+{
+ xfs_agblock_t eoag;
+
+ eoag = xfs_ag_block_count(mp, agno);
+ if (agbno >= eoag)
+ return false;
+ if (agbno <= XFS_AGFL_BLOCK(mp))
+ return false;
+ return true;
+}
+
+/*
+ * Verify that an FS block number pointer neither points outside the
+ * filesystem nor points at static AG metadata.
+ */
+bool
+xfs_verify_fsbno(
+ struct xfs_mount *mp,
+ xfs_fsblock_t fsbno)
+{
+ xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno);
+
+ if (agno >= mp->m_sb.sb_agcount)
+ return false;
+ return xfs_verify_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno));
+}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index aa60937b332e..3d6c02d8ebf3 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -215,6 +215,8 @@ xfs_alloc_get_rec(
int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
+int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp,
+ xfs_agnumber_t agno, struct xfs_buf **bpp);
int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno,
struct xfs_buf **agbp);
@@ -232,5 +234,9 @@ int xfs_alloc_query_range(struct xfs_btree_cur *cur,
xfs_alloc_query_range_fn fn, void *priv);
int xfs_alloc_query_all(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn,
void *priv);
+xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno);
+bool xfs_verify_agbno(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agblock_t agbno);
+bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno);
#endif /* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index aafc4245b698..b7775a1c5241 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -38,6 +38,7 @@
#include "xfs_bmap_util.h"
#include "xfs_bmap_btree.h"
#include "xfs_rtalloc.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
@@ -633,8 +634,8 @@ xfs_bmap_btree_to_extents(
cbno = be64_to_cpu(*pp);
*logflagsp = 0;
#ifdef DEBUG
- if ((error = xfs_btree_check_lptr(cur, cbno, 1)))
- return error;
+ XFS_WANT_CORRUPTED_RETURN(cur->bc_mp,
+ xfs_btree_check_lptr(cur, cbno, 1));
#endif
error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp, XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
@@ -3805,7 +3806,7 @@ xfs_bmapi_read(
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+ mp, XFS_ERRTAG_BMAPIFORMAT))) {
XFS_ERROR_REPORT("xfs_bmapi_read", XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
}
@@ -4283,7 +4284,7 @@ xfs_bmapi_write(
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+ mp, XFS_ERRTAG_BMAPIFORMAT))) {
XFS_ERROR_REPORT("xfs_bmapi_write", XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
}
@@ -4505,7 +4506,7 @@ xfs_bmapi_remap(
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+ mp, XFS_ERRTAG_BMAPIFORMAT))) {
XFS_ERROR_REPORT("xfs_bmapi_remap", XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
}
@@ -5629,8 +5630,8 @@ xfs_bmap_collapse_extents(
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
- XFS_ERROR_REPORT("__func__", XFS_ERRLEVEL_LOW, mp);
+ mp, XFS_ERRTAG_BMAPIFORMAT))) {
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
}
@@ -5725,7 +5726,7 @@ xfs_bmap_insert_extents(
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+ mp, XFS_ERRTAG_BMAPIFORMAT))) {
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
}
@@ -5835,7 +5836,7 @@ xfs_bmap_split_extent_at(
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+ mp, XFS_ERRTAG_BMAPIFORMAT))) {
XFS_ERROR_REPORT("xfs_bmap_split_extent_at",
XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
@@ -6072,8 +6073,7 @@ xfs_bmap_finish_one(
return -EFSCORRUPTED;
if (XFS_TEST_ERROR(false, tp->t_mountp,
- XFS_ERRTAG_BMAP_FINISH_ONE,
- XFS_RANDOM_BMAP_FINISH_ONE))
+ XFS_ERRTAG_BMAP_FINISH_ONE))
return -EIO;
switch (type) {
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index f798b3b33e5d..0dfa374f3d83 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -29,6 +29,7 @@
#include "xfs_inode_item.h"
#include "xfs_buf_item.h"
#include "xfs_btree.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
@@ -63,46 +64,64 @@ xfs_btree_magic(
return magic;
}
-STATIC int /* error (0 or EFSCORRUPTED) */
-xfs_btree_check_lblock(
- struct xfs_btree_cur *cur, /* btree cursor */
- struct xfs_btree_block *block, /* btree long form block pointer */
- int level, /* level of the btree block */
- struct xfs_buf *bp) /* buffer for block, if any */
+/*
+ * Check a long btree block header. Return the address of the failing check,
+ * or NULL if everything is ok.
+ */
+xfs_failaddr_t
+__xfs_btree_check_lblock(
+ struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block,
+ int level,
+ struct xfs_buf *bp)
{
- int lblock_ok = 1; /* block passes checks */
- struct xfs_mount *mp; /* file system mount point */
+ struct xfs_mount *mp = cur->bc_mp;
xfs_btnum_t btnum = cur->bc_btnum;
- int crc;
-
- mp = cur->bc_mp;
- crc = xfs_sb_version_hascrc(&mp->m_sb);
+ int crc = xfs_sb_version_hascrc(&mp->m_sb);
if (crc) {
- lblock_ok = lblock_ok &&
- uuid_equal(&block->bb_u.l.bb_uuid,
- &mp->m_sb.sb_meta_uuid) &&
- block->bb_u.l.bb_blkno == cpu_to_be64(
- bp ? bp->b_bn : XFS_BUF_DADDR_NULL);
+ if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid))
+ return __this_address;
+ if (block->bb_u.l.bb_blkno !=
+ cpu_to_be64(bp ? bp->b_bn : XFS_BUF_DADDR_NULL))
+ return __this_address;
+ if (block->bb_u.l.bb_pad != cpu_to_be32(0))
+ return __this_address;
}
- lblock_ok = lblock_ok &&
- be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) &&
- be16_to_cpu(block->bb_level) == level &&
- be16_to_cpu(block->bb_numrecs) <=
- cur->bc_ops->get_maxrecs(cur, level) &&
- block->bb_u.l.bb_leftsib &&
- (block->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK) ||
- XFS_FSB_SANITY_CHECK(mp,
- be64_to_cpu(block->bb_u.l.bb_leftsib))) &&
- block->bb_u.l.bb_rightsib &&
- (block->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK) ||
- XFS_FSB_SANITY_CHECK(mp,
- be64_to_cpu(block->bb_u.l.bb_rightsib)));
-
- if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp,
- XFS_ERRTAG_BTREE_CHECK_LBLOCK,
- XFS_RANDOM_BTREE_CHECK_LBLOCK))) {
+ if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+ return __this_address;
+ if (be16_to_cpu(block->bb_level) != level)
+ return __this_address;
+ if (be16_to_cpu(block->bb_numrecs) >
+ cur->bc_ops->get_maxrecs(cur, level))
+ return __this_address;
+ if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
+ !xfs_btree_check_lptr(cur, be64_to_cpu(block->bb_u.l.bb_leftsib),
+ level + 1))
+ return __this_address;
+ if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
+ !xfs_btree_check_lptr(cur, be64_to_cpu(block->bb_u.l.bb_rightsib),
+ level + 1))
+ return __this_address;
+
+ return NULL;
+}
+
+/* Check a long btree block header. */
+int
+xfs_btree_check_lblock(
+ struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block,
+ int level,
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_failaddr_t fa;
+
+ fa = __xfs_btree_check_lblock(cur, block, level, bp);
+ if (unlikely(XFS_TEST_ERROR(fa != NULL, mp,
+ XFS_ERRTAG_BTREE_CHECK_LBLOCK))) {
if (bp)
trace_xfs_btree_corrupt(bp, _RET_IP_);
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
@@ -111,50 +130,62 @@ xfs_btree_check_lblock(
return 0;
}
-STATIC int /* error (0 or EFSCORRUPTED) */
-xfs_btree_check_sblock(
- struct xfs_btree_cur *cur, /* btree cursor */
- struct xfs_btree_block *block, /* btree short form block pointer */
- int level, /* level of the btree block */
- struct xfs_buf *bp) /* buffer containing block */
+/*
+ * Check a short btree block header. Return the address of the failing check,
+ * or NULL if everything is ok.
+ */
+xfs_failaddr_t
+__xfs_btree_check_sblock(
+ struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block,
+ int level,
+ struct xfs_buf *bp)
{
- struct xfs_mount *mp; /* file system mount point */
- struct xfs_buf *agbp; /* buffer for ag. freespace struct */
- struct xfs_agf *agf; /* ag. freespace structure */
- xfs_agblock_t agflen; /* native ag. freespace length */
- int sblock_ok = 1; /* block passes checks */
+ struct xfs_mount *mp = cur->bc_mp;
xfs_btnum_t btnum = cur->bc_btnum;
- int crc;
-
- mp = cur->bc_mp;
- crc = xfs_sb_version_hascrc(&mp->m_sb);
- agbp = cur->bc_private.a.agbp;
- agf = XFS_BUF_TO_AGF(agbp);
- agflen = be32_to_cpu(agf->agf_length);
+ int crc = xfs_sb_version_hascrc(&mp->m_sb);
if (crc) {
- sblock_ok = sblock_ok &&
- uuid_equal(&block->bb_u.s.bb_uuid,
- &mp->m_sb.sb_meta_uuid) &&
- block->bb_u.s.bb_blkno == cpu_to_be64(
- bp ? bp->b_bn : XFS_BUF_DADDR_NULL);
+ if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
+ return __this_address;
+ if (block->bb_u.s.bb_blkno !=
+ cpu_to_be64(bp ? bp->b_bn : XFS_BUF_DADDR_NULL))
+ return __this_address;
}
- sblock_ok = sblock_ok &&
- be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) &&
- be16_to_cpu(block->bb_level) == level &&
- be16_to_cpu(block->bb_numrecs) <=
- cur->bc_ops->get_maxrecs(cur, level) &&
- (block->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK) ||
- be32_to_cpu(block->bb_u.s.bb_leftsib) < agflen) &&
- block->bb_u.s.bb_leftsib &&
- (block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK) ||
- be32_to_cpu(block->bb_u.s.bb_rightsib) < agflen) &&
- block->bb_u.s.bb_rightsib;
-
- if (unlikely(XFS_TEST_ERROR(!sblock_ok, mp,
- XFS_ERRTAG_BTREE_CHECK_SBLOCK,
- XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
+ if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+ return __this_address;
+ if (be16_to_cpu(block->bb_level) != level)
+ return __this_address;
+ if (be16_to_cpu(block->bb_numrecs) >
+ cur->bc_ops->get_maxrecs(cur, level))
+ return __this_address;
+ if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
+ !xfs_btree_check_sptr(cur, be32_to_cpu(block->bb_u.s.bb_leftsib),
+ level + 1))
+ return __this_address;
+ if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
+ !xfs_btree_check_sptr(cur, be32_to_cpu(block->bb_u.s.bb_rightsib),
+ level + 1))
+ return __this_address;
+
+ return NULL;
+}
+
+/* Check a short btree block header. */
+STATIC int
+xfs_btree_check_sblock(
+ struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block,
+ int level,
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_failaddr_t fa;
+
+ fa = __xfs_btree_check_sblock(cur, block, level, bp);
+ if (unlikely(XFS_TEST_ERROR(fa != NULL, mp,
+ XFS_ERRTAG_BTREE_CHECK_SBLOCK))) {
if (bp)
trace_xfs_btree_corrupt(bp, _RET_IP_);
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
@@ -179,59 +210,53 @@ xfs_btree_check_block(
return xfs_btree_check_sblock(cur, block, level, bp);
}
-/*
- * Check that (long) pointer is ok.
- */
-int /* error (0 or EFSCORRUPTED) */
+/* Check that this long pointer is valid and points within the fs. */
+bool
xfs_btree_check_lptr(
- struct xfs_btree_cur *cur, /* btree cursor */
- xfs_fsblock_t bno, /* btree block disk address */
- int level) /* btree block level */
+ struct xfs_btree_cur *cur,
+ xfs_fsblock_t fsbno,
+ int level)
{
- XFS_WANT_CORRUPTED_RETURN(cur->bc_mp,
- level > 0 &&
- bno != NULLFSBLOCK &&
- XFS_FSB_SANITY_CHECK(cur->bc_mp, bno));
- return 0;
+ if (level <= 0)
+ return false;
+ return xfs_verify_fsbno(cur->bc_mp, fsbno);
}
-#ifdef DEBUG
-/*
- * Check that (short) pointer is ok.
- */
-STATIC int /* error (0 or EFSCORRUPTED) */
+/* Check that this short pointer is valid and points within the AG. */
+bool
xfs_btree_check_sptr(
- struct xfs_btree_cur *cur, /* btree cursor */
- xfs_agblock_t bno, /* btree block disk address */
- int level) /* btree block level */
+ struct xfs_btree_cur *cur,
+ xfs_agblock_t agbno,
+ int level)
{
- xfs_agblock_t agblocks = cur->bc_mp->m_sb.sb_agblocks;
-
- XFS_WANT_CORRUPTED_RETURN(cur->bc_mp,
- level > 0 &&
- bno != NULLAGBLOCK &&
- bno != 0 &&
- bno < agblocks);
- return 0;
+ if (level <= 0)
+ return false;
+ return xfs_verify_agbno(cur->bc_mp, cur->bc_private.a.agno, agbno);
}
+#ifdef DEBUG
/*
- * Check that block ptr is ok.
+ * Check that a given (indexed) btree pointer at a certain level of a
+ * btree is valid and doesn't point past where it should.
*/
-STATIC int /* error (0 or EFSCORRUPTED) */
+int
xfs_btree_check_ptr(
- struct xfs_btree_cur *cur, /* btree cursor */
- union xfs_btree_ptr *ptr, /* btree block disk address */
- int index, /* offset from ptr to check */
- int level) /* btree block level */
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ int index,
+ int level)
{
if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- return xfs_btree_check_lptr(cur,
- be64_to_cpu((&ptr->l)[index]), level);
+ XFS_WANT_CORRUPTED_RETURN(cur->bc_mp,
+ xfs_btree_check_lptr(cur,
+ be64_to_cpu((&ptr->l)[index]), level));
} else {
- return xfs_btree_check_sptr(cur,
- be32_to_cpu((&ptr->s)[index]), level);
+ XFS_WANT_CORRUPTED_RETURN(cur->bc_mp,
+ xfs_btree_check_sptr(cur,
+ be32_to_cpu((&ptr->s)[index]), level));
}
+
+ return 0;
}
#endif
@@ -568,7 +593,7 @@ xfs_btree_ptr_offset(
/*
* Return a pointer to the n-th record in the btree block.
*/
-STATIC union xfs_btree_rec *
+union xfs_btree_rec *
xfs_btree_rec_addr(
struct xfs_btree_cur *cur,
int n,
@@ -581,7 +606,7 @@ xfs_btree_rec_addr(
/*
* Return a pointer to the n-th key in the btree block.
*/
-STATIC union xfs_btree_key *
+union xfs_btree_key *
xfs_btree_key_addr(
struct xfs_btree_cur *cur,
int n,
@@ -594,7 +619,7 @@ xfs_btree_key_addr(
/*
* Return a pointer to the n-th high key in the btree block.
*/
-STATIC union xfs_btree_key *
+union xfs_btree_key *
xfs_btree_high_key_addr(
struct xfs_btree_cur *cur,
int n,
@@ -607,7 +632,7 @@ xfs_btree_high_key_addr(
/*
* Return a pointer to the n-th block pointer in the btree block.
*/
-STATIC union xfs_btree_ptr *
+union xfs_btree_ptr *
xfs_btree_ptr_addr(
struct xfs_btree_cur *cur,
int n,
@@ -641,7 +666,7 @@ xfs_btree_get_iroot(
* Retrieve the block pointer from the cursor at the given level.
* This may be an inode btree root or from a buffer.
*/
-STATIC struct xfs_btree_block * /* generic btree block pointer */
+struct xfs_btree_block * /* generic btree block pointer */
xfs_btree_get_block(
struct xfs_btree_cur *cur, /* btree cursor */
int level, /* level in btree */
@@ -730,7 +755,8 @@ xfs_btree_firstrec(
* Get the block pointer for this level.
*/
block = xfs_btree_get_block(cur, level, &bp);
- xfs_btree_check_block(cur, block, level, bp);
+ if (xfs_btree_check_block(cur, block, level, bp))
+ return 0;
/*
* It's empty, there is no such record.
*/
@@ -759,7 +785,8 @@ xfs_btree_lastrec(
* Get the block pointer for this level.
*/
block = xfs_btree_get_block(cur, level, &bp);
- xfs_btree_check_block(cur, block, level, bp);
+ if (xfs_btree_check_block(cur, block, level, bp))
+ return 0;
/*
* It's empty, there is no such record.
*/
@@ -1756,7 +1783,7 @@ error0:
return error;
}
-STATIC int
+int
xfs_btree_lookup_get_block(
struct xfs_btree_cur *cur, /* btree cursor */
int level, /* level in the btree */
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 03c1d8976019..9a6de90966c7 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -257,6 +257,14 @@ typedef struct xfs_btree_cur
*/
#define XFS_BUF_TO_BLOCK(bp) ((struct xfs_btree_block *)((bp)->b_addr))
+/*
+ * Internal long and short btree block checks. They return NULL if the
+ * block is ok or the address of the failed check otherwise.
+ */
+xfs_failaddr_t __xfs_btree_check_lblock(struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block, int level, struct xfs_buf *bp);
+xfs_failaddr_t __xfs_btree_check_sblock(struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block, int level, struct xfs_buf *bp);
/*
* Check that block header is ok.
@@ -271,10 +279,19 @@ xfs_btree_check_block(
/*
* Check that (long) pointer is ok.
*/
-int /* error (0 or EFSCORRUPTED) */
+bool /* error (0 or EFSCORRUPTED) */
xfs_btree_check_lptr(
struct xfs_btree_cur *cur, /* btree cursor */
- xfs_fsblock_t ptr, /* btree block disk address */
+ xfs_fsblock_t fsbno, /* btree block disk address */
+ int level); /* btree block level */
+
+/*
+ * Check that (short) pointer is ok.
+ */
+bool /* error (0 or EFSCORRUPTED) */
+xfs_btree_check_sptr(
+ struct xfs_btree_cur *cur, /* btree cursor */
+ xfs_agblock_t agbno, /* btree block disk address */
int level); /* btree block level */
/*
@@ -507,4 +524,17 @@ int xfs_btree_visit_blocks(struct xfs_btree_cur *cur,
int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks);
+union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n,
+ struct xfs_btree_block *block);
+union xfs_btree_key *xfs_btree_key_addr(struct xfs_btree_cur *cur, int n,
+ struct xfs_btree_block *block);
+union xfs_btree_key *xfs_btree_high_key_addr(struct xfs_btree_cur *cur, int n,
+ struct xfs_btree_block *block);
+union xfs_btree_ptr *xfs_btree_ptr_addr(struct xfs_btree_cur *cur, int n,
+ struct xfs_btree_block *block);
+int xfs_btree_lookup_get_block(struct xfs_btree_cur *cur, int level,
+ union xfs_btree_ptr *pp, struct xfs_btree_block **blkp);
+struct xfs_btree_block *xfs_btree_get_block(struct xfs_btree_cur *cur,
+ int level, struct xfs_buf **bpp);
+
#endif /* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 2f389d366e93..67f4b6d22914 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -30,6 +30,8 @@
#include "xfs_bmap.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
+#include "xfs_ialloc.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trace.h"
@@ -202,24 +204,9 @@ xfs_dir_ino_validate(
xfs_mount_t *mp,
xfs_ino_t ino)
{
- xfs_agblock_t agblkno;
- xfs_agino_t agino;
- xfs_agnumber_t agno;
- int ino_ok;
- int ioff;
-
- agno = XFS_INO_TO_AGNO(mp, ino);
- agblkno = XFS_INO_TO_AGBNO(mp, ino);
- ioff = XFS_INO_TO_OFFSET(mp, ino);
- agino = XFS_OFFBNO_TO_AGINO(mp, agblkno, ioff);
- ino_ok =
- agno < mp->m_sb.sb_agcount &&
- agblkno < mp->m_sb.sb_agblocks &&
- agblkno != 0 &&
- ioff < (1 << mp->m_sb.sb_inopblog) &&
- XFS_AGINO_TO_INO(mp, agno, agino) == ino;
- if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE,
- XFS_RANDOM_DIR_INO_VALIDATE))) {
+ bool ino_ok = xfs_verify_dir_ino(mp, ino);
+
+ if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE))) {
xfs_warn(mp, "Invalid inode number 0x%Lx",
(unsigned long long) ino);
XFS_ERROR_REPORT("xfs_dir_ino_validate", XFS_ERRLEVEL_LOW, mp);
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 21c8f8bf94d5..9646240480ea 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -173,7 +173,7 @@ extern void xfs_dir2_data_log_unused(struct xfs_da_args *args,
extern void xfs_dir2_data_make_free(struct xfs_da_args *args,
struct xfs_buf *bp, xfs_dir2_data_aoff_t offset,
xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp);
-extern void xfs_dir2_data_use_free(struct xfs_da_args *args,
+extern int xfs_dir2_data_use_free(struct xfs_da_args *args,
struct xfs_buf *bp, struct xfs_dir2_data_unused *dup,
xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len,
int *needlogp, int *needscanp);
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index aa17cb788946..84351db958e6 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -450,15 +450,19 @@ xfs_dir2_block_addname(
* No stale entries, will use enddup space to hold new leaf.
*/
if (!btp->stale) {
+ xfs_dir2_data_aoff_t aoff;
+
/*
* Mark the space needed for the new leaf entry, now in use.
*/
- xfs_dir2_data_use_free(args, bp, enddup,
- (xfs_dir2_data_aoff_t)
- ((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) -
- sizeof(*blp)),
- (xfs_dir2_data_aoff_t)sizeof(*blp),
- &needlog, &needscan);
+ aoff = (xfs_dir2_data_aoff_t)((char *)enddup - (char *)hdr +
+ be16_to_cpu(enddup->length) - sizeof(*blp));
+ error = xfs_dir2_data_use_free(args, bp, enddup, aoff,
+ (xfs_dir2_data_aoff_t)sizeof(*blp), &needlog,
+ &needscan);
+ if (error)
+ return error;
+
/*
* Update the tail (entry count).
*/
@@ -540,9 +544,11 @@ xfs_dir2_block_addname(
/*
* Mark space for the data entry used.
*/
- xfs_dir2_data_use_free(args, bp, dup,
- (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
- (xfs_dir2_data_aoff_t)len, &needlog, &needscan);
+ error = xfs_dir2_data_use_free(args, bp, dup,
+ (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
+ (xfs_dir2_data_aoff_t)len, &needlog, &needscan);
+ if (error)
+ return error;
/*
* Create the new data entry.
*/
@@ -996,8 +1002,10 @@ xfs_dir2_leaf_to_block(
/*
* Use up the space at the end of the block (blp/btp).
*/
- xfs_dir2_data_use_free(args, dbp, dup, args->geo->blksize - size, size,
- &needlog, &needscan);
+ error = xfs_dir2_data_use_free(args, dbp, dup,
+ args->geo->blksize - size, size, &needlog, &needscan);
+ if (error)
+ return error;
/*
* Initialize the block tail.
*/
@@ -1109,18 +1117,14 @@ xfs_dir2_sf_to_block(
* Add block 0 to the inode.
*/
error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno);
- if (error) {
- kmem_free(sfp);
- return error;
- }
+ if (error)
+ goto out_free;
/*
* Initialize the data block, then convert it to block format.
*/
error = xfs_dir3_data_init(args, blkno, &bp);
- if (error) {
- kmem_free(sfp);
- return error;
- }
+ if (error)
+ goto out_free;
xfs_dir3_block_init(mp, tp, bp, dp);
hdr = bp->b_addr;
@@ -1135,8 +1139,10 @@ xfs_dir2_sf_to_block(
*/
dup = dp->d_ops->data_unused_p(hdr);
needlog = needscan = 0;
- xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i,
- i, &needlog, &needscan);
+ error = xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i,
+ i, &needlog, &needscan);
+ if (error)
+ goto out_free;
ASSERT(needscan == 0);
/*
* Fill in the tail.
@@ -1149,9 +1155,11 @@ xfs_dir2_sf_to_block(
/*
* Remove the freespace, we'll manage it.
*/
- xfs_dir2_data_use_free(args, bp, dup,
- (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
- be16_to_cpu(dup->length), &needlog, &needscan);
+ error = xfs_dir2_data_use_free(args, bp, dup,
+ (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
+ be16_to_cpu(dup->length), &needlog, &needscan);
+ if (error)
+ goto out_free;
/*
* Create entry for .
*/
@@ -1255,4 +1263,7 @@ xfs_dir2_sf_to_block(
xfs_dir2_block_log_tail(tp, bp);
xfs_dir3_data_check(dp, bp);
return 0;
+out_free:
+ kmem_free(sfp);
+ return error;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index d478065b9544..3fa7d192c262 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -910,10 +910,51 @@ xfs_dir2_data_make_free(
*needscanp = needscan;
}
+/* Check our free data for obvious signs of corruption. */
+static inline xfs_failaddr_t
+xfs_dir2_data_check_free(
+ struct xfs_dir2_data_hdr *hdr,
+ struct xfs_dir2_data_unused *dup,
+ xfs_dir2_data_aoff_t offset,
+ xfs_dir2_data_aoff_t len)
+{
+ if (hdr->magic != cpu_to_be32(XFS_DIR2_DATA_MAGIC) &&
+ hdr->magic != cpu_to_be32(XFS_DIR3_DATA_MAGIC) &&
+ hdr->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) &&
+ hdr->magic != cpu_to_be32(XFS_DIR3_BLOCK_MAGIC))
+ return __this_address;
+ if (be16_to_cpu(dup->freetag) != XFS_DIR2_DATA_FREE_TAG)
+ return __this_address;
+ if (offset < (char *)dup - (char *)hdr)
+ return __this_address;
+ if (offset + len > (char *)dup + be16_to_cpu(dup->length) - (char *)hdr)
+ return __this_address;
+ if ((char *)dup - (char *)hdr !=
+ be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)))
+ return __this_address;
+ return NULL;
+}
+
+/* Sanity-check a new bestfree entry. */
+static inline xfs_failaddr_t
+xfs_dir2_data_check_new_free(
+ struct xfs_dir2_data_hdr *hdr,
+ struct xfs_dir2_data_free *dfp,
+ struct xfs_dir2_data_unused *newdup)
+{
+ if (dfp == NULL)
+ return __this_address;
+ if (dfp->length != newdup->length)
+ return __this_address;
+ if (be16_to_cpu(dfp->offset) != (char *)newdup - (char *)hdr)
+ return __this_address;
+ return NULL;
+}
+
/*
* Take a byte range out of an existing unused space and make it un-free.
*/
-void
+int
xfs_dir2_data_use_free(
struct xfs_da_args *args,
struct xfs_buf *bp,
@@ -925,23 +966,19 @@ xfs_dir2_data_use_free(
{
xfs_dir2_data_hdr_t *hdr; /* data block header */
xfs_dir2_data_free_t *dfp; /* bestfree pointer */
+ xfs_dir2_data_unused_t *newdup; /* new unused entry */
+ xfs_dir2_data_unused_t *newdup2; /* another new unused entry */
+ struct xfs_dir2_data_free *bf;
+ xfs_failaddr_t fa;
int matchback; /* matches end of freespace */
int matchfront; /* matches start of freespace */
int needscan; /* need to regen bestfree */
- xfs_dir2_data_unused_t *newdup; /* new unused entry */
- xfs_dir2_data_unused_t *newdup2; /* another new unused entry */
int oldlen; /* old unused entry's length */
- struct xfs_dir2_data_free *bf;
hdr = bp->b_addr;
- ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
- ASSERT(be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG);
- ASSERT(offset >= (char *)dup - (char *)hdr);
- ASSERT(offset + len <= (char *)dup + be16_to_cpu(dup->length) - (char *)hdr);
- ASSERT((char *)dup - (char *)hdr == be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)));
+ fa = xfs_dir2_data_check_free(hdr, dup, offset, len);
+ if (fa)
+ goto corrupt;
/*
* Look up the entry in the bestfree table.
*/
@@ -986,9 +1023,9 @@ xfs_dir2_data_use_free(
xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
needlogp);
- ASSERT(dfp != NULL);
- ASSERT(dfp->length == newdup->length);
- ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
+ fa = xfs_dir2_data_check_new_free(hdr, dfp, newdup);
+ if (fa)
+ goto corrupt;
/*
* If we got inserted at the last slot,
* that means we don't know if there was a better
@@ -1014,9 +1051,9 @@ xfs_dir2_data_use_free(
xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
needlogp);
- ASSERT(dfp != NULL);
- ASSERT(dfp->length == newdup->length);
- ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
+ fa = xfs_dir2_data_check_new_free(hdr, dfp, newdup);
+ if (fa)
+ goto corrupt;
/*
* If we got inserted at the last slot,
* that means we don't know if there was a better
@@ -1062,4 +1099,9 @@ xfs_dir2_data_use_free(
}
}
*needscanp = needscan;
+ return 0;
+corrupt:
+ xfs_corruption_error(__func__, XFS_ERRLEVEL_LOW, args->dp->i_mount,
+ hdr, __FILE__, __LINE__, fa);
+ return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 68bf3e860a90..7ed2b6872d2b 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -256,7 +256,7 @@ const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = {
.verify_write = xfs_dir3_leafn_write_verify,
};
-static int
+int
xfs_dir3_leaf_read(
struct xfs_trans *tp,
struct xfs_inode *dp,
@@ -850,9 +850,13 @@ xfs_dir2_leaf_addname(
/*
* Mark the initial part of our freespace in use for the new entry.
*/
- xfs_dir2_data_use_free(args, dbp, dup,
- (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
- &needlog, &needscan);
+ error = xfs_dir2_data_use_free(args, dbp, dup,
+ (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
+ length, &needlog, &needscan);
+ if (error) {
+ xfs_trans_brelse(tp, lbp);
+ return error;
+ }
/*
* Initialize our new entry (at last).
*/
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index bbd1238852b3..6224a61793f1 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -1713,6 +1713,7 @@ xfs_dir2_node_addname_int(
__be16 *bests;
struct xfs_dir3_icfree_hdr freehdr;
struct xfs_dir2_data_free *bf;
+ xfs_dir2_data_aoff_t aoff;
dp = args->dp;
mp = dp->i_mount;
@@ -2007,9 +2008,13 @@ xfs_dir2_node_addname_int(
/*
* Mark the first part of the unused space, inuse for us.
*/
- xfs_dir2_data_use_free(args, dbp, dup,
- (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
- &needlog, &needscan);
+ aoff = (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr);
+ error = xfs_dir2_data_use_free(args, dbp, dup, aoff, length,
+ &needlog, &needscan);
+ if (error) {
+ xfs_trans_brelse(tp, dbp);
+ return error;
+ }
/*
* Fill in the new entry and log it.
*/
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 011df4da6cc2..576f2d267fa7 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -58,6 +58,8 @@ extern int xfs_dir3_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
struct xfs_buf **bpp);
/* xfs_dir2_leaf.c */
+extern int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
+ xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp);
extern int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp,
xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp);
extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
new file mode 100644
index 000000000000..a8da432fdf9f
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -0,0 +1,108 @@
+/*
+ * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
+ * Copyright (C) 2017 Oracle.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+#ifndef __XFS_ERRORTAG_H_
+#define __XFS_ERRORTAG_H_
+
+/*
+ * error injection tags - the labels can be anything you want
+ * but each tag should have its own unique number
+ */
+
+#define XFS_ERRTAG_NOERROR 0
+#define XFS_ERRTAG_IFLUSH_1 1
+#define XFS_ERRTAG_IFLUSH_2 2
+#define XFS_ERRTAG_IFLUSH_3 3
+#define XFS_ERRTAG_IFLUSH_4 4
+#define XFS_ERRTAG_IFLUSH_5 5
+#define XFS_ERRTAG_IFLUSH_6 6
+#define XFS_ERRTAG_DA_READ_BUF 7
+#define XFS_ERRTAG_BTREE_CHECK_LBLOCK 8
+#define XFS_ERRTAG_BTREE_CHECK_SBLOCK 9
+#define XFS_ERRTAG_ALLOC_READ_AGF 10
+#define XFS_ERRTAG_IALLOC_READ_AGI 11
+#define XFS_ERRTAG_ITOBP_INOTOBP 12
+#define XFS_ERRTAG_IUNLINK 13
+#define XFS_ERRTAG_IUNLINK_REMOVE 14
+#define XFS_ERRTAG_DIR_INO_VALIDATE 15
+#define XFS_ERRTAG_BULKSTAT_READ_CHUNK 16
+#define XFS_ERRTAG_IODONE_IOERR 17
+#define XFS_ERRTAG_STRATREAD_IOERR 18
+#define XFS_ERRTAG_STRATCMPL_IOERR 19
+#define XFS_ERRTAG_DIOWRITE_IOERR 20
+#define XFS_ERRTAG_BMAPIFORMAT 21
+#define XFS_ERRTAG_FREE_EXTENT 22
+#define XFS_ERRTAG_RMAP_FINISH_ONE 23
+#define XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE 24
+#define XFS_ERRTAG_REFCOUNT_FINISH_ONE 25
+#define XFS_ERRTAG_BMAP_FINISH_ONE 26
+#define XFS_ERRTAG_AG_RESV_CRITICAL 27
+/*
+ * DEBUG mode instrumentation to test and/or trigger delayed allocation
+ * block killing in the event of failed writes. When enabled, all
+ * buffered writes are silenty dropped and handled as if they failed.
+ * All delalloc blocks in the range of the write (including pre-existing
+ * delalloc blocks!) are tossed as part of the write failure error
+ * handling sequence.
+ */
+#define XFS_ERRTAG_DROP_WRITES 28
+#define XFS_ERRTAG_LOG_BAD_CRC 29
+#define XFS_ERRTAG_LOG_ITEM_PIN 30
+#define XFS_ERRTAG_BUF_LRU_REF 31
+#define XFS_ERRTAG_FORCE_SUMMARY_RECALC 33
+#define XFS_ERRTAG_MAX 34
+
+/*
+ * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
+ */
+#define XFS_RANDOM_DEFAULT 100
+#define XFS_RANDOM_IFLUSH_1 XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IFLUSH_2 XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IFLUSH_3 XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IFLUSH_4 XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IFLUSH_5 XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IFLUSH_6 XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_DA_READ_BUF XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_BTREE_CHECK_LBLOCK (XFS_RANDOM_DEFAULT/4)
+#define XFS_RANDOM_BTREE_CHECK_SBLOCK XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_ALLOC_READ_AGF XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IALLOC_READ_AGI XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_ITOBP_INOTOBP XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IUNLINK XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IUNLINK_REMOVE XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_DIR_INO_VALIDATE XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_BULKSTAT_READ_CHUNK XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_IODONE_IOERR (XFS_RANDOM_DEFAULT/10)
+#define XFS_RANDOM_STRATREAD_IOERR (XFS_RANDOM_DEFAULT/10)
+#define XFS_RANDOM_STRATCMPL_IOERR (XFS_RANDOM_DEFAULT/10)
+#define XFS_RANDOM_DIOWRITE_IOERR (XFS_RANDOM_DEFAULT/10)
+#define XFS_RANDOM_BMAPIFORMAT XFS_RANDOM_DEFAULT
+#define XFS_RANDOM_FREE_EXTENT 1
+#define XFS_RANDOM_RMAP_FINISH_ONE 1
+#define XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE 1
+#define XFS_RANDOM_REFCOUNT_FINISH_ONE 1
+#define XFS_RANDOM_BMAP_FINISH_ONE 1
+#define XFS_RANDOM_AG_RESV_CRITICAL 4
+#define XFS_RANDOM_DROP_WRITES 1
+#define XFS_RANDOM_LOG_BAD_CRC 1
+#define XFS_RANDOM_LOG_ITEM_PIN 1
+#define XFS_RANDOM_BUF_LRU_REF 2
+#define XFS_RANDOM_FORCE_SUMMARY_RECALC 1
+
+#endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index b2bc3204e96a..d11ea9ca686f 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1200,6 +1200,7 @@ struct xfs_dsymlink_hdr {
#define XFS_SYMLINK_CRC_OFF offsetof(struct xfs_dsymlink_hdr, sl_crc)
+#define XFS_SYMLINK_MAXLEN 1024
/*
* The maximum pathlen is 1024 bytes. Since the minimum file system
* blocksize is 512 bytes, we can get a max of 3 extents back from
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 3376635c223a..214670b965a2 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -31,6 +31,7 @@
#include "xfs_ialloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_bmap.h"
#include "xfs_cksum.h"
@@ -46,7 +47,7 @@
/*
* Allocation group level functions.
*/
-static inline int
+int
xfs_ialloc_cluster_alignment(
struct xfs_mount *mp)
{
@@ -98,24 +99,15 @@ xfs_inobt_update(
return xfs_btree_update(cur, &rec);
}
-/*
- * Get the data from the pointed-to record.
- */
-int /* error */
-xfs_inobt_get_rec(
- struct xfs_btree_cur *cur, /* btree cursor */
- xfs_inobt_rec_incore_t *irec, /* btree record */
- int *stat) /* output: success/failure */
+/* Convert on-disk btree record to incore inobt record. */
+void
+xfs_inobt_btrec_to_irec(
+ struct xfs_mount *mp,
+ union xfs_btree_rec *rec,
+ struct xfs_inobt_rec_incore *irec)
{
- union xfs_btree_rec *rec;
- int error;
-
- error = xfs_btree_get_rec(cur, &rec, stat);
- if (error || *stat == 0)
- return error;
-
irec->ir_startino = be32_to_cpu(rec->inobt.ir_startino);
- if (xfs_sb_version_hassparseinodes(&cur->bc_mp->m_sb)) {
+ if (xfs_sb_version_hassparseinodes(&mp->m_sb)) {
irec->ir_holemask = be16_to_cpu(rec->inobt.ir_u.sp.ir_holemask);
irec->ir_count = rec->inobt.ir_u.sp.ir_count;
irec->ir_freecount = rec->inobt.ir_u.sp.ir_freecount;
@@ -130,6 +122,25 @@ xfs_inobt_get_rec(
be32_to_cpu(rec->inobt.ir_u.f.ir_freecount);
}
irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
+}
+
+/*
+ * Get the data from the pointed-to record.
+ */
+int
+xfs_inobt_get_rec(
+ struct xfs_btree_cur *cur,
+ struct xfs_inobt_rec_incore *irec,
+ int *stat)
+{
+ union xfs_btree_rec *rec;
+ int error;
+
+ error = xfs_btree_get_rec(cur, &rec, stat);
+ if (error || *stat == 0)
+ return error;
+
+ xfs_inobt_btrec_to_irec(cur->bc_mp, rec, irec);
return 0;
}
@@ -2539,8 +2550,7 @@ xfs_agi_read_verify(
!xfs_buf_verify_cksum(bp, XFS_AGI_CRC_OFF))
xfs_buf_ioerror(bp, -EFSBADCRC);
else if (XFS_TEST_ERROR(!xfs_agi_verify(bp), mp,
- XFS_ERRTAG_IALLOC_READ_AGI,
- XFS_RANDOM_IALLOC_READ_AGI))
+ XFS_ERRTAG_IALLOC_READ_AGI))
xfs_buf_ioerror(bp, -EFSCORRUPTED);
if (bp->b_error)
@@ -2655,3 +2665,93 @@ xfs_ialloc_pagi_init(
xfs_trans_brelse(tp, bp);
return 0;
}
+
+/* Calculate the first and last possible inode number in an AG. */
+void
+xfs_ialloc_agino_range(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_agino_t *first,
+ xfs_agino_t *last)
+{
+ xfs_agblock_t bno;
+ xfs_agblock_t eoag;
+
+ eoag = xfs_ag_block_count(mp, agno);
+
+ /*
+ * Calculate the first inode, which will be in the first
+ * cluster-aligned block after the AGFL.
+ */
+ bno = round_up(XFS_AGFL_BLOCK(mp) + 1,
+ xfs_ialloc_cluster_alignment(mp));
+ *first = XFS_OFFBNO_TO_AGINO(mp, bno, 0);
+
+ /*
+ * Calculate the last inode, which will be at the end of the
+ * last (aligned) cluster that can be allocated in the AG.
+ */
+ bno = round_down(eoag, xfs_ialloc_cluster_alignment(mp));
+ *last = XFS_OFFBNO_TO_AGINO(mp, bno, 0) - 1;
+}
+
+/*
+ * Verify that an AG inode number pointer neither points outside the AG
+ * nor points at static metadata.
+ */
+bool
+xfs_verify_agino(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_agino_t agino)
+{
+ xfs_agino_t first;
+ xfs_agino_t last;
+
+ xfs_ialloc_agino_range(mp, agno, &first, &last);
+ return agino >= first && agino <= last;
+}
+
+/*
+ * Verify that an FS inode number pointer neither points outside the
+ * filesystem nor points at static AG metadata.
+ */
+bool
+xfs_verify_ino(
+ struct xfs_mount *mp,
+ xfs_ino_t ino)
+{
+ xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ino);
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino);
+
+ if (agno >= mp->m_sb.sb_agcount)
+ return false;
+ if (XFS_AGINO_TO_INO(mp, agno, agino) != ino)
+ return false;
+ return xfs_verify_agino(mp, agno, agino);
+}
+
+/* Is this an internal inode number? */
+bool
+xfs_internal_inum(
+ struct xfs_mount *mp,
+ xfs_ino_t ino)
+{
+ return ino == mp->m_sb.sb_rbmino || ino == mp->m_sb.sb_rsumino ||
+ (xfs_sb_version_hasquota(&mp->m_sb) &&
+ xfs_is_quota_inode(&mp->m_sb, ino));
+}
+
+/*
+ * Verify that a directory entry's inode number doesn't point at an internal
+ * inode, empty space, or static AG metadata.
+ */
+bool
+xfs_verify_dir_ino(
+ struct xfs_mount *mp,
+ xfs_ino_t ino)
+{
+ if (xfs_internal_inum(mp, ino))
+ return false;
+ return xfs_verify_ino(mp, ino);
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 0bb89669fc07..d2bdcd5e7312 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -168,5 +168,17 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_agnumber_t agno, struct xfs_buf **bpp);
+union xfs_btree_rec;
+void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, union xfs_btree_rec *rec,
+ struct xfs_inobt_rec_incore *irec);
+
+int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
+void xfs_ialloc_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agino_t *first, xfs_agino_t *last);
+bool xfs_verify_agino(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agino_t agino);
+bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
+bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
+bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
#endif /* __XFS_IALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index ed2fd3d29c33..b9c0bf80669c 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -24,6 +24,7 @@
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_cksum.h"
#include "xfs_icache.h"
@@ -107,8 +108,7 @@ xfs_inode_buf_verify(
di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
xfs_dinode_good_version(mp, dip->di_version);
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
- XFS_ERRTAG_ITOBP_INOTOBP,
- XFS_RANDOM_ITOBP_INOTOBP))) {
+ XFS_ERRTAG_ITOBP_INOTOBP))) {
if (readahead) {
bp->b_flags &= ~XBF_DONE;
xfs_buf_ioerror(bp, -EIO);
@@ -384,7 +384,7 @@ xfs_log_dinode_to_disk(
}
}
-static bool
+bool
xfs_dinode_verify(
struct xfs_mount *mp,
xfs_ino_t ino,
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 0827d7def1ce..a9c97a356c30 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -82,4 +82,7 @@ void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
#define xfs_inobp_check(mp, bp)
#endif /* DEBUG */
+bool xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
+ struct xfs_dinode *dip);
+
#endif /* __XFS_INODE_BUF_H__ */
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 84946829c4bf..53a94834f747 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -89,6 +89,19 @@ static inline uint xlog_get_cycle(char *ptr)
#define XLOG_UNMOUNT_TYPE 0x556e /* Un for Unmount */
+/*
+ * Log item for unmount records.
+ *
+ * The unmount record used to have a string "Unmount filesystem--" in the
+ * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
+ * We just write the magic number now; see xfs_log_unmount_write.
+ */
+struct xfs_unmount_log_format {
+ uint16_t magic; /* XLOG_UNMOUNT_TYPE */
+ uint16_t pad1;
+ uint32_t pad2; /* may as well make it 64 bits */
+};
+
/* Region types for iovec's i_type */
#define XLOG_REG_TYPE_BFORMAT 1
#define XLOG_REG_TYPE_BCHUNK 2
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index e1e610260310..39e3ce66d07e 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -30,6 +30,7 @@
#include "xfs_bmap.h"
#include "xfs_refcount_btree.h"
#include "xfs_alloc.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
@@ -813,8 +814,7 @@ xfs_refcount_still_have_space(
*/
if (cur->bc_private.a.priv.refc.nr_ops > 2 &&
XFS_TEST_ERROR(false, cur->bc_mp,
- XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE,
- XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE))
+ XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE))
return false;
if (cur->bc_private.a.priv.refc.nr_ops == 0)
@@ -1076,8 +1076,7 @@ xfs_refcount_finish_one(
blockcount);
if (XFS_TEST_ERROR(false, mp,
- XFS_ERRTAG_REFCOUNT_FINISH_ONE,
- XFS_RANDOM_REFCOUNT_FINISH_ONE))
+ XFS_ERRTAG_REFCOUNT_FINISH_ONE))
return -EIO;
/*
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 1bcb41fe0156..dd019cee1b3b 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -34,6 +34,7 @@
#include "xfs_rmap_btree.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_extent_busy.h"
#include "xfs_bmap.h"
@@ -179,7 +180,8 @@ done:
return error;
}
-static int
+/* Convert an internal btree record to an rmap record. */
+int
xfs_rmap_btrec_to_irec(
union xfs_btree_rec *rec,
struct xfs_rmap_irec *irec)
@@ -2086,8 +2088,7 @@ xfs_rmap_finish_one(
startoff, blockcount, state);
if (XFS_TEST_ERROR(false, mp,
- XFS_ERRTAG_RMAP_FINISH_ONE,
- XFS_RANDOM_RMAP_FINISH_ONE))
+ XFS_ERRTAG_RMAP_FINISH_ONE))
return -EIO;
/*
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 265116d044f4..466ede637080 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -216,5 +216,8 @@ int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
struct xfs_rmap_irec *irec, int *stat);
int xfs_rmap_compare(const struct xfs_rmap_irec *a,
const struct xfs_rmap_irec *b);
+union xfs_btree_rec;
+int xfs_rmap_btrec_to_irec(union xfs_btree_rec *rec,
+ struct xfs_rmap_irec *irec);
#endif /* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 26bba7f90fdf..4523a92d5507 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -70,7 +70,7 @@ const struct xfs_buf_ops xfs_rtbuf_ops = {
* Get a buffer for the bitmap or summary file block specified.
* The buffer is returned read and locked.
*/
-static int
+int
xfs_rtbuf_get(
xfs_mount_t *mp, /* file system mount structure */
xfs_trans_t *tp, /* transaction pointer */
@@ -1086,3 +1086,15 @@ xfs_rtalloc_query_all(
return xfs_rtalloc_query_range(tp, &keys[0], &keys[1], fn, priv);
}
+
+/*
+ * Verify that an realtime block number pointer doesn't point off the
+ * end of the realtime device.
+ */
+bool
+xfs_verify_rtbno(
+ struct xfs_mount *mp,
+ xfs_rtblock_t rtbno)
+{
+ return rtbno < mp->m_sb.sb_rblocks;
+}
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 2e2c6716b623..c484877129a0 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -114,7 +114,7 @@ xfs_symlink_verify(
if (bp->b_bn != be64_to_cpu(dsl->sl_blkno))
return false;
if (be32_to_cpu(dsl->sl_offset) +
- be32_to_cpu(dsl->sl_bytes) >= MAXPATHLEN)
+ be32_to_cpu(dsl->sl_bytes) >= XFS_SYMLINK_MAXLEN)
return false;
if (dsl->sl_owner == 0)
return false;
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index b456cca1bfb2..6bd916bd35e2 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -477,14 +477,14 @@ xfs_calc_mkdir_reservation(
/*
* Making a new symplink is the same as creating a new file, but
* with the added blocks for remote symlink data which can be up to 1kB in
- * length (MAXPATHLEN).
+ * length (XFS_SYMLINK_MAXLEN).
*/
STATIC uint
xfs_calc_symlink_reservation(
struct xfs_mount *mp)
{
return xfs_calc_create_reservation(mp) +
- xfs_calc_buf_res(1, MAXPATHLEN);
+ xfs_calc_buf_res(1, XFS_SYMLINK_MAXLEN);
}
/*
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index b3043f071bed..3c560695c546 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -48,6 +48,12 @@ typedef int64_t xfs_srtblock_t; /* signed version of xfs_rtblock_t */
typedef int64_t xfs_sfiloff_t; /* signed block number in a file */
/*
+ * New verifiers will return the instruction address of the failing check.
+ * NULL means everything is ok.
+ */
+typedef void * xfs_failaddr_t;
+
+/*
* Null values for the types.
*/
#define NULLFSBLOCK ((xfs_fsblock_t)-1)
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 20ac9f9144f5..adae4eaf8c6c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -42,6 +42,8 @@
#include "xfs_mount.h"
#include "xfs_trace.h"
#include "xfs_log.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
static kmem_zone_t *xfs_buf_zone;
@@ -2075,3 +2077,17 @@ xfs_buf_terminate(void)
{
kmem_zone_destroy(xfs_buf_zone);
}
+
+void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
+{
+ /*
+ * Set the lru reference count to 0 based on the error injection tag.
+ * This allows userspace to disrupt buffer caching for debug/testing
+ * purposes.
+ */
+ if (XFS_TEST_ERROR(false, bp->b_target->bt_mount,
+ XFS_ERRTAG_BUF_LRU_REF))
+ lru_ref = 0;
+
+ atomic_set(&bp->b_lru_ref, lru_ref);
+}
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 9845eab493ee..19eeeee27928 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -351,10 +351,7 @@ extern void xfs_buf_terminate(void);
#define XFS_BUF_ADDR(bp) ((bp)->b_maps[0].bm_bn)
#define XFS_BUF_SET_ADDR(bp, bno) ((bp)->b_maps[0].bm_bn = (xfs_daddr_t)(bno))
-static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
-{
- atomic_set(&bp->b_lru_ref, lru_ref);
-}
+void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref);
static inline int xfs_buf_ispinned(struct xfs_buf *bp)
{
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index bcf72970ca6b..e4f2c012ef06 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -21,104 +21,280 @@
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
+#include "xfs_sysfs.h"
#ifdef DEBUG
-int xfs_etest[XFS_NUM_INJECT_ERROR];
-int64_t xfs_etest_fsid[XFS_NUM_INJECT_ERROR];
-char * xfs_etest_fsname[XFS_NUM_INJECT_ERROR];
-int xfs_error_test_active;
+static unsigned int xfs_errortag_random_default[] = {
+ XFS_RANDOM_DEFAULT,
+ XFS_RANDOM_IFLUSH_1,
+ XFS_RANDOM_IFLUSH_2,
+ XFS_RANDOM_IFLUSH_3,
+ XFS_RANDOM_IFLUSH_4,
+ XFS_RANDOM_IFLUSH_5,
+ XFS_RANDOM_IFLUSH_6,
+ XFS_RANDOM_DA_READ_BUF,
+ XFS_RANDOM_BTREE_CHECK_LBLOCK,
+ XFS_RANDOM_BTREE_CHECK_SBLOCK,
+ XFS_RANDOM_ALLOC_READ_AGF,
+ XFS_RANDOM_IALLOC_READ_AGI,
+ XFS_RANDOM_ITOBP_INOTOBP,
+ XFS_RANDOM_IUNLINK,
+ XFS_RANDOM_IUNLINK_REMOVE,
+ XFS_RANDOM_DIR_INO_VALIDATE,
+ XFS_RANDOM_BULKSTAT_READ_CHUNK,
+ XFS_RANDOM_IODONE_IOERR,
+ XFS_RANDOM_STRATREAD_IOERR,
+ XFS_RANDOM_STRATCMPL_IOERR,
+ XFS_RANDOM_DIOWRITE_IOERR,
+ XFS_RANDOM_BMAPIFORMAT,
+ XFS_RANDOM_FREE_EXTENT,
+ XFS_RANDOM_RMAP_FINISH_ONE,
+ XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE,
+ XFS_RANDOM_REFCOUNT_FINISH_ONE,
+ XFS_RANDOM_BMAP_FINISH_ONE,
+ XFS_RANDOM_AG_RESV_CRITICAL,
+ XFS_RANDOM_DROP_WRITES,
+ XFS_RANDOM_LOG_BAD_CRC,
+ XFS_RANDOM_LOG_ITEM_PIN,
+ XFS_RANDOM_BUF_LRU_REF,
+ XFS_RANDOM_FORCE_SUMMARY_RECALC,
+};
-int
-xfs_error_test(int error_tag, int *fsidp, char *expression,
- int line, char *file, unsigned long randfactor)
+struct xfs_errortag_attr {
+ struct attribute attr;
+ unsigned int tag;
+};
+
+static inline struct xfs_errortag_attr *
+to_attr(struct attribute *attr)
{
- int i;
- int64_t fsid;
+ return container_of(attr, struct xfs_errortag_attr, attr);
+}
- if (prandom_u32() % randfactor)
- return 0;
+static inline struct xfs_mount *
+to_mp(struct kobject *kobject)
+{
+ struct xfs_kobj *kobj = to_kobj(kobject);
- memcpy(&fsid, fsidp, sizeof(xfs_fsid_t));
+ return container_of(kobj, struct xfs_mount, m_errortag_kobj);
+}
+
+STATIC ssize_t
+xfs_errortag_attr_store(
+ struct kobject *kobject,
+ struct attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ struct xfs_mount *mp = to_mp(kobject);
+ struct xfs_errortag_attr *xfs_attr = to_attr(attr);
+ int ret;
+ unsigned int val;
- for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
- if (xfs_etest[i] == error_tag && xfs_etest_fsid[i] == fsid) {
- xfs_warn(NULL,
- "Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
- expression, file, line, xfs_etest_fsname[i]);
- return 1;
- }
+ if (strcmp(buf, "default") == 0) {
+ val = xfs_errortag_random_default[xfs_attr->tag];
+ } else {
+ ret = kstrtouint(buf, 0, &val);
+ if (ret)
+ return ret;
}
- return 0;
+ ret = xfs_errortag_set(mp, xfs_attr->tag, val);
+ if (ret)
+ return ret;
+ return count;
+}
+
+STATIC ssize_t
+xfs_errortag_attr_show(
+ struct kobject *kobject,
+ struct attribute *attr,
+ char *buf)
+{
+ struct xfs_mount *mp = to_mp(kobject);
+ struct xfs_errortag_attr *xfs_attr = to_attr(attr);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ xfs_errortag_get(mp, xfs_attr->tag));
+}
+
+static const struct sysfs_ops xfs_errortag_sysfs_ops = {
+ .show = xfs_errortag_attr_show,
+ .store = xfs_errortag_attr_store,
+};
+
+#define XFS_ERRORTAG_ATTR_RW(_name, _tag) \
+static struct xfs_errortag_attr xfs_errortag_attr_##_name = { \
+ .attr = {.name = __stringify(_name), \
+ .mode = VERIFY_OCTAL_PERMISSIONS(S_IWUSR | S_IRUGO) }, \
+ .tag = (_tag), \
}
+#define XFS_ERRORTAG_ATTR_LIST(_name) &xfs_errortag_attr_##_name.attr
+
+XFS_ERRORTAG_ATTR_RW(noerror, XFS_ERRTAG_NOERROR);
+XFS_ERRORTAG_ATTR_RW(iflush1, XFS_ERRTAG_IFLUSH_1);
+XFS_ERRORTAG_ATTR_RW(iflush2, XFS_ERRTAG_IFLUSH_2);
+XFS_ERRORTAG_ATTR_RW(iflush3, XFS_ERRTAG_IFLUSH_3);
+XFS_ERRORTAG_ATTR_RW(iflush4, XFS_ERRTAG_IFLUSH_4);
+XFS_ERRORTAG_ATTR_RW(iflush5, XFS_ERRTAG_IFLUSH_5);
+XFS_ERRORTAG_ATTR_RW(iflush6, XFS_ERRTAG_IFLUSH_6);
+XFS_ERRORTAG_ATTR_RW(dareadbuf, XFS_ERRTAG_DA_READ_BUF);
+XFS_ERRORTAG_ATTR_RW(btree_chk_lblk, XFS_ERRTAG_BTREE_CHECK_LBLOCK);
+XFS_ERRORTAG_ATTR_RW(btree_chk_sblk, XFS_ERRTAG_BTREE_CHECK_SBLOCK);
+XFS_ERRORTAG_ATTR_RW(readagf, XFS_ERRTAG_ALLOC_READ_AGF);
+XFS_ERRORTAG_ATTR_RW(readagi, XFS_ERRTAG_IALLOC_READ_AGI);
+XFS_ERRORTAG_ATTR_RW(itobp, XFS_ERRTAG_ITOBP_INOTOBP);
+XFS_ERRORTAG_ATTR_RW(iunlink, XFS_ERRTAG_IUNLINK);
+XFS_ERRORTAG_ATTR_RW(iunlinkrm, XFS_ERRTAG_IUNLINK_REMOVE);
+XFS_ERRORTAG_ATTR_RW(dirinovalid, XFS_ERRTAG_DIR_INO_VALIDATE);
+XFS_ERRORTAG_ATTR_RW(bulkstat, XFS_ERRTAG_BULKSTAT_READ_CHUNK);
+XFS_ERRORTAG_ATTR_RW(logiodone, XFS_ERRTAG_IODONE_IOERR);
+XFS_ERRORTAG_ATTR_RW(stratread, XFS_ERRTAG_STRATREAD_IOERR);
+XFS_ERRORTAG_ATTR_RW(stratcmpl, XFS_ERRTAG_STRATCMPL_IOERR);
+XFS_ERRORTAG_ATTR_RW(diowrite, XFS_ERRTAG_DIOWRITE_IOERR);
+XFS_ERRORTAG_ATTR_RW(bmapifmt, XFS_ERRTAG_BMAPIFORMAT);
+XFS_ERRORTAG_ATTR_RW(free_extent, XFS_ERRTAG_FREE_EXTENT);
+XFS_ERRORTAG_ATTR_RW(rmap_finish_one, XFS_ERRTAG_RMAP_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(refcount_continue_update, XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE);
+XFS_ERRORTAG_ATTR_RW(refcount_finish_one, XFS_ERRTAG_REFCOUNT_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(bmap_finish_one, XFS_ERRTAG_BMAP_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(ag_resv_critical, XFS_ERRTAG_AG_RESV_CRITICAL);
+XFS_ERRORTAG_ATTR_RW(drop_writes, XFS_ERRTAG_DROP_WRITES);
+XFS_ERRORTAG_ATTR_RW(log_bad_crc, XFS_ERRTAG_LOG_BAD_CRC);
+XFS_ERRORTAG_ATTR_RW(log_item_pin, XFS_ERRTAG_LOG_ITEM_PIN);
+XFS_ERRORTAG_ATTR_RW(buf_lru_ref, XFS_ERRTAG_BUF_LRU_REF);
+XFS_ERRORTAG_ATTR_RW(bad_summary, XFS_ERRTAG_FORCE_SUMMARY_RECALC);
+
+static struct attribute *xfs_errortag_attrs[] = {
+ XFS_ERRORTAG_ATTR_LIST(noerror),
+ XFS_ERRORTAG_ATTR_LIST(iflush1),
+ XFS_ERRORTAG_ATTR_LIST(iflush2),
+ XFS_ERRORTAG_ATTR_LIST(iflush3),
+ XFS_ERRORTAG_ATTR_LIST(iflush4),
+ XFS_ERRORTAG_ATTR_LIST(iflush5),
+ XFS_ERRORTAG_ATTR_LIST(iflush6),
+ XFS_ERRORTAG_ATTR_LIST(dareadbuf),
+ XFS_ERRORTAG_ATTR_LIST(btree_chk_lblk),
+ XFS_ERRORTAG_ATTR_LIST(btree_chk_sblk),
+ XFS_ERRORTAG_ATTR_LIST(readagf),
+ XFS_ERRORTAG_ATTR_LIST(readagi),
+ XFS_ERRORTAG_ATTR_LIST(itobp),
+ XFS_ERRORTAG_ATTR_LIST(iunlink),
+ XFS_ERRORTAG_ATTR_LIST(iunlinkrm),
+ XFS_ERRORTAG_ATTR_LIST(dirinovalid),
+ XFS_ERRORTAG_ATTR_LIST(bulkstat),
+ XFS_ERRORTAG_ATTR_LIST(logiodone),
+ XFS_ERRORTAG_ATTR_LIST(stratread),
+ XFS_ERRORTAG_ATTR_LIST(stratcmpl),
+ XFS_ERRORTAG_ATTR_LIST(diowrite),
+ XFS_ERRORTAG_ATTR_LIST(bmapifmt),
+ XFS_ERRORTAG_ATTR_LIST(free_extent),
+ XFS_ERRORTAG_ATTR_LIST(rmap_finish_one),
+ XFS_ERRORTAG_ATTR_LIST(refcount_continue_update),
+ XFS_ERRORTAG_ATTR_LIST(refcount_finish_one),
+ XFS_ERRORTAG_ATTR_LIST(bmap_finish_one),
+ XFS_ERRORTAG_ATTR_LIST(ag_resv_critical),
+ XFS_ERRORTAG_ATTR_LIST(drop_writes),
+ XFS_ERRORTAG_ATTR_LIST(log_bad_crc),
+ XFS_ERRORTAG_ATTR_LIST(log_item_pin),
+ XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
+ XFS_ERRORTAG_ATTR_LIST(bad_summary),
+ NULL,
+};
+
+struct kobj_type xfs_errortag_ktype = {
+ .release = xfs_sysfs_release,
+ .sysfs_ops = &xfs_errortag_sysfs_ops,
+ .default_attrs = xfs_errortag_attrs,
+};
+
int
-xfs_errortag_add(unsigned int error_tag, xfs_mount_t *mp)
+xfs_errortag_init(
+ struct xfs_mount *mp)
{
- int i;
- int len;
- int64_t fsid;
+ mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX,
+ KM_SLEEP | KM_MAYFAIL);
+ if (!mp->m_errortag)
+ return -ENOMEM;
- if (error_tag >= XFS_ERRTAG_MAX)
- return -EINVAL;
+ return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype,
+ &mp->m_kobj, "errortag");
+}
- memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
+void
+xfs_errortag_del(
+ struct xfs_mount *mp)
+{
+ xfs_sysfs_del(&mp->m_errortag_kobj);
+ kmem_free(mp->m_errortag);
+}
- for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
- if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) {
- xfs_warn(mp, "error tag #%d on", error_tag);
- return 0;
- }
- }
+bool
+xfs_errortag_test(
+ struct xfs_mount *mp,
+ const char *expression,
+ const char *file,
+ int line,
+ unsigned int error_tag)
+{
+ unsigned int randfactor;
- for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
- if (xfs_etest[i] == 0) {
- xfs_warn(mp, "Turned on XFS error tag #%d",
- error_tag);
- xfs_etest[i] = error_tag;
- xfs_etest_fsid[i] = fsid;
- len = strlen(mp->m_fsname);
- xfs_etest_fsname[i] = kmem_alloc(len + 1, KM_SLEEP);
- strcpy(xfs_etest_fsname[i], mp->m_fsname);
- xfs_error_test_active++;
- return 0;
- }
- }
+ ASSERT(error_tag < XFS_ERRTAG_MAX);
+ randfactor = mp->m_errortag[error_tag];
+ if (!randfactor || prandom_u32() % randfactor)
+ return false;
- xfs_warn(mp, "error tag overflow, too many turned on");
+ xfs_warn_ratelimited(mp,
+"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
+ expression, file, line, mp->m_fsname);
+ return true;
+}
- return 1;
+int
+xfs_errortag_get(
+ struct xfs_mount *mp,
+ unsigned int error_tag)
+{
+ if (error_tag >= XFS_ERRTAG_MAX)
+ return -EINVAL;
+
+ return mp->m_errortag[error_tag];
}
int
-xfs_errortag_clearall(xfs_mount_t *mp, int loud)
+xfs_errortag_set(
+ struct xfs_mount *mp,
+ unsigned int error_tag,
+ unsigned int tag_value)
{
- int64_t fsid;
- int cleared = 0;
- int i;
-
- memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
-
-
- for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
- if ((fsid == 0LL || xfs_etest_fsid[i] == fsid) &&
- xfs_etest[i] != 0) {
- cleared = 1;
- xfs_warn(mp, "Clearing XFS error tag #%d",
- xfs_etest[i]);
- xfs_etest[i] = 0;
- xfs_etest_fsid[i] = 0LL;
- kmem_free(xfs_etest_fsname[i]);
- xfs_etest_fsname[i] = NULL;
- xfs_error_test_active--;
- }
- }
+ if (error_tag >= XFS_ERRTAG_MAX)
+ return -EINVAL;
- if (loud || cleared)
- xfs_warn(mp, "Cleared all XFS error tags for filesystem");
+ mp->m_errortag[error_tag] = tag_value;
+ return 0;
+}
+int
+xfs_errortag_add(
+ struct xfs_mount *mp,
+ unsigned int error_tag)
+{
+ if (error_tag >= XFS_ERRTAG_MAX)
+ return -EINVAL;
+
+ return xfs_errortag_set(mp, error_tag,
+ xfs_errortag_random_default[error_tag]);
+}
+
+int
+xfs_errortag_clearall(
+ struct xfs_mount *mp)
+{
+ memset(mp->m_errortag, 0, sizeof(unsigned int) * XFS_ERRTAG_MAX);
return 0;
}
#endif /* DEBUG */
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 05f8666733a0..ea816c1bf8db 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -63,89 +63,26 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
} \
}
-/*
- * error injection tags - the labels can be anything you want
- * but each tag should have its own unique number
- */
-
-#define XFS_ERRTAG_NOERROR 0
-#define XFS_ERRTAG_IFLUSH_1 1
-#define XFS_ERRTAG_IFLUSH_2 2
-#define XFS_ERRTAG_IFLUSH_3 3
-#define XFS_ERRTAG_IFLUSH_4 4
-#define XFS_ERRTAG_IFLUSH_5 5
-#define XFS_ERRTAG_IFLUSH_6 6
-#define XFS_ERRTAG_DA_READ_BUF 7
-#define XFS_ERRTAG_BTREE_CHECK_LBLOCK 8
-#define XFS_ERRTAG_BTREE_CHECK_SBLOCK 9
-#define XFS_ERRTAG_ALLOC_READ_AGF 10
-#define XFS_ERRTAG_IALLOC_READ_AGI 11
-#define XFS_ERRTAG_ITOBP_INOTOBP 12
-#define XFS_ERRTAG_IUNLINK 13
-#define XFS_ERRTAG_IUNLINK_REMOVE 14
-#define XFS_ERRTAG_DIR_INO_VALIDATE 15
-#define XFS_ERRTAG_BULKSTAT_READ_CHUNK 16
-#define XFS_ERRTAG_IODONE_IOERR 17
-#define XFS_ERRTAG_STRATREAD_IOERR 18
-#define XFS_ERRTAG_STRATCMPL_IOERR 19
-#define XFS_ERRTAG_DIOWRITE_IOERR 20
-#define XFS_ERRTAG_BMAPIFORMAT 21
-#define XFS_ERRTAG_FREE_EXTENT 22
-#define XFS_ERRTAG_RMAP_FINISH_ONE 23
-#define XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE 24
-#define XFS_ERRTAG_REFCOUNT_FINISH_ONE 25
-#define XFS_ERRTAG_BMAP_FINISH_ONE 26
-#define XFS_ERRTAG_AG_RESV_CRITICAL 27
-#define XFS_ERRTAG_MAX 28
-
-/*
- * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
- */
-#define XFS_RANDOM_DEFAULT 100
-#define XFS_RANDOM_IFLUSH_1 XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IFLUSH_2 XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IFLUSH_3 XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IFLUSH_4 XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IFLUSH_5 XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IFLUSH_6 XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_DA_READ_BUF XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_BTREE_CHECK_LBLOCK (XFS_RANDOM_DEFAULT/4)
-#define XFS_RANDOM_BTREE_CHECK_SBLOCK XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_ALLOC_READ_AGF XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IALLOC_READ_AGI XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_ITOBP_INOTOBP XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IUNLINK XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IUNLINK_REMOVE XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_DIR_INO_VALIDATE XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_BULKSTAT_READ_CHUNK XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_IODONE_IOERR (XFS_RANDOM_DEFAULT/10)
-#define XFS_RANDOM_STRATREAD_IOERR (XFS_RANDOM_DEFAULT/10)
-#define XFS_RANDOM_STRATCMPL_IOERR (XFS_RANDOM_DEFAULT/10)
-#define XFS_RANDOM_DIOWRITE_IOERR (XFS_RANDOM_DEFAULT/10)
-#define XFS_RANDOM_BMAPIFORMAT XFS_RANDOM_DEFAULT
-#define XFS_RANDOM_FREE_EXTENT 1
-#define XFS_RANDOM_RMAP_FINISH_ONE 1
-#define XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE 1
-#define XFS_RANDOM_REFCOUNT_FINISH_ONE 1
-#define XFS_RANDOM_BMAP_FINISH_ONE 1
-#define XFS_RANDOM_AG_RESV_CRITICAL 4
-
#ifdef DEBUG
-extern int xfs_error_test_active;
-extern int xfs_error_test(int, int *, char *, int, char *, unsigned long);
-
-#define XFS_NUM_INJECT_ERROR 10
-#define XFS_TEST_ERROR(expr, mp, tag, rf) \
- ((expr) || (xfs_error_test_active && \
- xfs_error_test((tag), (mp)->m_fixedfsid, "expr", __LINE__, __FILE__, \
- (rf))))
+extern int xfs_errortag_init(struct xfs_mount *mp);
+extern void xfs_errortag_del(struct xfs_mount *mp);
+extern bool xfs_errortag_test(struct xfs_mount *mp, const char *expression,
+ const char *file, int line, unsigned int error_tag);
+#define XFS_TEST_ERROR(expr, mp, tag) \
+ ((expr) || xfs_errortag_test((mp), #expr, __FILE__, __LINE__, (tag)))
-extern int xfs_errortag_add(unsigned int error_tag, struct xfs_mount *mp);
-extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud);
+extern int xfs_errortag_get(struct xfs_mount *mp, unsigned int error_tag);
+extern int xfs_errortag_set(struct xfs_mount *mp, unsigned int error_tag,
+ unsigned int tag_value);
+extern int xfs_errortag_add(struct xfs_mount *mp, unsigned int error_tag);
+extern int xfs_errortag_clearall(struct xfs_mount *mp);
#else
-#define XFS_TEST_ERROR(expr, mp, tag, rf) (expr)
-#define xfs_errortag_add(tag, mp) (ENOSYS)
-#define xfs_errortag_clearall(mp, loud) (ENOSYS)
+#define xfs_errortag_init(mp) (0)
+#define xfs_errortag_del(mp)
+#define XFS_TEST_ERROR(expr, mp, tag) (expr)
+#define xfs_errortag_set(mp, tag, val) (ENOSYS)
+#define xfs_errortag_add(mp, tag) (ENOSYS)
+#define xfs_errortag_clearall(mp) (ENOSYS)
#endif /* DEBUG */
/*
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ff05b23f45b3..6d1b072e843b 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -40,6 +40,7 @@
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
@@ -3523,7 +3524,7 @@ xfs_iflush_int(
dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC),
- mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
+ mp, XFS_ERRTAG_IFLUSH_1)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: Bad inode %Lu magic number 0x%x, ptr 0x%p",
__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
@@ -3533,7 +3534,7 @@ xfs_iflush_int(
if (XFS_TEST_ERROR(
(ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
(ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_IFLUSH_3, XFS_RANDOM_IFLUSH_3)) {
+ mp, XFS_ERRTAG_IFLUSH_3)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: Bad regular inode %Lu, ptr 0x%p",
__func__, ip->i_ino, ip);
@@ -3544,7 +3545,7 @@ xfs_iflush_int(
(ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
(ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
(ip->i_d.di_format != XFS_DINODE_FMT_LOCAL),
- mp, XFS_ERRTAG_IFLUSH_4, XFS_RANDOM_IFLUSH_4)) {
+ mp, XFS_ERRTAG_IFLUSH_4)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: Bad directory inode %Lu, ptr 0x%p",
__func__, ip->i_ino, ip);
@@ -3552,8 +3553,7 @@ xfs_iflush_int(
}
}
if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents >
- ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5,
- XFS_RANDOM_IFLUSH_5)) {
+ ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: detected corrupt incore inode %Lu, "
"total extents = %d, nblocks = %Ld, ptr 0x%p",
@@ -3563,7 +3563,7 @@ xfs_iflush_int(
goto corrupt_out;
}
if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
- mp, XFS_ERRTAG_IFLUSH_6, XFS_RANDOM_IFLUSH_6)) {
+ mp, XFS_ERRTAG_IFLUSH_6)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: bad inode %Lu, forkoff 0x%x, ptr 0x%p",
__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 48660555f381..f4500d1f5894 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -2045,14 +2045,14 @@ xfs_file_ioctl(
if (copy_from_user(&in, arg, sizeof(in)))
return -EFAULT;
- return xfs_errortag_add(in.errtag, mp);
+ return xfs_errortag_add(mp, in.errtag);
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- return xfs_errortag_clearall(mp, 1);
+ return xfs_errortag_clearall(mp);
case XFS_IOC_FREE_EOFBLOCKS: {
struct xfs_fs_eofblocks eofb;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 966b173b5057..1d5d817054da 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -30,6 +30,7 @@
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_trans_space.h"
@@ -545,7 +546,7 @@ xfs_file_iomap_begin_delay(
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
- mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+ mp, XFS_ERRTAG_BMAPIFORMAT))) {
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
error = -EFSCORRUPTED;
goto out_unlock;
@@ -1122,7 +1123,7 @@ xfs_file_iomap_end_delalloc(
* Behave as if the write failed if drop writes is enabled. Set the NEW
* flag to force delalloc cleanup.
*/
- if (xfs_mp_drop_writes(mp)) {
+ if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) {
iomap->flags |= IOMAP_F_NEW;
written = 0;
}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 2ce26cbe89b9..e8c70b7ac475 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -458,7 +458,7 @@ xfs_vn_get_link(
if (!dentry)
return ERR_PTR(-ECHILD);
- link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
+ link = kmalloc(XFS_SYMLINK_MAXLEN+1, GFP_KERNEL);
if (!link)
goto out_err;
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 5ef6f12af577..d58310514423 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -31,16 +31,6 @@
#include "xfs_trace.h"
#include "xfs_icache.h"
-STATIC int
-xfs_internal_inum(
- xfs_mount_t *mp,
- xfs_ino_t ino)
-{
- return (ino == mp->m_sb.sb_rbmino || ino == mp->m_sb.sb_rsumino ||
- (xfs_sb_version_hasquota(&mp->m_sb) &&
- xfs_is_quota_inode(&mp->m_sb, ino)));
-}
-
/*
* Return stat information for one inode.
* Return 0 if ok, else errno.
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index c829344c8523..00a5efeec496 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -142,8 +142,14 @@ typedef __u32 xfs_nlink_t;
#define SYNCHRONIZE() barrier()
#define __return_address __builtin_return_address(0)
+/*
+ * Return the address of a label. Use barrier() so that the optimizer
+ * won't reorder code to refactor the error jumpouts into a single
+ * return, which throws off the reported address.
+ */
+#define __this_address ({ __label__ __here; __here: barrier(); &&__here; })
+
#define XFS_PROJID_DEFAULT 0
-#define MAXPATHLEN 1024
#define MIN(a,b) (min(a,b))
#define MAX(a,b) (max(a,b))
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index c124b291330b..2841926bdfa9 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -22,6 +22,7 @@
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
@@ -822,6 +823,88 @@ xfs_log_mount_cancel(
* deallocation must not be done until source-end.
*/
+/* Actually write the unmount record to disk. */
+static void
+xfs_log_write_unmount_record(
+ struct xfs_mount *mp)
+{
+ /* the data section must be 32 bit size aligned */
+ struct xfs_unmount_log_format magic = {
+ .magic = XLOG_UNMOUNT_TYPE,
+ };
+ struct xfs_log_iovec reg = {
+ .i_addr = &magic,
+ .i_len = sizeof(magic),
+ .i_type = XLOG_REG_TYPE_UNMOUNT,
+ };
+ struct xfs_log_vec vec = {
+ .lv_niovecs = 1,
+ .lv_iovecp = &reg,
+ };
+ struct xlog *log = mp->m_log;
+ struct xlog_in_core *iclog;
+ struct xlog_ticket *tic = NULL;
+ xfs_lsn_t lsn;
+ uint flags = XLOG_UNMOUNT_TRANS;
+ int error;
+
+ error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
+ if (error)
+ goto out_err;
+
+ /*
+ * If we think the summary counters are bad, clear the unmount header
+ * flag in the unmount record so that the summary counters will be
+ * recalculated during log recovery at next mount. Refer to
+ * xlog_check_unmount_rec for more details.
+ */
+ if (XFS_TEST_ERROR((mp->m_flags & XFS_MOUNT_BAD_SUMMARY), mp,
+ XFS_ERRTAG_FORCE_SUMMARY_RECALC)) {
+ xfs_alert(mp, "%s: will fix summary counters at next mount",
+ __func__);
+ flags &= ~XLOG_UNMOUNT_TRANS;
+ }
+
+ /* remove inited flag, and account for space used */
+ tic->t_flags = 0;
+ tic->t_curr_res -= sizeof(magic);
+ error = xlog_write(log, &vec, tic, &lsn, NULL, flags);
+ /*
+ * At this point, we're umounting anyway, so there's no point in
+ * transitioning log state to IOERROR. Just continue...
+ */
+out_err:
+ if (error)
+ xfs_alert(mp, "%s: unmount record failed", __func__);
+
+ spin_lock(&log->l_icloglock);
+ iclog = log->l_iclog;
+ atomic_inc(&iclog->ic_refcnt);
+ xlog_state_want_sync(log, iclog);
+ spin_unlock(&log->l_icloglock);
+ error = xlog_state_release_iclog(log, iclog);
+
+ spin_lock(&log->l_icloglock);
+ switch (iclog->ic_state) {
+ default:
+ if (!XLOG_FORCED_SHUTDOWN(log)) {
+ xlog_wait(&iclog->ic_force_wait, &log->l_icloglock);
+ break;
+ }
+ /* fall through */
+ case XLOG_STATE_ACTIVE:
+ case XLOG_STATE_DIRTY:
+ spin_unlock(&log->l_icloglock);
+ break;
+ }
+
+ if (tic) {
+ trace_xfs_log_umount_write(log, tic);
+ xlog_ungrant_log_space(log, tic);
+ xfs_log_ticket_put(tic);
+ }
+}
+
/*
* Unmount record used to have a string "Unmount filesystem--" in the
* data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
@@ -838,8 +921,6 @@ xfs_log_unmount_write(xfs_mount_t *mp)
#ifdef DEBUG
xlog_in_core_t *first_iclog;
#endif
- xlog_ticket_t *tic = NULL;
- xfs_lsn_t lsn;
int error;
/*
@@ -866,66 +947,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
} while (iclog != first_iclog);
#endif
if (! (XLOG_FORCED_SHUTDOWN(log))) {
- error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
- if (!error) {
- /* the data section must be 32 bit size aligned */
- struct {
- uint16_t magic;
- uint16_t pad1;
- uint32_t pad2; /* may as well make it 64 bits */
- } magic = {
- .magic = XLOG_UNMOUNT_TYPE,
- };
- struct xfs_log_iovec reg = {
- .i_addr = &magic,
- .i_len = sizeof(magic),
- .i_type = XLOG_REG_TYPE_UNMOUNT,
- };
- struct xfs_log_vec vec = {
- .lv_niovecs = 1,
- .lv_iovecp = &reg,
- };
-
- /* remove inited flag, and account for space used */
- tic->t_flags = 0;
- tic->t_curr_res -= sizeof(magic);
- error = xlog_write(log, &vec, tic, &lsn,
- NULL, XLOG_UNMOUNT_TRANS);
- /*
- * At this point, we're umounting anyway,
- * so there's no point in transitioning log state
- * to IOERROR. Just continue...
- */
- }
-
- if (error)
- xfs_alert(mp, "%s: unmount record failed", __func__);
-
-
- spin_lock(&log->l_icloglock);
- iclog = log->l_iclog;
- atomic_inc(&iclog->ic_refcnt);
- xlog_state_want_sync(log, iclog);
- spin_unlock(&log->l_icloglock);
- error = xlog_state_release_iclog(log, iclog);
-
- spin_lock(&log->l_icloglock);
- if (!(iclog->ic_state == XLOG_STATE_ACTIVE ||
- iclog->ic_state == XLOG_STATE_DIRTY)) {
- if (!XLOG_FORCED_SHUTDOWN(log)) {
- xlog_wait(&iclog->ic_force_wait,
- &log->l_icloglock);
- } else {
- spin_unlock(&log->l_icloglock);
- }
- } else {
- spin_unlock(&log->l_icloglock);
- }
- if (tic) {
- trace_xfs_log_umount_write(log, tic);
- xlog_ungrant_log_space(log, tic);
- xfs_log_ticket_put(tic);
- }
+ xfs_log_write_unmount_record(mp);
} else {
/*
* We're already in forced_shutdown mode, couldn't
@@ -1234,8 +1256,7 @@ xlog_iodone(xfs_buf_t *bp)
* IOABORT state. The IOABORT state is only set in DEBUG mode to inject
* CRC errors into log recovery.
*/
- if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR,
- XFS_RANDOM_IODONE_IOERR) ||
+ if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR) ||
iclog->ic_state & XLOG_STATE_IOABORT) {
if (iclog->ic_state & XLOG_STATE_IOABORT)
iclog->ic_state &= ~XLOG_STATE_IOABORT;
@@ -1887,7 +1908,6 @@ xlog_sync(
/* calculcate the checksum */
iclog->ic_header.h_crc = xlog_cksum(log, &iclog->ic_header,
iclog->ic_datap, size);
-#ifdef DEBUG
/*
* Intentionally corrupt the log record CRC based on the error injection
* frequency, if defined. This facilitates testing log recovery in the
@@ -1895,15 +1915,13 @@ xlog_sync(
* write on I/O completion and shutdown the fs. The subsequent mount
* detects the bad CRC and attempts to recover.
*/
- if (log->l_badcrc_factor &&
- (prandom_u32() % log->l_badcrc_factor == 0)) {
+ if (XFS_TEST_ERROR(false, log->l_mp, XFS_ERRTAG_LOG_BAD_CRC)) {
iclog->ic_header.h_crc &= cpu_to_le32(0xAAAAAAAA);
iclog->ic_state |= XLOG_STATE_IOABORT;
xfs_warn(log->l_mp,
"Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.",
be64_to_cpu(iclog->ic_header.h_lsn));
}
-#endif
bp->b_io_length = BTOBB(count);
bp->b_fspriv = iclog;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 34550b60e98e..924bb3d9051c 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -769,10 +769,13 @@ xfs_mountfs(
if (error)
goto out_del_stats;
+ error = xfs_errortag_init(mp);
+ if (error)
+ goto out_remove_error_sysfs;
error = xfs_uuid_mount(mp);
if (error)
- goto out_remove_error_sysfs;
+ goto out_remove_errortag;
/*
* Set the minimum read and write sizes
@@ -1062,6 +1065,8 @@ xfs_mountfs(
xfs_da_unmount(mp);
out_remove_uuid:
xfs_uuid_unmount(mp);
+ out_remove_errortag:
+ xfs_errortag_del(mp);
out_remove_error_sysfs:
xfs_error_sysfs_del(mp);
out_del_stats:
@@ -1165,10 +1170,11 @@ xfs_unmountfs(
xfs_uuid_unmount(mp);
#if defined(DEBUG)
- xfs_errortag_clearall(mp, 0);
+ xfs_errortag_clearall(mp);
#endif
xfs_free_perag(mp);
+ xfs_errortag_del(mp);
xfs_error_sysfs_del(mp);
xfs_sysfs_del(&mp->m_stats.xs_kobj);
xfs_sysfs_del(&mp->m_kobj);
@@ -1416,3 +1422,16 @@ xfs_dev_is_read_only(
}
return 0;
}
+
+/* Force the summary counters to be recalculated at next mount. */
+void
+xfs_force_summary_recalc(
+ struct xfs_mount *mp)
+{
+ if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
+ return;
+
+ spin_lock(&mp->m_sb_lock);
+ mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+ spin_unlock(&mp->m_sb_lock);
+}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index b7692467f4ab..aef17103b1d3 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -199,14 +199,12 @@ typedef struct xfs_mount {
bool m_fail_unmount;
#ifdef DEBUG
/*
- * DEBUG mode instrumentation to test and/or trigger delayed allocation
- * block killing in the event of failed writes. When enabled, all
- * buffered writes are silenty dropped and handled as if they failed.
- * All delalloc blocks in the range of the write (including pre-existing
- * delalloc blocks!) are tossed as part of the write failure error
- * handling sequence.
+ * Frequency with which errors are injected. Replaces xfs_etest; the
+ * value stored in here is the inverse of the frequency with which the
+ * error triggers. 1 = always, 2 = half the time, etc.
*/
- bool m_drop_writes;
+ unsigned int *m_errortag;
+ struct xfs_kobj m_errortag_kobj;
#endif
} xfs_mount_t;
@@ -326,20 +324,6 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks);
}
-#ifdef DEBUG
-static inline bool
-xfs_mp_drop_writes(struct xfs_mount *mp)
-{
- return mp->m_drop_writes;
-}
-#else
-static inline bool
-xfs_mp_drop_writes(struct xfs_mount *mp)
-{
- return 0;
-}
-#endif
-
/* per-AG block reservation data structures*/
enum xfs_ag_resv_type {
XFS_AG_RESV_NONE = 0,
@@ -463,5 +447,6 @@ int xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
int error_class, int error);
+void xfs_force_summary_recalc(struct xfs_mount *mp);
#endif /* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index f13133e6f19f..3f30f846d7f2 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -107,6 +107,8 @@ xfs_growfs_rt(
/*
* From xfs_rtbitmap.c
*/
+int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp,
+ xfs_rtblock_t block, int issum, struct xfs_buf **bpp);
int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_rtblock_t start, xfs_extlen_t len, int val,
xfs_rtblock_t *new, int *stat);
@@ -136,6 +138,7 @@ int xfs_rtalloc_query_range(struct xfs_trans *tp,
int xfs_rtalloc_query_all(struct xfs_trans *tp,
xfs_rtalloc_query_range_fn fn,
void *priv);
+bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
#else
# define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb) (ENOSYS)
# define xfs_rtfree_extent(t,b,l) (ENOSYS)
@@ -143,6 +146,8 @@ int xfs_rtalloc_query_all(struct xfs_trans *tp,
# define xfs_growfs_rt(mp,in) (ENOSYS)
# define xfs_rtalloc_query_range(t,l,h,f,p) (ENOSYS)
# define xfs_rtalloc_query_all(t,f,p) (ENOSYS)
+# define xfs_rtbuf_get(m,t,b,i,p) (ENOSYS)
+# define xfs_verify_rtbno(m, r) (false)
static inline int /* error */
xfs_rtmount_init(
xfs_mount_t *mp) /* file system mount structure */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 7e5826a77ff2..2ac79fed72ca 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -143,7 +143,7 @@ xfs_readlink(
if (!pathlen)
goto out;
- if (pathlen < 0 || pathlen > MAXPATHLEN) {
+ if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)",
__func__, (unsigned long long) ip->i_ino,
(long long) pathlen);
@@ -202,7 +202,7 @@ xfs_symlink(
* Check component lengths of the target path name.
*/
pathlen = strlen(target_path);
- if (pathlen >= MAXPATHLEN) /* total string too long */
+ if (pathlen >= XFS_SYMLINK_MAXLEN) /* total string too long */
return -ENAMETOOLONG;
udqp = gdqp = NULL;
@@ -560,7 +560,7 @@ xfs_inactive_symlink(
return 0;
}
- if (pathlen < 0 || pathlen > MAXPATHLEN) {
+ if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
xfs_alert(mp, "%s: inode (0x%llx) bad symlink length (%d)",
__func__, (unsigned long long)ip->i_ino, pathlen);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 80ac15fb9638..78d70560eb87 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -90,49 +90,7 @@ to_mp(struct kobject *kobject)
return container_of(kobj, struct xfs_mount, m_kobj);
}
-#ifdef DEBUG
-
-STATIC ssize_t
-drop_writes_store(
- struct kobject *kobject,
- const char *buf,
- size_t count)
-{
- struct xfs_mount *mp = to_mp(kobject);
- int ret;
- int val;
-
- ret = kstrtoint(buf, 0, &val);
- if (ret)
- return ret;
-
- if (val == 1)
- mp->m_drop_writes = true;
- else if (val == 0)
- mp->m_drop_writes = false;
- else
- return -EINVAL;
-
- return count;
-}
-
-STATIC ssize_t
-drop_writes_show(
- struct kobject *kobject,
- char *buf)
-{
- struct xfs_mount *mp = to_mp(kobject);
-
- return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_drop_writes ? 1 : 0);
-}
-XFS_SYSFS_ATTR_RW(drop_writes);
-
-#endif /* DEBUG */
-
static struct attribute *xfs_mp_attrs[] = {
-#ifdef DEBUG
- ATTR_LIST(drop_writes),
-#endif
NULL,
};
@@ -314,47 +272,11 @@ write_grant_head_show(
}
XFS_SYSFS_ATTR_RO(write_grant_head);
-#ifdef DEBUG
-STATIC ssize_t
-log_badcrc_factor_store(
- struct kobject *kobject,
- const char *buf,
- size_t count)
-{
- struct xlog *log = to_xlog(kobject);
- int ret;
- uint32_t val;
-
- ret = kstrtouint(buf, 0, &val);
- if (ret)
- return ret;
-
- log->l_badcrc_factor = val;
-
- return count;
-}
-
-STATIC ssize_t
-log_badcrc_factor_show(
- struct kobject *kobject,
- char *buf)
-{
- struct xlog *log = to_xlog(kobject);
-
- return snprintf(buf, PAGE_SIZE, "%d\n", log->l_badcrc_factor);
-}
-
-XFS_SYSFS_ATTR_RW(log_badcrc_factor);
-#endif /* DEBUG */
-
static struct attribute *xfs_log_attrs[] = {
ATTR_LIST(log_head_lsn),
ATTR_LIST(log_tail_lsn),
ATTR_LIST(reserve_grant_head),
ATTR_LIST(write_grant_head),
-#ifdef DEBUG
- ATTR_LIST(log_badcrc_factor),
-#endif
NULL,
};
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 70f5ab017323..77ebd5d503bc 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -25,6 +25,7 @@
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_trace.h"
+#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_log.h"
@@ -325,6 +326,21 @@ xfs_ail_delete(
xfs_trans_ail_cursor_clear(ailp, lip);
}
+static inline uint
+xfsaild_push_item(
+ struct xfs_ail *ailp,
+ struct xfs_log_item *lip)
+{
+ /*
+ * If log item pinning is enabled, skip the push and track the item as
+ * pinned. This can help induce head-behind-tail conditions.
+ */
+ if (XFS_TEST_ERROR(false, ailp->xa_mount, XFS_ERRTAG_LOG_ITEM_PIN))
+ return XFS_ITEM_PINNED;
+
+ return lip->li_ops->iop_push(lip, &ailp->xa_buf_list);
+}
+
static long
xfsaild_push(
struct xfs_ail *ailp)
@@ -382,7 +398,7 @@ xfsaild_push(
* rely on the AIL cursor implementation to be able to deal with
* the dropped lock.
*/
- lock_result = lip->li_ops->iop_push(lip, &ailp->xa_buf_list);
+ lock_result = xfsaild_push_item(ailp, lip);
switch (lock_result) {
case XFS_ITEM_SUCCESS:
XFS_STATS_INC(mp, xs_push_ail_success);
diff --git a/include/linux/atalk.h b/include/linux/atalk.h
index 73fd8b7e9534..af43ed404ff4 100644
--- a/include/linux/atalk.h
+++ b/include/linux/atalk.h
@@ -150,19 +150,29 @@ extern int sysctl_aarp_retransmit_limit;
extern int sysctl_aarp_resolve_time;
#ifdef CONFIG_SYSCTL
-extern void atalk_register_sysctl(void);
+extern int atalk_register_sysctl(void);
extern void atalk_unregister_sysctl(void);
#else
-#define atalk_register_sysctl() do { } while(0)
-#define atalk_unregister_sysctl() do { } while(0)
+static inline int atalk_register_sysctl(void)
+{
+ return 0;
+}
+static inline void atalk_unregister_sysctl(void)
+{
+}
#endif
#ifdef CONFIG_PROC_FS
extern int atalk_proc_init(void);
extern void atalk_proc_exit(void);
#else
-#define atalk_proc_init() ({ 0; })
-#define atalk_proc_exit() do { } while(0)
+static inline int atalk_proc_init(void)
+{
+ return 0;
+}
+static inline void atalk_proc_exit(void)
+{
+}
#endif /* CONFIG_PROC_FS */
#endif /* __LINUX_ATALK_H__ */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index d2bab7d55152..381b2377493f 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -593,6 +593,7 @@ struct unixware_disklabel {
extern int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
extern void blk_free_devt(dev_t devt);
+extern void blk_invalidate_devt(dev_t devt);
extern dev_t blk_lookup_devt(const char *name, int partno);
extern char *disk_name (struct gendisk *hd, int partno, char *buf);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6dc4e2ba48f1..4682d5d67d8e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -775,6 +775,10 @@ struct mlx5_pagefault {
};
struct mlx5_td {
+ /* protects tirs list changes while tirs refresh */
+#ifndef __GENKSYMS__
+ struct mutex list_lock;
+#endif
struct list_head tirs_list;
u32 tdn;
};
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 7966915ba5a0..72fa32f08b37 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2554,6 +2554,8 @@
#define PCI_VENDOR_ID_CIRCUITCO 0x1cc8
#define PCI_SUBSYSTEM_ID_CIRCUITCO_MINNOWBOARD 0x0001
+#define PCI_VENDOR_ID_HYGON 0x1d94
+
#define PCI_VENDOR_ID_TEKRAM 0x1de1
#define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29
diff --git a/include/media/davinci/vpbe.h b/include/media/davinci/vpbe.h
index 79a566d7defd..180a05e91497 100644
--- a/include/media/davinci/vpbe.h
+++ b/include/media/davinci/vpbe.h
@@ -92,7 +92,7 @@ struct vpbe_config {
struct encoder_config_info *ext_encoders;
/* amplifier information goes here */
struct amp_config_info *amp;
- int num_outputs;
+ unsigned int num_outputs;
/* Order is venc outputs followed by LCD and then external encoders */
struct vpbe_output *outputs;
};
diff --git a/include/net/ip.h b/include/net/ip.h
index f7b1db4cff49..6992833dc754 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -596,6 +596,7 @@ int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
void ip_options_undo(struct ip_options *opt);
void ip_forward_options(struct sk_buff *skb);
int ip_options_rcv_srr(struct sk_buff *skb);
+int ip_options_rcv_srr2(struct sk_buff *skb, struct net_device *dev);
/*
* Functions provided by ip_sockglue.c
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 3334dbfa5aa4..7fc78663ec9d 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -6,7 +6,7 @@
static inline int rtnh_ok(const struct rtnexthop *rtnh, int remaining)
{
- return remaining >= sizeof(*rtnh) &&
+ return remaining >= (int)sizeof(*rtnh) &&
rtnh->rtnh_len >= sizeof(*rtnh) &&
rtnh->rtnh_len <= remaining;
}
diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h
index 3e11e7cc60b7..62e990b620aa 100644
--- a/include/rdma/ib_cache.h
+++ b/include/rdma/ib_cache.h
@@ -133,28 +133,4 @@ const struct ib_gid_attr *rdma_get_gid_attr(struct ib_device *device,
void rdma_put_gid_attr(const struct ib_gid_attr *attr);
void rdma_hold_gid_attr(const struct ib_gid_attr *attr);
-/*
- * This is to be removed. It only exists to make merging rdma and smc simpler.
- */
-static inline __deprecated int ib_query_gid(struct ib_device *device,
- u8 port_num, int index,
- union ib_gid *gid,
- struct ib_gid_attr *attr_out)
-{
- const struct ib_gid_attr *attr;
-
- memset(attr_out, 0, sizeof(*attr_out));
- attr = rdma_get_gid_attr(device, port_num, index);
- if (IS_ERR(attr))
- return PTR_ERR(attr);
-
- if (attr->ndev)
- dev_hold(attr->ndev);
- *attr_out = *attr;
-
- rdma_put_gid_attr(attr);
-
- return 0;
-}
-
#endif /* _IB_CACHE_H */
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 22a3997ff29a..6f02cc979c5e 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -24,7 +24,7 @@ endif
ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
NEON_FLAGS := -ffreestanding
ifeq ($(ARCH),arm)
-NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
+NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon
endif
CFLAGS_recov_neon_inner.o += $(NEON_FLAGS)
ifeq ($(ARCH),arm64)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1828ace5411a..29463467900b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -780,6 +780,8 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
{
pgprot_t pgprot = vma->vm_page_prot;
pgtable_t pgtable = NULL;
+
+ addr &= PMD_MASK;
/*
* If we had pmd_special, we could avoid all these restrictions,
* but we need to be consistent with PTEs and architectures that
@@ -855,6 +857,8 @@ int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud, pfn_t pfn, bool write)
{
pgprot_t pgprot = vma->vm_page_prot;
+
+ addr &= PUD_MASK;
/*
* If we had pud_special, we could avoid all these restrictions,
* but we need to be consistent with PTEs and architectures that
diff --git a/mm/mincore.c b/mm/mincore.c
index c5687c45c326..578827c5ee6a 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -168,6 +168,22 @@ out:
return 0;
}
+static inline bool can_do_mincore(struct vm_area_struct *vma)
+{
+ if (vma_is_anonymous(vma))
+ return true;
+ if (!vma->vm_file)
+ return false;
+ /*
+ * Reveal pagecache information only for non-anonymous mappings that
+ * correspond to the files the calling process could (if tried) open
+ * for writing; otherwise we'd be including shared non-exclusive
+ * mappings, which opens a side channel.
+ */
+ return inode_owner_or_capable(file_inode(vma->vm_file)) ||
+ inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
+}
+
/*
* Do a chunk of "sys_mincore()". We've already checked
* all the arguments, we hold the mmap semaphore: we should
@@ -188,8 +204,13 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v
vma = find_vma(current->mm, addr);
if (!vma || addr < vma->vm_start)
return -ENOMEM;
- mincore_walk.mm = vma->vm_mm;
end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
+ if (!can_do_mincore(vma)) {
+ unsigned long pages = DIV_ROUND_UP(end - addr, PAGE_SIZE);
+ memset(vec, 1, pages);
+ return pages;
+ }
+ mincore_walk.mm = vma->vm_mm;
err = walk_page_range(addr, end, &mincore_walk);
if (err < 0)
return err;
diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
index af46bc49e1e9..b5f84f428aa6 100644
--- a/net/appletalk/atalk_proc.c
+++ b/net/appletalk/atalk_proc.c
@@ -293,7 +293,7 @@ out_interface:
goto out;
}
-void __exit atalk_proc_exit(void)
+void atalk_proc_exit(void)
{
remove_proc_entry("interface", atalk_proc_dir);
remove_proc_entry("route", atalk_proc_dir);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 5d035c1f1156..d1b68cc7da89 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1912,12 +1912,16 @@ static const char atalk_err_snap[] __initconst =
/* Called by proto.c on kernel start up */
static int __init atalk_init(void)
{
- int rc = proto_register(&ddp_proto, 0);
+ int rc;
- if (rc != 0)
+ rc = proto_register(&ddp_proto, 0);
+ if (rc)
goto out;
- (void)sock_register(&atalk_family_ops);
+ rc = sock_register(&atalk_family_ops);
+ if (rc)
+ goto out_proto;
+
ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
if (!ddp_dl)
printk(atalk_err_snap);
@@ -1925,12 +1929,33 @@ static int __init atalk_init(void)
dev_add_pack(&ltalk_packet_type);
dev_add_pack(&ppptalk_packet_type);
- register_netdevice_notifier(&ddp_notifier);
+ rc = register_netdevice_notifier(&ddp_notifier);
+ if (rc)
+ goto out_sock;
+
aarp_proto_init();
- atalk_proc_init();
- atalk_register_sysctl();
+ rc = atalk_proc_init();
+ if (rc)
+ goto out_aarp;
+
+ rc = atalk_register_sysctl();
+ if (rc)
+ goto out_proc;
out:
return rc;
+out_proc:
+ atalk_proc_exit();
+out_aarp:
+ aarp_cleanup_module();
+ unregister_netdevice_notifier(&ddp_notifier);
+out_sock:
+ dev_remove_pack(&ppptalk_packet_type);
+ dev_remove_pack(&ltalk_packet_type);
+ unregister_snap_client(ddp_dl);
+ sock_unregister(PF_APPLETALK);
+out_proto:
+ proto_unregister(&ddp_proto);
+ goto out;
}
module_init(atalk_init);
diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c
index ebb864361f7a..4e6042e0fcac 100644
--- a/net/appletalk/sysctl_net_atalk.c
+++ b/net/appletalk/sysctl_net_atalk.c
@@ -44,9 +44,12 @@ static struct ctl_table atalk_table[] = {
static struct ctl_table_header *atalk_table_header;
-void atalk_register_sysctl(void)
+int __init atalk_register_sysctl(void)
{
atalk_table_header = register_net_sysctl(&init_net, "net/appletalk", atalk_table);
+ if (!atalk_table_header)
+ return -ENOMEM;
+ return 0;
}
void atalk_unregister_sysctl(void)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index e13952d3c0b1..0a2771c13276 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -833,7 +833,8 @@ static unsigned int ip_sabotage_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) {
+ if (skb->nf_bridge && !skb->nf_bridge->in_prerouting &&
+ !netif_is_l3_master(skb->dev)) {
state->okfn(state->net, state->sk, skb);
return NF_STOLEN;
}
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 9b11e61c4b7e..d7418e1d70e8 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -402,6 +402,12 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par,
watcher = xt_request_find_target(NFPROTO_BRIDGE, w->u.name, 0);
if (IS_ERR(watcher))
return PTR_ERR(watcher);
+
+ if (watcher->family != NFPROTO_BRIDGE) {
+ module_put(watcher->me);
+ return -ENOENT;
+ }
+
w->u.watcher = watcher;
par->target = watcher;
@@ -700,6 +706,8 @@ ebt_check_entry(struct ebt_entry *e, struct net *net,
}
i = 0;
+ memset(&mtpar, 0, sizeof(mtpar));
+ memset(&tgpar, 0, sizeof(tgpar));
mtpar.net = tgpar.net = net;
mtpar.table = tgpar.table = name;
mtpar.entryinfo = tgpar.entryinfo = e;
@@ -721,6 +729,13 @@ ebt_check_entry(struct ebt_entry *e, struct net *net,
goto cleanup_watchers;
}
+ /* Reject UNSPEC, xtables verdicts/return values are incompatible */
+ if (target->family != NFPROTO_BRIDGE) {
+ module_put(target->me);
+ ret = -ENOENT;
+ goto cleanup_watchers;
+ }
+
t->u.target = target;
if (t->u.target == &ebt_standard_target) {
if (gap < sizeof(struct ebt_standard_target)) {
@@ -1950,7 +1965,8 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
int off, pad = 0;
unsigned int size_kern, match_size = mwt->match_size;
- strlcpy(name, mwt->u.name, sizeof(name));
+ if (strscpy(name, mwt->u.name, sizeof(name)) < 0)
+ return -EINVAL;
if (state->buf_kern_start)
dst = state->buf_kern_start + state->buf_kern_offset;
diff --git a/net/core/dev.c b/net/core/dev.c
index 35514b75a743..4ca771adf31a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2087,7 +2087,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
int i, j;
for (i = count, j = offset; i--; j++) {
- if (!remove_xps_queue(dev_maps, cpu, j))
+ if (!remove_xps_queue(dev_maps, tci, j))
break;
}
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index c0548d268e1a..e3e6a3e2ca22 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -57,8 +57,8 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
return -EINVAL;
list_for_each_entry(ha, &list->list, list) {
- if (!memcmp(ha->addr, addr, addr_len) &&
- ha->type == addr_type) {
+ if (ha->type == addr_type &&
+ !memcmp(ha->addr, addr, addr_len)) {
if (global) {
/* check if addr is already used as global */
if (ha->global_use)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index afd90ecbe3e9..563923af8884 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1896,11 +1896,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
WARN_ON_ONCE(!ret);
gstrings.len = ret;
- data = vzalloc(gstrings.len * ETH_GSTRING_LEN);
- if (gstrings.len && !data)
- return -ENOMEM;
- __ethtool_get_strings(dev, gstrings.string_set, data);
+ if (gstrings.len) {
+ data = vzalloc(gstrings.len * ETH_GSTRING_LEN);
+ if (!data)
+ return -ENOMEM;
+
+ __ethtool_get_strings(dev, gstrings.string_set, data);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
@@ -1996,11 +2001,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
return -EFAULT;
stats.n_stats = n_stats;
- data = vzalloc(n_stats * sizeof(u64));
- if (n_stats && !data)
- return -ENOMEM;
- ops->get_ethtool_stats(dev, &stats, data);
+ if (n_stats) {
+ data = vzalloc(n_stats * sizeof(u64));
+ if (!data)
+ return -ENOMEM;
+ ops->get_ethtool_stats(dev, &stats, data);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
@@ -2036,13 +2045,18 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
return -EFAULT;
stats.n_stats = n_stats;
- data = vzalloc(n_stats * sizeof(u64));
- if (n_stats && !data)
- return -ENOMEM;
- mutex_lock(&phydev->lock);
- phydev->drv->get_stats(phydev, &stats, data);
- mutex_unlock(&phydev->lock);
+ if (n_stats) {
+ data = vzalloc(n_stats * sizeof(u64));
+ if (!data)
+ return -ENOMEM;
+
+ mutex_lock(&phydev->lock);
+ phydev->drv->get_stats(phydev, &stats, data);
+ mutex_unlock(&phydev->lock);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 85357c416ba9..7c37ec821c5a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -896,6 +896,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
n->cloned = 1;
n->nohdr = 0;
+ n->peeked = 0;
n->destructor = NULL;
C(tail);
C(end);
@@ -3512,7 +3513,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
unsigned int delta_truesize;
struct sk_buff *lp;
- if (unlikely(p->len + len >= 65536))
+ if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
return -E2BIG;
lp = NAPI_GRO_CB(p)->last;
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index f227f002c73d..db87d9f58019 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -738,7 +738,12 @@ static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local,
if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len))
return -ENOMEM;
- return dccp_feat_push_change(fn, feat, is_local, mandatory, &fval);
+ if (dccp_feat_push_change(fn, feat, is_local, mandatory, &fval)) {
+ kfree(fval.sp.vec);
+ return -ENOMEM;
+ }
+
+ return 0;
}
/**
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index eaec888f3b6c..6afb20af0f93 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -820,10 +820,9 @@ static void igmp_timer_expire(unsigned long data)
spin_lock(&im->lock);
im->tm_running = 0;
- if (im->unsolicit_count) {
- im->unsolicit_count--;
+ if (im->unsolicit_count && --im->unsolicit_count)
igmp_start_timer(im, unsolicited_report_interval(in_dev));
- }
+
im->reporter = 1;
spin_unlock(&im->lock);
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index b20c8ac64081..64007ce87273 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -210,6 +210,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC);
if (p) {
p->daddr = *daddr;
+ p->dtime = (__u32)jiffies;
refcount_set(&p->refcnt, 2);
atomic_set(&p->rid, 0);
p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index e7f6ca051f87..8e4a143727ce 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -259,11 +259,10 @@ int ip_local_deliver(struct sk_buff *skb)
ip_local_deliver_finish);
}
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt;
const struct iphdr *iph;
- struct net_device *dev = skb->dev;
/* It looks as overkill, because not all
IP options require packet mangling.
@@ -299,7 +298,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
}
}
- if (ip_options_rcv_srr(skb))
+ if (ip_options_rcv_srr2(skb, dev))
goto drop;
}
@@ -355,7 +354,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
}
#endif
- if (iph->ihl > 5 && ip_rcv_options(skb))
+ if (iph->ihl > 5 && ip_rcv_options(skb, dev))
goto drop;
rt = skb_rtable(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 4ee63381a481..4986a497850d 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -614,7 +614,7 @@ void ip_forward_options(struct sk_buff *skb)
}
}
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr2(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt = &(IPCB(skb)->opt);
int srrspace, srrptr;
@@ -649,7 +649,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
orefdst = skb->_skb_refdst;
skb_dst_set(skb, NULL);
- err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+ err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
rt2 = skb_rtable(skb);
if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
skb_dst_drop(skb);
@@ -670,4 +670,10 @@ int ip_options_rcv_srr(struct sk_buff *skb)
}
return 0;
}
+EXPORT_SYMBOL(ip_options_rcv_srr2);
+
+int ip_options_rcv_srr(struct sk_buff *skb)
+{
+ return ip_options_rcv_srr2(skb, skb->dev);
+}
EXPORT_SYMBOL(ip_options_rcv_srr);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fde40387f4fe..aa81e948bc43 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1042,7 +1042,8 @@ alloc_new_skb:
if (copy > length)
copy = length;
- if (!(rt->dst.dev->features&NETIF_F_SG)) {
+ if (!(rt->dst.dev->features&NETIF_F_SG) &&
+ skb_tailroom(skb) >= copy) {
unsigned int off;
off = skb->len;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 14a65a64fcc7..b3612d0c55ad 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -261,8 +261,8 @@ static struct net_device *__ip_tunnel_create(struct net *net,
} else {
if (strlen(ops->kind) > (IFNAMSIZ - 3))
goto failed;
- strlcpy(name, ops->kind, IFNAMSIZ);
- strncat(name, "%d", 2);
+ strcpy(name, ops->kind);
+ strcat(name, "%d");
}
ASSERT_RTNL();
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 4c5dfe6bd34d..cecafefd71d7 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -780,6 +780,11 @@ static void __init ic_bootp_init_ext(u8 *e)
*/
static inline void __init ic_bootp_init(void)
{
+ /* Re-initialise all name servers to NONE, in case any were set via the
+ * "ip=" or "nfsaddrs=" kernel command line parameters: any IP addresses
+ * specified there will already have been decoded but are no longer
+ * needed
+ */
ic_nameservers_predef();
dev_add_pack(&bootp_packet_type);
@@ -1401,6 +1406,13 @@ static int __init ip_auto_config(void)
int err;
unsigned int i;
+ /* Initialise all name servers to NONE (but only if the "ip=" or
+ * "nfsaddrs=" kernel command line parameters weren't decoded, otherwise
+ * we'll overwrite the IP addresses specified there)
+ */
+ if (ic_set_manually == 0)
+ ic_nameservers_predef();
+
#ifdef CONFIG_PROC_FS
proc_create("pnp", S_IRUGO, init_net.proc_net, &pnp_seq_fops);
#endif /* CONFIG_PROC_FS */
@@ -1621,6 +1633,7 @@ static int __init ip_auto_config_setup(char *addrs)
return 1;
}
+ /* Initialise all name servers to NONE */
ic_nameservers_predef();
/* Parse string for static IP assignment. */
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index b3b49c07b7af..7bf9d034112f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -546,6 +546,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
return -ENOMEM;
j = 0;
+ memset(&mtpar, 0, sizeof(mtpar));
mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ip;
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 1a9b88c8cf72..4f9e782cb12d 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -67,11 +67,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
module_param(dctcp_alpha_on_init, uint, 0644);
MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
- "parameter for clamping alpha on loss");
-
static struct tcp_congestion_ops dctcp_reno;
static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
@@ -213,21 +208,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
}
}
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
{
- if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
- struct dctcp *ca = inet_csk_ca(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
- /* If this extension is enabled, we clamp dctcp_alpha to
- * max on packet loss; the motivation is that dctcp_alpha
- * is an indicator to the extend of congestion and packet
- * loss is an indicator of extreme congestion; setting
- * this in practice turned out to be beneficial, and
- * effectively assumes total congestion which reduces the
- * window by half.
- */
- ca->dctcp_alpha = DCTCP_MAX_ALPHA;
- }
+ ca->loss_cwnd = tp->snd_cwnd;
+ tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+ if (new_state == TCP_CA_Recovery &&
+ new_state != inet_csk(sk)->icsk_ca_state)
+ dctcp_react_to_loss(sk);
+ /* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+ * one loss-adjustment per RTT.
+ */
}
static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
@@ -258,6 +255,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
case CA_EVENT_ECN_NO_CE:
dctcp_ce_state_1_to_0(sk);
break;
+ case CA_EVENT_LOSS:
+ dctcp_react_to_loss(sk);
+ break;
case CA_EVENT_DELAYED_ACK:
case CA_EVENT_NON_DELAYED_ACK:
dctcp_update_ack_reserved(sk, ev);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index db18d2d88d5e..10dd14faa602 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2901,8 +2901,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
return -EBUSY;
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
- if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
- BUG();
+ if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
@@ -3400,6 +3402,7 @@ static void tcp_connect_init(struct sock *sk)
sock_reset_flag(sk, SOCK_DONE);
tp->snd_wnd = 0;
tcp_init_wl(tp, 0);
+ tcp_write_queue_purge(sk);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
tp->snd_up = tp->write_seq;
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index c794a9aa15f5..38018229b9d1 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -66,6 +66,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
if (xo && (xo->flags & XFRM_GRO)) {
skb_mac_header_rebuild(skb);
+ skb_reset_transport_header(skb);
return 0;
}
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 3d36644890bb..1ad2c2c4e250 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -46,7 +46,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
int ihl = skb->data - skb_transport_header(skb);
- struct xfrm_offload *xo = xfrm_offload(skb);
if (skb->transport_header != skb->network_header) {
memmove(skb_transport_header(skb),
@@ -54,8 +53,7 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
skb->network_header = skb->transport_header;
}
ip_hdr(skb)->tot_len = htons(skb->len + ihl);
- if (!xo || !(xo->flags & XFRM_GRO))
- skb_reset_transport_header(skb);
+ skb_reset_transport_header(skb);
return 0;
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 74986c8bed53..4606d57b6877 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -395,8 +395,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
if (ndev->cnf.stable_secret.initialized)
ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
- else
- ndev->cnf.addr_gen_mode = ipv6_devconf_dflt.addr_gen_mode;
ndev->cnf.mtu6 = dev->mtu;
ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
@@ -5153,7 +5151,9 @@ static inline size_t inet6_ifla6_size(void)
+ nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */
+ nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */
+ nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */
- + nla_total_size(sizeof(struct in6_addr)); /* IFLA_INET6_TOKEN */
+ + nla_total_size(sizeof(struct in6_addr)) /* IFLA_INET6_TOKEN */
+ + nla_total_size(1) /* IFLA_INET6_ADDR_GEN_MODE */
+ + 0;
}
static inline size_t inet6_if_nlmsg_size(void)
@@ -5834,32 +5834,31 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
loff_t *ppos)
{
int ret = 0;
- int new_val;
+ u32 new_val;
struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1;
struct net *net = (struct net *)ctl->extra2;
+ struct ctl_table tmp = {
+ .data = &new_val,
+ .maxlen = sizeof(new_val),
+ .mode = ctl->mode,
+ };
if (!rtnl_trylock())
return restart_syscall();
- ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ new_val = *((u32 *)ctl->data);
- if (write) {
- new_val = *((int *)ctl->data);
+ ret = proc_douintvec(&tmp, write, buffer, lenp, ppos);
+ if (ret != 0)
+ goto out;
+ if (write) {
if (check_addr_gen_mode(new_val) < 0) {
ret = -EINVAL;
goto out;
}
- /* request for default */
- if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) {
- ipv6_devconf_dflt.addr_gen_mode = new_val;
-
- /* request for individual net device */
- } else {
- if (!idev)
- goto out;
-
+ if (idev) {
if (check_stable_privacy(idev, net, new_val) < 0) {
ret = -EINVAL;
goto out;
@@ -5869,7 +5868,21 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
idev->cnf.addr_gen_mode = new_val;
addrconf_dev_config(idev->dev);
}
+ } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) {
+ struct net_device *dev;
+
+ net->ipv6.devconf_dflt->addr_gen_mode = new_val;
+ for_each_netdev(net, dev) {
+ idev = __in6_dev_get(dev);
+ if (idev &&
+ idev->cnf.addr_gen_mode != new_val) {
+ idev->cnf.addr_gen_mode = new_val;
+ addrconf_dev_config(idev->dev);
+ }
+ }
}
+
+ *((u32 *)ctl->data) = new_val;
}
out:
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f7b974249137..01efe2eb0a4f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -940,14 +940,14 @@ static int __init inet6_init(void)
err = proto_register(&pingv6_prot, 1);
if (err)
- goto out_unregister_ping_proto;
+ goto out_unregister_raw_proto;
/* We MUST register RAW sockets before we create the ICMP6,
* IGMP6, or NDISC control sockets.
*/
err = rawv6_init();
if (err)
- goto out_unregister_raw_proto;
+ goto out_unregister_ping_proto;
/* Register the family here so that the init calls below will
* be able to create sockets. (?? is this dangerous ??)
@@ -1115,11 +1115,11 @@ netfilter_fail:
igmp_fail:
ndisc_cleanup();
ndisc_fail:
- ip6_mr_cleanup();
+ icmpv6_cleanup();
icmp_fail:
- unregister_pernet_subsys(&inet6_net_ops);
+ ip6_mr_cleanup();
ipmr_fail:
- icmpv6_cleanup();
+ unregister_pernet_subsys(&inet6_net_ops);
register_pernet_fail:
sock_unregister(PF_INET6);
rtnl_unregister_all(PF_INET6);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b3b75034a266..402f03e23f44 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1480,7 +1480,8 @@ alloc_new_skb:
if (copy > length)
copy = length;
- if (!(rt->dst.dev->features&NETIF_F_SG)) {
+ if (!(rt->dst.dev->features&NETIF_F_SG) &&
+ skb_tailroom(skb) >= copy) {
unsigned int off;
off = skb->len;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 4eb62dec0b5d..f5947df9182e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -633,7 +633,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
IPPROTO_IPIP,
RT_TOS(eiph->tos), 0);
if (IS_ERR(rt) ||
- rt->dst.dev->type != ARPHRD_TUNNEL) {
+ rt->dst.dev->type != ARPHRD_TUNNEL6) {
if (!IS_ERR(rt))
ip_rt_put(rt);
goto out;
@@ -643,7 +643,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
ip_rt_put(rt);
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
skb2->dev) ||
- skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
+ skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
goto out;
}
@@ -1115,7 +1115,7 @@ route_lookup:
dst = NULL;
goto tx_err_link_failure;
}
- if (t->parms.collect_md &&
+ if (t->parms.collect_md && ipv6_addr_any(&fl6->saddr) &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6->daddr, 0, &fl6->saddr))
goto tx_err_link_failure;
@@ -1253,6 +1253,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPIP;
+ fl6.saddr = key->u.ipv6.src;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
dsfield = key->tos;
@@ -1325,6 +1326,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPV6;
+ fl6.saddr = key->u.ipv6.src;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
dsfield = key->tos;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 0642884bb08f..3c6479b32b97 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2084,7 +2084,8 @@ void ipv6_mc_dad_complete(struct inet6_dev *idev)
mld_send_initial_cr(idev);
idev->mc_dad_count--;
if (idev->mc_dad_count)
- mld_dad_start_timer(idev, idev->mc_maxdelay);
+ mld_dad_start_timer(idev,
+ unsolicited_report_interval(idev));
}
}
@@ -2096,7 +2097,8 @@ static void mld_dad_timer_expire(unsigned long data)
if (idev->mc_dad_count) {
idev->mc_dad_count--;
if (idev->mc_dad_count)
- mld_dad_start_timer(idev, idev->mc_maxdelay);
+ mld_dad_start_timer(idev,
+ unsolicited_report_interval(idev));
}
in6_dev_put(idev);
}
@@ -2454,7 +2456,8 @@ static void mld_ifc_timer_expire(unsigned long data)
if (idev->mc_ifc_count) {
idev->mc_ifc_count--;
if (idev->mc_ifc_count)
- mld_ifc_start_timer(idev, idev->mc_maxdelay);
+ mld_ifc_start_timer(idev,
+ unsolicited_report_interval(idev));
}
in6_dev_put(idev);
}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 7d2228be6fa5..f2b3b5879536 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -567,6 +567,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
return -ENOMEM;
j = 0;
+ memset(&mtpar, 0, sizeof(mtpar));
mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ipv6;
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 7c5e582b1af8..520e9592d402 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -56,6 +56,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
if (xo && (xo->flags & XFRM_GRO)) {
skb_mac_header_rebuild(skb);
+ skb_reset_transport_header(skb);
return -1;
}
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 9ad07a91708e..3c29da5defe6 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -51,7 +51,6 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
int ihl = skb->data - skb_transport_header(skb);
- struct xfrm_offload *xo = xfrm_offload(skb);
if (skb->transport_header != skb->network_header) {
memmove(skb_transport_header(skb),
@@ -60,8 +59,7 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
}
ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
sizeof(struct ipv6hdr));
- if (!xo || !(xo->flags & XFRM_GRO))
- skb_reset_transport_header(skb);
+ skb_reset_transport_header(skb);
return 0;
}
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 8ae87d4ec5ff..29dae7f2ff14 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -170,9 +170,11 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (toobig && xfrm6_local_dontfrag(skb)) {
xfrm6_local_rxpmtu(skb, mtu);
+ kfree_skb(skb);
return -EMSGSIZE;
} else if (!skb->ignore_df && toobig && skb->sk) {
xfrm_local_error(skb, mtu);
+ kfree_skb(skb);
return -EMSGSIZE;
}
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 79651bc71bf0..7d89acf2fdd6 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -119,7 +119,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
struct flowi6 *fl6 = &fl->u.ip6;
int onlyproto = 0;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
- u16 offset = sizeof(*hdr);
+ u32 offset = sizeof(*hdr);
struct ipv6_opt_hdr *exthdr;
const unsigned char *nh = skb_network_header(skb);
u16 nhoff = IP6CB(skb)->nhoff;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ff9a387097fb..3e7ec1b07027 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1787,7 +1787,7 @@ static __net_exit void l2tp_exit_net(struct net *net)
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- (void)l2tp_tunnel_delete(tunnel);
+ l2tp_tunnel_delete(tunnel);
}
rcu_read_unlock_bh();
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 49f9afd4c607..8068f5c05408 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -280,7 +280,7 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info
l2tp_tunnel_notify(&l2tp_nl_family, info,
tunnel, L2TP_CMD_TUNNEL_DELETE);
- (void) l2tp_tunnel_delete(tunnel);
+ l2tp_tunnel_delete(tunnel);
l2tp_tunnel_dec_refcount(tunnel);
@@ -761,8 +761,6 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
if ((session->ifname[0] &&
nla_put_string(skb, L2TP_ATTR_IFNAME, session->ifname)) ||
- (session->offset &&
- nla_put_u16(skb, L2TP_ATTR_OFFSET, session->offset)) ||
(session->cookie_len &&
nla_put(skb, L2TP_ATTR_COOKIE, session->cookie_len,
&session->cookie[0])) ||
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 6541e8103187..93d4c72e4ee5 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -722,6 +722,15 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
.encap = L2TP_ENCAPTYPE_UDP,
.debug = 0,
};
+
+ /* Prevent l2tp_tunnel_register() from trying to set up
+ * a kernel socket.
+ */
+ if (fd < 0) {
+ error = -EBADF;
+ goto end;
+ }
+
error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel);
if (error < 0)
goto end;
@@ -746,6 +755,12 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
session = l2tp_session_get(sock_net(sk), tunnel, session_id);
if (session) {
drop_refcnt = true;
+
+ if (session->pwtype != L2TP_PWTYPE_PPP) {
+ error = -EPROTOTYPE;
+ goto end;
+ }
+
ps = l2tp_session_priv(session);
/* Using a pre-existing session is fine as long as it hasn't
@@ -1199,13 +1214,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
l2tp_session_get(sock_net(sk), tunnel,
stats.session_id);
- if (session) {
- err = pppol2tp_session_ioctl(session, cmd,
- arg);
+ if (!session) {
+ err = -EBADR;
+ break;
+ }
+ if (session->pwtype != L2TP_PWTYPE_PPP) {
l2tp_session_dec_refcount(session);
- } else {
err = -EBADR;
+ break;
}
+
+ err = pppol2tp_session_ioctl(session, cmd, arg);
+ l2tp_session_dec_refcount(session);
break;
}
#ifdef CONFIG_XFRM
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 4fed1136adaf..23fdda66b2c9 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -23,7 +23,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, struct mesh_path *mpath);
static u32 mesh_table_hash(const void *addr, u32 len, u32 seed)
{
/* Use last four bytes of hw addr as hash index */
- return jhash_1word(*(u32 *)(addr+2), seed);
+ return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed);
}
static const struct rhashtable_params mesh_rht_params = {
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 6bb0029873b7..7fa9ad079dd4 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3185,6 +3185,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
u8 max_subframes = sta->sta.max_amsdu_subframes;
int max_frags = local->hw.max_tx_fragments;
int max_amsdu_len = sta->sta.max_amsdu_len;
+ int orig_truesize;
__be16 len;
void *data;
bool ret = false;
@@ -3218,6 +3219,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
if (!head)
goto out;
+ orig_truesize = head->truesize;
orig_len = head->len;
if (skb->len + head->len > max_amsdu_len)
@@ -3272,6 +3274,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
*frag_tail = skb;
out_recalc:
+ fq->memory_usage += head->truesize - orig_truesize;
if (head->len != orig_len) {
flow->backlog += head->len - orig_len;
tin->backlog_bytes += head->len - orig_len;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index ad99c1ceea6f..edc0f883cd2f 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -119,6 +119,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
+ local_bh_disable();
+
s = this_cpu_ptr(dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.inpkts++;
@@ -139,6 +141,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->cnt.inpkts++;
s->cnt.inbytes += skb->len;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
}
@@ -153,6 +157,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
+ local_bh_disable();
+
s = this_cpu_ptr(dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.outpkts++;
@@ -173,6 +179,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->cnt.outpkts++;
s->cnt.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
}
@@ -183,6 +191,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
struct netns_ipvs *ipvs = svc->ipvs;
struct ip_vs_cpu_stats *s;
+ local_bh_disable();
+
s = this_cpu_ptr(cp->dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.conns++;
@@ -197,6 +207,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
u64_stats_update_begin(&s->syncp);
s->cnt.conns++;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
@@ -1968,13 +1980,20 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
- if (sysctl_expire_nodest_conn(ipvs)) {
+ __u32 flags = cp->flags;
+
+ /* when timer already started, silently drop the packet.*/
+ if (timer_pending(&cp->timer))
+ __ip_vs_conn_put(cp);
+ else
+ ip_vs_conn_put(cp);
+
+ if (sysctl_expire_nodest_conn(ipvs) &&
+ !(flags & IP_VS_CONN_F_ONE_PACKET)) {
/* try to expire the connection immediately */
ip_vs_conn_expire_now(cp);
}
- /* don't restart its timer, and silently
- drop the packet. */
- __ip_vs_conn_put(cp);
+
return NF_DROP;
}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 061fa2fe5bc0..73d712b7d83e 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2252,6 +2252,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user
u->udp_timeout);
#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
@@ -2383,14 +2395,12 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
struct ipvs_sync_daemon_cfg cfg;
memset(&cfg, 0, sizeof(cfg));
- strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
- sizeof(cfg.mcast_ifn));
+ ret = -EINVAL;
+ if (strscpy(cfg.mcast_ifn, dm->mcast_ifn,
+ sizeof(cfg.mcast_ifn)) <= 0)
+ goto out_dec;
cfg.syncid = dm->syncid;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &cfg, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
@@ -2426,12 +2436,19 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
}
}
+ if ((cmd == IP_VS_SO_SET_ADD || cmd == IP_VS_SO_SET_EDIT) &&
+ strnlen(usvc.sched_name, IP_VS_SCHEDNAME_MAXLEN) ==
+ IP_VS_SCHEDNAME_MAXLEN) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
/* Check for valid protocol: TCP or UDP or SCTP, even for fwmark!=0 */
if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP &&
usvc.protocol != IPPROTO_SCTP) {
- pr_err("set_ctl: invalid protocol: %d %pI4:%d %s\n",
+ pr_err("set_ctl: invalid protocol: %d %pI4:%d\n",
usvc.protocol, &usvc.addr.ip,
- ntohs(usvc.port), usvc.sched_name);
+ ntohs(usvc.port));
ret = -EFAULT;
goto out_unlock;
}
@@ -2853,7 +2870,7 @@ static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = {
static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = {
[IPVS_DAEMON_ATTR_STATE] = { .type = NLA_U32 },
[IPVS_DAEMON_ATTR_MCAST_IFN] = { .type = NLA_NUL_STRING,
- .len = IP_VS_IFNAME_MAXLEN },
+ .len = IP_VS_IFNAME_MAXLEN - 1 },
[IPVS_DAEMON_ATTR_SYNC_ID] = { .type = NLA_U32 },
[IPVS_DAEMON_ATTR_SYNC_MAXLEN] = { .type = NLA_U16 },
[IPVS_DAEMON_ATTR_MCAST_GROUP] = { .type = NLA_U32 },
@@ -2871,7 +2888,7 @@ static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = {
[IPVS_SVC_ATTR_PORT] = { .type = NLA_U16 },
[IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 },
[IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING,
- .len = IP_VS_SCHEDNAME_MAXLEN },
+ .len = IP_VS_SCHEDNAME_MAXLEN - 1 },
[IPVS_SVC_ATTR_PE_NAME] = { .type = NLA_NUL_STRING,
.len = IP_VS_PENAME_MAXLEN },
[IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY,
@@ -3483,12 +3500,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
if (ipvs->mixed_address_family_dests > 0)
return -EINVAL;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
return ret;
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 0e5b64a75da0..9f1aa78e837d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -48,6 +48,7 @@
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/kernel.h>
+#include <linux/sched/signal.h>
#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */
@@ -1359,15 +1360,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val)
/*
* Specifiy default interface for outgoing multicasts
*/
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
{
- struct net_device *dev;
struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
-
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1395,19 +1390,14 @@ static int set_mcast_if(struct sock *sk, char *ifname)
* in the in_addr structure passed in as a parameter.
*/
static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
{
- struct net *net = sock_net(sk);
struct ip_mreqn mreq;
- struct net_device *dev;
int ret;
memset(&mreq, 0, sizeof(mreq));
memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1422,15 +1412,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
#ifdef CONFIG_IP_VS_IPV6
static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
- char *ifname)
+ struct net_device *dev)
{
- struct net *net = sock_net(sk);
- struct net_device *dev;
int ret;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1442,24 +1427,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
}
#endif
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
{
- struct net *net = sock_net(sock->sk);
- struct net_device *dev;
__be32 addr;
struct sockaddr_in sin;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
-
addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
if (!addr)
pr_err("You probably need to specify IP address on "
"multicast interface.\n");
IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
- ifname, &addr);
+ dev->name, &addr);
/* Now bind the socket with the address of multicast interface */
sin.sin_family = AF_INET;
@@ -1492,7 +1471,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1504,9 +1484,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
- result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+ *sock_ret = sock;
+ result = set_mcast_if(sock->sk, dev);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
goto error;
@@ -1521,7 +1502,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
set_sock_size(sock->sk, 1, result);
if (AF_INET == ipvs->mcfg.mcast_af)
- result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+ result = bind_mcastif_addr(sock, dev);
else
result = 0;
if (result < 0) {
@@ -1537,19 +1518,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
- int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1561,8 +1541,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
+ *sock_ret = sock;
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = SK_CAN_REUSE;
result = sysctl_sync_sock_size(ipvs);
@@ -1570,7 +1551,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
set_sock_size(sock->sk, 0, result);
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
- sock->sk->sk_bound_dev_if = ifindex;
+ sock->sk->sk_bound_dev_if = dev->ifindex;
result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
@@ -1581,21 +1562,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
#ifdef CONFIG_IP_VS_IPV6
if (ipvs->bcfg.mcast_af == AF_INET6)
result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
else
#endif
result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
if (result < 0) {
pr_err("Error joining to the multicast group\n");
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
@@ -1780,13 +1760,12 @@ static int sync_thread_backup(void *data)
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo;
+ struct ip_vs_sync_thread_data *tinfo = NULL;
struct task_struct **array = NULL, *task;
- struct socket *sock;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
- int id, count, hlen;
+ int id = 0, count, hlen;
int result = -ENOMEM;
u16 mtu, min_mtu;
@@ -1794,6 +1773,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ /* Do not hold one mutex and then to block on another */
+ for (;;) {
+ rtnl_lock();
+ if (mutex_trylock(&ipvs->sync_mutex))
+ break;
+ rtnl_unlock();
+ mutex_lock(&ipvs->sync_mutex);
+ if (rtnl_trylock())
+ break;
+ mutex_unlock(&ipvs->sync_mutex);
+ }
+
if (!ipvs->sync_state) {
count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
ipvs->threads_mask = count - 1;
@@ -1812,7 +1803,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
- return -ENODEV;
+ result = -ENODEV;
+ goto out_early;
}
hlen = (AF_INET6 == c->mcast_af) ?
sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
@@ -1829,26 +1821,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
c->sync_maxlen = mtu - hlen;
if (state == IP_VS_STATE_MASTER) {
+ result = -EEXIST;
if (ipvs->ms)
- return -EEXIST;
+ goto out_early;
ipvs->mcfg = *c;
name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
+ result = -EEXIST;
if (ipvs->backup_threads)
- return -EEXIST;
+ goto out_early;
ipvs->bcfg = *c;
name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
} else {
- return -EINVAL;
+ result = -EINVAL;
+ goto out_early;
}
if (state == IP_VS_STATE_MASTER) {
struct ipvs_master_sync_state *ms;
+ result = -ENOMEM;
ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
if (!ipvs->ms)
goto out;
@@ -1864,39 +1860,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
} else {
array = kcalloc(count, sizeof(struct task_struct *),
GFP_KERNEL);
+ result = -ENOMEM;
if (!array)
goto out;
}
- tinfo = NULL;
for (id = 0; id < count; id++) {
- if (state == IP_VS_STATE_MASTER)
- sock = make_send_sock(ipvs, id);
- else
- sock = make_receive_sock(ipvs, id, dev->ifindex);
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto outtinfo;
- }
+ result = -ENOMEM;
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
- goto outsocket;
+ goto out;
tinfo->ipvs = ipvs;
- tinfo->sock = sock;
+ tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
- goto outtinfo;
+ goto out;
} else {
tinfo->buf = NULL;
}
tinfo->id = id;
+ if (state == IP_VS_STATE_MASTER)
+ result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+ else
+ result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+ if (result < 0)
+ goto out;
task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
if (IS_ERR(task)) {
result = PTR_ERR(task);
- goto outtinfo;
+ goto out;
}
tinfo = NULL;
if (state == IP_VS_STATE_MASTER)
@@ -1913,20 +1908,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
+
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outsocket:
- sock_release(sock);
-
-outtinfo:
- if (tinfo) {
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
- }
+out:
+ /* We do not need RTNL lock anymore, release it here so that
+ * sock_release below and in the kthreads can use rtnl_lock
+ * to leave the mcast group.
+ */
+ rtnl_unlock();
count = id;
while (count-- > 0) {
if (state == IP_VS_STATE_MASTER)
@@ -1934,13 +1929,23 @@ outtinfo:
else
kthread_stop(array[count]);
}
- kfree(array);
-
-out:
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
+ mutex_unlock(&ipvs->sync_mutex);
+ if (tinfo) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ kfree(array);
+ return result;
+
+out_early:
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
return result;
}
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 0af6b01f8a08..a06a4b9a5d05 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -168,7 +168,7 @@ static inline bool crosses_local_route_boundary(int skb_af, struct sk_buff *skb,
bool new_rt_is_local)
{
bool rt_mode_allow_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
- bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
+ bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_NON_LOCAL);
bool rt_mode_allow_redirect = !!(rt_mode & IP_VS_RT_MODE_RDR);
bool source_is_loopback;
bool old_rt_is_local;
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 8bb152a7cca4..cdc744aa5889 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -440,6 +440,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
if (write) {
struct ctl_table tmp = *table;
+ /* proc_dostring() can append to existing strings, so we need to
+ * initialize it as an empty string.
+ */
+ buf[0] = '\0';
tmp.data = buf;
r = proc_dostring(&tmp, write, buffer, lenp, ppos);
if (r)
@@ -458,14 +462,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
mutex_unlock(&nf_log_mutex);
} else {
+ struct ctl_table tmp = *table;
+
+ tmp.data = buf;
mutex_lock(&nf_log_mutex);
logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
if (!logger)
- table->data = "NONE";
+ strlcpy(buf, "NONE", sizeof(buf));
else
- table->data = logger->name;
- r = proc_dostring(table, write, buffer, lenp, ppos);
+ strlcpy(buf, logger->name, sizeof(buf));
mutex_unlock(&nf_log_mutex);
+ r = proc_dostring(&tmp, write, buffer, lenp, ppos);
}
return r;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 595004098410..4d424069b5d8 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2251,41 +2251,46 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
}
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
- if (nft_is_active_next(net, old_rule)) {
- trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
- old_rule);
- if (trans == NULL) {
- err = -ENOMEM;
- goto err2;
- }
- nft_deactivate_next(net, old_rule);
- chain->use--;
- list_add_tail_rcu(&rule->list, &old_rule->list);
- } else {
+ if (!nft_is_active_next(net, old_rule)) {
err = -ENOENT;
goto err2;
}
- } else if (nlh->nlmsg_flags & NLM_F_APPEND)
- if (old_rule)
- list_add_rcu(&rule->list, &old_rule->list);
- else
- list_add_tail_rcu(&rule->list, &chain->rules);
- else {
- if (old_rule)
- list_add_tail_rcu(&rule->list, &old_rule->list);
- else
- list_add_rcu(&rule->list, &chain->rules);
- }
+ trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+ old_rule);
+ if (trans == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+ nft_deactivate_next(net, old_rule);
+ chain->use--;
- if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
- err = -ENOMEM;
- goto err3;
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ } else {
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ if (nlh->nlmsg_flags & NLM_F_APPEND) {
+ if (old_rule)
+ list_add_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_tail_rcu(&rule->list, &chain->rules);
+ } else {
+ if (old_rule)
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_rcu(&rule->list, &chain->rules);
+ }
}
chain->use++;
return 0;
-err3:
- list_del_rcu(&rule->list);
err2:
nf_tables_rule_destroy(&ctx, rule);
err1:
@@ -2559,12 +2564,13 @@ static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
u32 id = ntohl(nla_get_be32(nla));
list_for_each_entry(trans, &net->nft.commit_list, list) {
- struct nft_set *set = nft_trans_set(trans);
+ if (trans->msg_type == NFT_MSG_NEWSET) {
+ struct nft_set *set = nft_trans_set(trans);
- if (trans->msg_type == NFT_MSG_NEWSET &&
- id == nft_trans_set_id(trans) &&
- nft_active_genmask(set, genmask))
- return set;
+ if (id == nft_trans_set_id(trans) &&
+ nft_active_genmask(set, genmask))
+ return set;
+ }
}
return ERR_PTR(-ENOENT);
}
@@ -4060,6 +4066,7 @@ static int nft_flush_set(const struct nft_ctx *ctx,
}
set->ndeact++;
+ nft_set_elem_deactivate(ctx->net, set, elem);
nft_trans_elem_set(trans) = set;
nft_trans_elem(trans) = *elem;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 1678e9e75e8e..2cded8ee6d30 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -875,22 +875,26 @@ static int nft_ct_helper_obj_dump(struct sk_buff *skb,
struct nft_object *obj, bool reset)
{
const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
- const struct nf_conntrack_helper *helper = priv->helper4;
+ const struct nf_conntrack_helper *helper;
u16 family;
+ if (priv->helper4 && priv->helper6) {
+ family = NFPROTO_INET;
+ helper = priv->helper4;
+ } else if (priv->helper6) {
+ family = NFPROTO_IPV6;
+ helper = priv->helper6;
+ } else {
+ family = NFPROTO_IPV4;
+ helper = priv->helper4;
+ }
+
if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name))
return -1;
if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto))
return -1;
- if (priv->helper4 && priv->helper6)
- family = NFPROTO_INET;
- else if (priv->helper6)
- family = NFPROTO_IPV6;
- else
- family = NFPROTO_IPV4;
-
if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family)))
return -1;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 3e012d578ccd..70cf781ececb 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1812,6 +1812,8 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (msg->msg_namelen) {
err = -EINVAL;
+ if (msg->msg_namelen < sizeof(struct sockaddr_nl))
+ goto out;
if (addr->nl_family != AF_NETLINK)
goto out;
dst_portid = addr->nl_pid;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 88d4d3ede99d..baf0faad8f86 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2895,13 +2895,17 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
if (skb == NULL)
goto out_unlock;
- skb_set_network_header(skb, reserve);
+ skb_reset_network_header(skb);
err = -EINVAL;
if (sock->type == SOCK_DGRAM) {
offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
if (unlikely(offset < 0))
goto out_free;
+ } else if (reserve) {
+ skb_reserve(skb, -reserve);
+ if (len < reserve)
+ skb_reset_network_header(skb);
}
/* Returns -EFAULT on error */
@@ -4251,6 +4255,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
}
if (req->tp_block_nr) {
+ unsigned int min_frame_size;
+
/* Sanity tests and some calculations */
err = -EBUSY;
if (unlikely(rb->pg_vec))
@@ -4273,12 +4279,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
goto out;
if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
goto out;
+ min_frame_size = po->tp_hdrlen + po->tp_reserve;
if (po->tp_version >= TPACKET_V3 &&
- req->tp_block_size <=
- BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr))
+ req->tp_block_size <
+ BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size)
goto out;
- if (unlikely(req->tp_frame_size < po->tp_hdrlen +
- po->tp_reserve))
+ if (unlikely(req->tp_frame_size < min_frame_size))
goto out;
if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1)))
goto out;
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index ff4864d550b8..852a036c775e 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -133,22 +133,52 @@ static int rxrpc_open_socket(struct rxrpc_local *local)
}
}
- /* we want to receive ICMP errors */
- opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
- (char *) &opt, sizeof(opt));
- if (ret < 0) {
- _debug("setsockopt failed");
- goto error;
- }
+ switch (local->srx.transport.family) {
+ case AF_INET6:
+ /* we want to receive ICMPv6 errors */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
- /* we want to set the don't fragment bit */
- opt = IP_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
- (char *) &opt, sizeof(opt));
- if (ret < 0) {
- _debug("setsockopt failed");
- goto error;
+ /* we want to set the don't fragment bit */
+ opt = IPV6_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+
+ /* Fall through and set IPv4 options too otherwise we don't get
+ * errors from IPv4 packets sent through the IPv6 socket.
+ */
+
+ case AF_INET:
+ /* we want to receive ICMP errors */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+
+ /* we want to set the don't fragment bit */
+ opt = IP_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+ break;
+
+ default:
+ BUG();
}
/* set the socket up */
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index c5ffbc1cc57d..d8a60011567f 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -43,6 +43,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
struct tc_action_net *tn = net_generic(net, sample_net_id);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
struct psample_group *psample_group;
+ u32 rate;
struct tc_sample *parm;
u32 psample_group_num;
struct tcf_sample *s;
@@ -80,6 +81,11 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
return -EEXIST;
}
+ rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+ if (!rate) {
+ tcf_idr_release(*a, bind);
+ return -EINVAL;
+ }
psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
psample_group = psample_group_get(net, psample_group_num);
if (!psample_group) {
@@ -91,7 +97,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
spin_lock_bh(&s->tcf_lock);
s->tcf_action = parm->action;
- s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+ s->rate = rate;
s->psample_group_num = psample_group_num;
RCU_INIT_POINTER(s->psample_group, psample_group);
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 856fa79d4ffd..621bc1d5b057 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -126,6 +126,11 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
static void *mall_get(struct tcf_proto *tp, u32 handle)
{
+ struct cls_mall_head *head = rtnl_dereference(tp->root);
+
+ if (head && head->handle == handle)
+ return head;
+
return NULL;
}
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 05be058255ea..b3f44daf3af6 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -1447,7 +1447,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
* the outstanding bytes for this chunk, so only
* count bytes associated with a transport.
*/
- if (transport) {
+ if (transport && !tchunk->tsn_gap_acked) {
/* If this chunk is being used for RTT
* measurement, calculate the RTT and update
* the RTO using this value.
@@ -1459,14 +1459,34 @@ static void sctp_check_transmitted(struct sctp_outq *q,
* first instance of the packet or a later
* instance).
*/
- if (!tchunk->tsn_gap_acked &&
- !sctp_chunk_retransmitted(tchunk) &&
+ if (!sctp_chunk_retransmitted(tchunk) &&
tchunk->rtt_in_progress) {
tchunk->rtt_in_progress = 0;
rtt = jiffies - tchunk->sent_at;
sctp_transport_update_rto(transport,
rtt);
}
+
+ if (TSN_lte(tsn, sack_ctsn)) {
+ /*
+ * SFR-CACC algorithm:
+ * 2) If the SACK contains gap acks
+ * and the flag CHANGEOVER_ACTIVE is
+ * set the receiver of the SACK MUST
+ * take the following action:
+ *
+ * B) For each TSN t being acked that
+ * has not been acked in any SACK so
+ * far, set cacc_saw_newack to 1 for
+ * the destination that the TSN was
+ * sent to.
+ */
+ if (sack->num_gap_ack_blocks &&
+ q->asoc->peer.primary_path->cacc.
+ changeover_active)
+ transport->cacc.cacc_saw_newack
+ = 1;
+ }
}
/* If the chunk hasn't been marked as ACKED,
@@ -1498,28 +1518,6 @@ static void sctp_check_transmitted(struct sctp_outq *q,
restart_timer = 1;
forward_progress = true;
- if (!tchunk->tsn_gap_acked) {
- /*
- * SFR-CACC algorithm:
- * 2) If the SACK contains gap acks
- * and the flag CHANGEOVER_ACTIVE is
- * set the receiver of the SACK MUST
- * take the following action:
- *
- * B) For each TSN t being acked that
- * has not been acked in any SACK so
- * far, set cacc_saw_newack to 1 for
- * the destination that the TSN was
- * sent to.
- */
- if (transport &&
- sack->num_gap_ack_blocks &&
- q->asoc->peer.primary_path->cacc.
- changeover_active)
- transport->cacc.cacc_saw_newack
- = 1;
- }
-
list_add_tail(&tchunk->transmitted_list,
&q->sacked);
} else {
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e1a3ae4f3cab..b58adcf1a971 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -606,6 +606,7 @@ out:
static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
{
/* No address mapping for V4 sockets */
+ memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
return sizeof(struct sockaddr_in);
}
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 880804982718..eff394ebc0ca 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -136,11 +136,9 @@ static int smc_release(struct socket *sock)
smc = smc_sk(sk);
/* cleanup for a dangling non-blocking connect */
- if (smc->connect_info && sk->sk_state == SMC_INIT)
+ if (smc->connect_nonblock && sk->sk_state == SMC_INIT)
tcp_abort(smc->clcsock->sk, ECONNABORTED);
flush_work(&smc->connect_work);
- kfree(smc->connect_info);
- smc->connect_info = NULL;
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
@@ -169,10 +167,9 @@ static int smc_release(struct socket *sock)
if (sk->sk_state == SMC_CLOSED) {
if (smc->clcsock) {
- mutex_lock(&smc->clcsock_release_lock);
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- mutex_unlock(&smc->clcsock_release_lock);
+ release_sock(sk);
+ smc_clcsock_release(smc);
+ lock_sock(sk);
}
if (!smc->use_fallback)
smc_conn_free(&smc->conn);
@@ -448,12 +445,22 @@ static void smc_link_save_peer_info(struct smc_link *link,
link->peer_mtu = clc->qp_mtu;
}
+static void smc_switch_to_fallback(struct smc_sock *smc)
+{
+ smc->use_fallback = true;
+ if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
+ smc->clcsock->file = smc->sk.sk_socket->file;
+ smc->clcsock->file->private_data = smc->clcsock;
+ }
+}
+
/* fall back during connect */
static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
{
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = reason_code;
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
return 0;
@@ -493,46 +500,41 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code,
mutex_unlock(&smc_client_lgr_pending);
smc_conn_free(&smc->conn);
+ smc->connect_nonblock = 0;
return reason_code;
}
/* check if there is a rdma device available for this connection. */
/* called for connect and listen */
-static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
- u8 *ibport, unsigned short vlan_id, u8 gid[])
+static int smc_find_rdma_device(struct smc_sock *smc, struct smc_init_info *ini)
{
- int reason_code = 0;
-
/* PNET table look up: search active ib_device and port
* within same PNETID that also contains the ethernet device
* used for the internal TCP socket
*/
- smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport, vlan_id,
- gid);
- if (!(*ibdev))
- reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
-
- return reason_code;
+ smc_pnet_find_roce_resource(smc->clcsock->sk, ini);
+ if (!ini->ib_dev)
+ return SMC_CLC_DECL_NOSMCRDEV;
+ return 0;
}
/* check if there is an ISM device available for this connection. */
/* called for connect and listen */
-static int smc_check_ism(struct smc_sock *smc, struct smcd_dev **ismdev)
+static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini)
{
/* Find ISM device with same PNETID as connecting interface */
- smc_pnet_find_ism_resource(smc->clcsock->sk, ismdev);
- if (!(*ismdev))
- return SMC_CLC_DECL_CNFERR; /* configuration error */
+ smc_pnet_find_ism_resource(smc->clcsock->sk, ini);
+ if (!ini->ism_dev)
+ return SMC_CLC_DECL_NOSMCDDEV;
return 0;
}
/* Check for VLAN ID and register it on ISM device just for CLC handshake */
static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
- struct smcd_dev *ismdev,
- unsigned short vlan_id)
+ struct smc_init_info *ini)
{
- if (vlan_id && smc_ism_get_vlan(ismdev, vlan_id))
- return SMC_CLC_DECL_CNFERR;
+ if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev, ini->vlan_id))
+ return SMC_CLC_DECL_ISMVLANERR;
return 0;
}
@@ -540,12 +542,11 @@ static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
* used, the VLAN ID will be registered again during the connection setup.
*/
static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
- struct smcd_dev *ismdev,
- unsigned short vlan_id)
+ struct smc_init_info *ini)
{
if (!is_smcd)
return 0;
- if (vlan_id && smc_ism_put_vlan(ismdev, vlan_id))
+ if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev, ini->vlan_id))
return SMC_CLC_DECL_CNFERR;
return 0;
}
@@ -553,13 +554,12 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
/* CLC handshake during connect */
static int smc_connect_clc(struct smc_sock *smc, int smc_type,
struct smc_clc_msg_accept_confirm *aclc,
- struct smc_ib_device *ibdev, u8 ibport,
- u8 gid[], struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
int rc = 0;
/* do inband token exchange */
- rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev);
+ rc = smc_clc_send_proposal(smc, smc_type, ini);
if (rc)
return rc;
/* receive SMC Accept CLC message */
@@ -570,23 +570,19 @@ static int smc_connect_clc(struct smc_sock *smc, int smc_type,
/* setup for RDMA connection of client */
static int smc_connect_rdma(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *aclc,
- struct smc_ib_device *ibdev, u8 ibport)
+ struct smc_init_info *ini)
{
- int local_contact = SMC_FIRST_CONTACT;
struct smc_link *link;
int reason_code = 0;
+ ini->is_smcd = false;
+ ini->ib_lcl = &aclc->lcl;
+ ini->ib_clcqpn = ntoh24(aclc->qpn);
+ ini->srv_first_contact = aclc->hdr.flag;
+
mutex_lock(&smc_client_lgr_pending);
- local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
- ibport, ntoh24(aclc->qpn), &aclc->lcl,
- NULL, 0);
- if (local_contact < 0) {
- if (local_contact == -ENOMEM)
- reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- else if (local_contact == -ENOLINK)
- reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
- else
- reason_code = SMC_CLC_DECL_INTERR; /* other error */
+ reason_code = smc_conn_create(smc, ini);
+ if (reason_code) {
mutex_unlock(&smc_client_lgr_pending);
return reason_code;
}
@@ -596,45 +592,48 @@ static int smc_connect_rdma(struct smc_sock *smc,
/* create send buffer and rmb */
if (smc_buf_create(smc, false))
- return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
+ ini->cln_first_contact);
- if (local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_link_save_peer_info(link, aclc);
if (smc_rmb_rtoken_handling(&smc->conn, aclc))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
- local_contact);
+ ini->cln_first_contact);
smc_close_init(smc);
smc_rx_init(smc);
- if (local_contact == SMC_FIRST_CONTACT) {
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
if (smc_ib_ready_link(link))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
- local_contact);
+ ini->cln_first_contact);
} else {
if (smc_reg_rmb(link, smc->conn.rmb_desc, true))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
- local_contact);
+ ini->cln_first_contact);
}
smc_rmb_sync_sg_for_device(&smc->conn);
reason_code = smc_clc_send_confirm(smc);
if (reason_code)
- return smc_connect_abort(smc, reason_code, local_contact);
+ return smc_connect_abort(smc, reason_code,
+ ini->cln_first_contact);
smc_tx_init(smc);
- if (local_contact == SMC_FIRST_CONTACT) {
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
/* QP confirmation over RoCE fabric */
reason_code = smc_clnt_conf_first_link(smc);
if (reason_code)
return smc_connect_abort(smc, reason_code,
- local_contact);
+ ini->cln_first_contact);
}
mutex_unlock(&smc_client_lgr_pending);
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
@@ -644,23 +643,26 @@ static int smc_connect_rdma(struct smc_sock *smc,
/* setup for ISM connection of client */
static int smc_connect_ism(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *aclc,
- struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
- int local_contact = SMC_FIRST_CONTACT;
int rc = 0;
+ ini->is_smcd = true;
+ ini->ism_gid = aclc->gid;
+ ini->srv_first_contact = aclc->hdr.flag;
+
/* there is only one lgr role for SMC-D; use server lock */
mutex_lock(&smc_server_lgr_pending);
- local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0,
- NULL, ismdev, aclc->gid);
- if (local_contact < 0) {
+ rc = smc_conn_create(smc, ini);
+ if (rc) {
mutex_unlock(&smc_server_lgr_pending);
- return SMC_CLC_DECL_MEM;
+ return rc;
}
/* Create send and receive buffers */
if (smc_buf_create(smc, true))
- return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
+ ini->cln_first_contact);
smc_conn_save_peer_info(smc, aclc);
smc_close_init(smc);
@@ -669,10 +671,11 @@ static int smc_connect_ism(struct smc_sock *smc,
rc = smc_clc_send_confirm(smc);
if (rc)
- return smc_connect_abort(smc, rc, local_contact);
+ return smc_connect_abort(smc, rc, ini->cln_first_contact);
mutex_unlock(&smc_server_lgr_pending);
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
@@ -684,13 +687,9 @@ static int __smc_connect(struct smc_sock *smc)
{
bool ism_supported = false, rdma_supported = false;
struct smc_clc_msg_accept_confirm aclc;
- struct smc_ib_device *ibdev;
- struct smcd_dev *ismdev;
- u8 gid[SMC_GID_SIZE];
- unsigned short vlan;
+ struct smc_init_info ini = {0};
int smc_type;
int rc = 0;
- u8 ibport;
sock_hold(&smc->sk); /* sock put in passive closing */
@@ -705,20 +704,21 @@ static int __smc_connect(struct smc_sock *smc)
if (using_ipsec(smc))
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
- /* check for VLAN ID */
- if (smc_vlan_by_tcpsk(smc->clcsock, &vlan))
- return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+ /* get vlan id from IP device */
+ if (smc_vlan_by_tcpsk(smc->clcsock, &ini))
+ return smc_connect_decline_fallback(smc,
+ SMC_CLC_DECL_GETVLANERR);
/* check if there is an ism device available */
- if (!smc_check_ism(smc, &ismdev) &&
- !smc_connect_ism_vlan_setup(smc, ismdev, vlan)) {
+ if (!smc_find_ism_device(smc, &ini) &&
+ !smc_connect_ism_vlan_setup(smc, &ini)) {
/* ISM is supported for this connection */
ism_supported = true;
smc_type = SMC_TYPE_D;
}
/* check if there is a rdma device available */
- if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) {
+ if (!smc_find_rdma_device(smc, &ini)) {
/* RDMA is supported for this connection */
rdma_supported = true;
if (ism_supported)
@@ -732,25 +732,25 @@ static int __smc_connect(struct smc_sock *smc)
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
/* perform CLC handshake */
- rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
+ rc = smc_connect_clc(smc, smc_type, &aclc, &ini);
if (rc) {
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return smc_connect_decline_fallback(smc, rc);
}
/* depending on previous steps, connect using rdma or ism */
if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
- rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
+ rc = smc_connect_rdma(smc, &aclc, &ini);
else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
- rc = smc_connect_ism(smc, &aclc, ismdev);
+ rc = smc_connect_ism(smc, &aclc, &ini);
else
rc = SMC_CLC_DECL_MODEUNSUPP;
if (rc) {
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return smc_connect_decline_fallback(smc, rc);
}
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return 0;
}
@@ -758,17 +758,30 @@ static void smc_connect_work(struct work_struct *work)
{
struct smc_sock *smc = container_of(work, struct smc_sock,
connect_work);
- int rc;
+ long timeo = smc->sk.sk_sndtimeo;
+ int rc = 0;
- lock_sock(&smc->sk);
- rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
- smc->connect_info->alen, smc->connect_info->flags);
+ if (!timeo)
+ timeo = MAX_SCHEDULE_TIMEOUT;
+ lock_sock(smc->clcsock->sk);
if (smc->clcsock->sk->sk_err) {
smc->sk.sk_err = smc->clcsock->sk->sk_err;
- goto out;
- }
- if (rc < 0) {
- smc->sk.sk_err = -rc;
+ } else if ((1 << smc->clcsock->sk->sk_state) &
+ (TCPF_SYN_SENT | TCP_SYN_RECV)) {
+ rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo);
+ if ((rc == -EPIPE) &&
+ ((1 << smc->clcsock->sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)))
+ rc = 0;
+ }
+ release_sock(smc->clcsock->sk);
+ lock_sock(&smc->sk);
+ if (rc != 0 || smc->sk.sk_err) {
+ smc->sk.sk_state = SMC_CLOSED;
+ if (rc == -EPIPE || rc == -EAGAIN)
+ smc->sk.sk_err = EPIPE;
+ else if (signal_pending(current))
+ smc->sk.sk_err = -sock_intr_errno(timeo);
goto out;
}
@@ -777,12 +790,14 @@ static void smc_connect_work(struct work_struct *work)
smc->sk.sk_err = -rc;
out:
- if (smc->sk.sk_err)
- smc->sk.sk_state_change(&smc->sk);
- else
- smc->sk.sk_write_space(&smc->sk);
- kfree(smc->connect_info);
- smc->connect_info = NULL;
+ if (!sock_flag(&smc->sk, SOCK_DEAD)) {
+ if (smc->sk.sk_err) {
+ smc->sk.sk_state_change(&smc->sk);
+ } else { /* allow polling before and after fallback decision */
+ smc->clcsock->sk->sk_write_space(smc->clcsock->sk);
+ smc->sk.sk_write_space(&smc->sk);
+ }
+ }
release_sock(&smc->sk);
}
@@ -815,26 +830,18 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
smc_copy_sock_settings_to_clc(smc);
tcp_sk(smc->clcsock->sk)->syn_smc = 1;
+ if (smc->connect_nonblock) {
+ rc = -EALREADY;
+ goto out;
+ }
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc && rc != -EINPROGRESS)
+ goto out;
if (flags & O_NONBLOCK) {
- if (smc->connect_info) {
- rc = -EALREADY;
- goto out;
- }
- smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
- if (!smc->connect_info) {
- rc = -ENOMEM;
- goto out;
- }
- smc->connect_info->alen = alen;
- smc->connect_info->flags = flags ^ O_NONBLOCK;
- memcpy(&smc->connect_info->addr, addr, alen);
- schedule_work(&smc->connect_work);
+ if (schedule_work(&smc->connect_work))
+ smc->connect_nonblock = 1;
rc = -EINPROGRESS;
} else {
- rc = kernel_connect(smc->clcsock, addr, alen, flags);
- if (rc)
- goto out;
-
rc = __smc_connect(smc);
if (rc < 0)
goto out;
@@ -874,11 +881,11 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
if (rc < 0)
lsk->sk_err = -rc;
if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (new_clcsock)
sock_release(new_clcsock);
new_sk->sk_state = SMC_CLOSED;
sock_set_flag(new_sk, SOCK_DEAD);
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
*new_smc = NULL;
goto out;
@@ -929,16 +936,21 @@ struct sock *smc_accept_dequeue(struct sock *parent,
smc_accept_unlink(new_sk);
if (new_sk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (isk->clcsock) {
sock_release(isk->clcsock);
isk->clcsock = NULL;
}
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
continue;
}
- if (new_sock)
+ if (new_sock) {
sock_graft(new_sk, new_sock);
+ if (isk->use_fallback) {
+ smc_sk(new_sk)->clcsock->file = new_sock->file;
+ isk->clcsock->file->private_data = isk->clcsock;
+ }
+ }
return new_sk;
}
return NULL;
@@ -958,6 +970,7 @@ void smc_close_non_accepted(struct sock *sk)
sock_set_flag(sk, SOCK_DEAD);
sk->sk_shutdown |= SHUTDOWN_MASK;
}
+ sk->sk_prot->unhash(sk);
if (smc->clcsock) {
struct socket *tcp;
@@ -973,7 +986,6 @@ void smc_close_non_accepted(struct sock *sk)
smc_conn_free(&smc->conn);
}
release_sock(sk);
- sk->sk_prot->unhash(sk);
sock_put(sk); /* final sock_put */
}
@@ -1039,13 +1051,13 @@ static void smc_listen_out(struct smc_sock *new_smc)
struct smc_sock *lsmc = new_smc->listen_smc;
struct sock *newsmcsk = &new_smc->sk;
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
smc_accept_enqueue(&lsmc->sk, newsmcsk);
+ release_sock(&lsmc->sk);
} else { /* no longer listening */
smc_close_non_accepted(newsmcsk);
}
- release_sock(&lsmc->sk);
/* Wake up accept */
lsmc->sk.sk_data_ready(&lsmc->sk);
@@ -1089,7 +1101,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
return;
}
smc_conn_free(&new_smc->conn);
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = reason_code;
if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
if (smc_clc_send_decline(new_smc, reason_code) < 0) {
@@ -1101,7 +1113,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
}
/* listen worker: check prefixes */
-static int smc_listen_rdma_check(struct smc_sock *new_smc,
+static int smc_listen_prfx_check(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc)
{
struct smc_clc_msg_proposal_prefix *pclc_prfx;
@@ -1109,25 +1121,21 @@ static int smc_listen_rdma_check(struct smc_sock *new_smc,
pclc_prfx = smc_clc_proposal_get_prefix(pclc);
if (smc_clc_prfx_match(newclcsock, pclc_prfx))
- return SMC_CLC_DECL_CNFERR;
+ return SMC_CLC_DECL_DIFFPREFIX;
return 0;
}
/* listen worker: initialize connection and buffers */
static int smc_listen_rdma_init(struct smc_sock *new_smc,
- struct smc_clc_msg_proposal *pclc,
- struct smc_ib_device *ibdev, u8 ibport,
- int *local_contact)
+ struct smc_init_info *ini)
{
+ int rc;
+
/* allocate connection / link group */
- *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, 0,
- &pclc->lcl, NULL, 0);
- if (*local_contact < 0) {
- if (*local_contact == -ENOMEM)
- return SMC_CLC_DECL_MEM;/* insufficient memory*/
- return SMC_CLC_DECL_INTERR; /* other error */
- }
+ rc = smc_conn_create(new_smc, ini);
+ if (rc)
+ return rc;
/* create send buffer and rmb */
if (smc_buf_create(new_smc, false))
@@ -1139,33 +1147,30 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc,
/* listen worker: initialize connection and buffers for SMC-D */
static int smc_listen_ism_init(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc,
- struct smcd_dev *ismdev,
- int *local_contact)
+ struct smc_init_info *ini)
{
struct smc_clc_msg_smcd *pclc_smcd;
+ int rc;
pclc_smcd = smc_get_clc_msg_smcd(pclc);
- *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, 0, NULL,
- ismdev, pclc_smcd->gid);
- if (*local_contact < 0) {
- if (*local_contact == -ENOMEM)
- return SMC_CLC_DECL_MEM;/* insufficient memory*/
- return SMC_CLC_DECL_INTERR; /* other error */
- }
+ ini->ism_gid = pclc_smcd->gid;
+ rc = smc_conn_create(new_smc, ini);
+ if (rc)
+ return rc;
/* Check if peer can be reached via ISM device */
if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid,
new_smc->conn.lgr->vlan_id,
new_smc->conn.lgr->smcd)) {
- if (*local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_lgr_forget(new_smc->conn.lgr);
smc_conn_free(&new_smc->conn);
- return SMC_CLC_DECL_CNFERR;
+ return SMC_CLC_DECL_SMCDNOTALK;
}
/* Create send and receive buffers */
if (smc_buf_create(new_smc, true)) {
- if (*local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_lgr_forget(new_smc->conn.lgr);
smc_conn_free(&new_smc->conn);
return SMC_CLC_DECL_MEM;
@@ -1229,15 +1234,13 @@ static void smc_listen_work(struct work_struct *work)
struct socket *newclcsock = new_smc->clcsock;
struct smc_clc_msg_accept_confirm cclc;
struct smc_clc_msg_proposal *pclc;
- struct smc_ib_device *ibdev;
+ struct smc_init_info ini = {0};
bool ism_supported = false;
- struct smcd_dev *ismdev;
u8 buf[SMC_CLC_MAX_LEN];
- int local_contact = 0;
- unsigned short vlan;
- int reason_code = 0;
int rc = 0;
- u8 ibport;
+
+ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+ return smc_listen_out_err(new_smc);
if (new_smc->use_fallback) {
smc_listen_out_connected(new_smc);
@@ -1246,7 +1249,7 @@ static void smc_listen_work(struct work_struct *work)
/* check if peer is smc capable */
if (!tcp_sk(newclcsock->sk)->syn_smc) {
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
smc_listen_out_connected(new_smc);
return;
@@ -1256,17 +1259,26 @@ static void smc_listen_work(struct work_struct *work)
* wait for and receive SMC Proposal CLC message
*/
pclc = (struct smc_clc_msg_proposal *)&buf;
- reason_code = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
- SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
- if (reason_code) {
- smc_listen_decline(new_smc, reason_code, 0);
- return;
- }
+ rc = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
+ SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
+ if (rc)
+ goto out_decl;
/* IPSec connections opt out of SMC-R optimizations */
if (using_ipsec(new_smc)) {
- smc_listen_decline(new_smc, SMC_CLC_DECL_IPSEC, 0);
- return;
+ rc = SMC_CLC_DECL_IPSEC;
+ goto out_decl;
+ }
+
+ /* check for matching IP prefix and subnet length */
+ rc = smc_listen_prfx_check(new_smc, pclc);
+ if (rc)
+ goto out_decl;
+
+ /* get vlan id from IP device */
+ if (smc_vlan_by_tcpsk(new_smc->clcsock, &ini)) {
+ rc = SMC_CLC_DECL_GETVLANERR;
+ goto out_decl;
}
mutex_lock(&smc_server_lgr_pending);
@@ -1275,59 +1287,73 @@ static void smc_listen_work(struct work_struct *work)
smc_tx_init(new_smc);
/* check if ISM is available */
- if ((pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) &&
- !smc_check_ism(new_smc, &ismdev) &&
- !smc_listen_ism_init(new_smc, pclc, ismdev, &local_contact)) {
- ism_supported = true;
+ if (pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) {
+ ini.is_smcd = true; /* prepare ISM check */
+ rc = smc_find_ism_device(new_smc, &ini);
+ if (!rc)
+ rc = smc_listen_ism_init(new_smc, pclc, &ini);
+ if (!rc)
+ ism_supported = true;
+ else if (pclc->hdr.path == SMC_TYPE_D)
+ goto out_unlock; /* skip RDMA and decline */
}
/* check if RDMA is available */
- if (!ism_supported &&
- ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
- smc_vlan_by_tcpsk(new_smc->clcsock, &vlan) ||
- smc_check_rdma(new_smc, &ibdev, &ibport, vlan, NULL) ||
- smc_listen_rdma_check(new_smc, pclc) ||
- smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
- &local_contact) ||
- smc_listen_rdma_reg(new_smc, local_contact))) {
- /* SMC not supported, decline */
- mutex_unlock(&smc_server_lgr_pending);
- smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP,
- local_contact);
- return;
+ if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */
+ /* prepare RDMA check */
+ memset(&ini, 0, sizeof(ini));
+ ini.is_smcd = false;
+ ini.ib_lcl = &pclc->lcl;
+ rc = smc_find_rdma_device(new_smc, &ini);
+ if (rc) {
+ /* no RDMA device found */
+ if (pclc->hdr.path == SMC_TYPE_B)
+ /* neither ISM nor RDMA device found */
+ rc = SMC_CLC_DECL_NOSMCDEV;
+ goto out_unlock;
+ }
+ rc = smc_listen_rdma_init(new_smc, &ini);
+ if (rc)
+ goto out_unlock;
+ rc = smc_listen_rdma_reg(new_smc, ini.cln_first_contact);
+ if (rc)
+ goto out_unlock;
}
/* send SMC Accept CLC message */
- rc = smc_clc_send_accept(new_smc, local_contact);
- if (rc) {
- mutex_unlock(&smc_server_lgr_pending);
- smc_listen_decline(new_smc, rc, local_contact);
- return;
- }
+ rc = smc_clc_send_accept(new_smc, ini.cln_first_contact);
+ if (rc)
+ goto out_unlock;
/* SMC-D does not need this lock any more */
if (ism_supported)
mutex_unlock(&smc_server_lgr_pending);
/* receive SMC Confirm CLC message */
- reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
- SMC_CLC_CONFIRM, CLC_WAIT_TIME);
- if (reason_code) {
+ rc = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
+ SMC_CLC_CONFIRM, CLC_WAIT_TIME);
+ if (rc) {
if (!ism_supported)
- mutex_unlock(&smc_server_lgr_pending);
- smc_listen_decline(new_smc, reason_code, local_contact);
- return;
+ goto out_unlock;
+ goto out_decl;
}
/* finish worker */
if (!ism_supported) {
- rc = smc_listen_rdma_finish(new_smc, &cclc, local_contact);
+ rc = smc_listen_rdma_finish(new_smc, &cclc,
+ ini.cln_first_contact);
mutex_unlock(&smc_server_lgr_pending);
if (rc)
return;
}
smc_conn_save_peer_info(new_smc, &cclc);
smc_listen_out_connected(new_smc);
+ return;
+
+out_unlock:
+ mutex_unlock(&smc_server_lgr_pending);
+out_decl:
+ smc_listen_decline(new_smc, rc, ini.cln_first_contact);
}
static void smc_tcp_listen_work(struct work_struct *work)
@@ -1503,7 +1529,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (msg->msg_flags & MSG_FASTOPEN) {
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
rc = -EINVAL;
@@ -1573,8 +1599,8 @@ static unsigned int smc_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
struct sock *sk = sock->sk;
- unsigned int mask = 0;
struct smc_sock *smc;
+ unsigned int mask = 0;
if (!sk)
return POLLNVAL;
@@ -1584,8 +1610,6 @@ static unsigned int smc_poll(struct file *file, struct socket *sock,
/* delegate to CLC child sock */
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err)
- mask |= POLLERR;
} else {
if (sk->sk_state != SMC_CLOSED)
sock_poll_wait(file, sk_sleep(sk), wait);
@@ -1596,9 +1620,14 @@ static unsigned int smc_poll(struct file *file, struct socket *sock,
mask |= POLLHUP;
if (sk->sk_state == SMC_LISTEN) {
/* woken up by sk_data_ready in smc_listen_work() */
- mask = smc_accept_poll(sk);
+ mask |= smc_accept_poll(sk);
+ } else if (smc->use_fallback) { /* as result of connect_work()*/
+ mask |= smc->clcsock->ops->poll(file, smc->clcsock,
+ wait);
+ sk->sk_err = smc->clcsock->sk->sk_err;
} else {
- if (atomic_read(&smc->conn.sndbuf_space) ||
+ if ((sk->sk_state != SMC_INIT &&
+ atomic_read(&smc->conn.sndbuf_space)) ||
sk->sk_shutdown & SEND_SHUTDOWN) {
mask |= POLLOUT | POLLWRNORM;
} else {
@@ -1703,7 +1732,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
case TCP_FASTOPEN_CONNECT:
/* option not supported by SMC */
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
if (!smc->use_fallback)
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 16a689588b46..6f83cd015a2e 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -189,18 +189,11 @@ struct smc_connection {
u64 peer_token; /* SMC-D token of peer */
};
-struct smc_connect_info {
- int flags;
- int alen;
- struct sockaddr addr;
-};
-
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
- struct smc_connect_info *connect_info; /* connect address & flags */
struct work_struct connect_work; /* handle non-blocking connect*/
struct work_struct tcp_listen_work;/* handle tcp socket accepts */
struct work_struct smc_listen_work;/* prepare new accept socket */
@@ -218,6 +211,10 @@ struct smc_sock { /* smc sock container */
* started, waiting for unsent
* data to be sent
*/
+ u8 connect_nonblock : 1;
+ /* non-blocking connect in
+ * flight
+ */
struct mutex clcsock_release_lock;
/* protects clcsock of a listen
* socket
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 66ea142690c0..d9138b771c4a 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -384,8 +384,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
/* send CLC PROPOSAL message across internal TCP socket */
int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
- struct smc_ib_device *ibdev, u8 ibport, u8 gid[],
- struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
struct smc_clc_msg_proposal_prefix pclc_prfx;
@@ -415,8 +414,9 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
/* add SMC-R specifics */
memcpy(pclc.lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
- memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE);
- memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
+ memcpy(&pclc.lcl.gid, ini->ib_gid, SMC_GID_SIZE);
+ memcpy(&pclc.lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1],
+ ETH_ALEN);
pclc.iparea_offset = htons(0);
}
if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
@@ -424,7 +424,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
memset(&pclc_smcd, 0, sizeof(pclc_smcd));
plen += sizeof(pclc_smcd);
pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET);
- pclc_smcd.gid = ismdev->local_gid;
+ pclc_smcd.gid = ini->ism_dev->local_gid;
}
pclc.hdr.length = htons(plen);
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 786c00d6df1b..6f164f539919 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -33,16 +33,22 @@
#define SMC_CLC_DECL_CNFERR 0x03000000 /* configuration error */
#define SMC_CLC_DECL_PEERNOSMC 0x03010000 /* peer did not indicate SMC */
#define SMC_CLC_DECL_IPSEC 0x03020000 /* IPsec usage */
-#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found */
+#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */
+#define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */
+#define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */
+#define SMC_CLC_DECL_SMCDNOTALK 0x03030003 /* SMC-D dev can't talk to peer */
#define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/
#define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */
#define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */
+#define SMC_CLC_DECL_DIFFPREFIX 0x03070000 /* IP prefix / subnet mismatch */
+#define SMC_CLC_DECL_GETVLANERR 0x03080000 /* err to get vlan id of ip device*/
+#define SMC_CLC_DECL_ISMVLANERR 0x03090000 /* err to reg vlan id on ism dev */
#define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */
#define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */
-#define SMC_CLC_DECL_INTERR 0x99990000 /* internal error */
-#define SMC_CLC_DECL_ERR_RTOK 0x99990001 /* rtoken handling failed */
-#define SMC_CLC_DECL_ERR_RDYLNK 0x99990002 /* ib ready link failed */
-#define SMC_CLC_DECL_ERR_REGRMB 0x99990003 /* reg rmb failed */
+#define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */
+#define SMC_CLC_DECL_ERR_RTOK 0x09990001 /* rtoken handling failed */
+#define SMC_CLC_DECL_ERR_RDYLNK 0x09990002 /* ib ready link failed */
+#define SMC_CLC_DECL_ERR_REGRMB 0x09990003 /* reg rmb failed */
struct smc_clc_msg_hdr { /* header1 of clc messages */
u8 eyecatcher[4]; /* eye catcher */
@@ -178,6 +184,7 @@ smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop)
}
struct smcd_dev;
+struct smc_init_info;
int smc_clc_prfx_match(struct socket *clcsock,
struct smc_clc_msg_proposal_prefix *prop);
@@ -185,8 +192,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
u8 expected_type, unsigned long timeout);
int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
- struct smc_ib_device *smcibdev, u8 ibport, u8 gid[],
- struct smcd_dev *ismdev);
+ struct smc_init_info *ini);
int smc_clc_send_confirm(struct smc_sock *smc);
int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index e53083c41685..5a556f8b52d2 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -20,6 +20,22 @@
#define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ)
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+ struct socket *tcp;
+
+ if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+ cancel_work_sync(&smc->smc_listen_work);
+ mutex_lock(&smc->clcsock_release_lock);
+ if (smc->clcsock) {
+ tcp = smc->clcsock;
+ smc->clcsock = NULL;
+ sock_release(tcp);
+ }
+ mutex_unlock(&smc->clcsock_release_lock);
+}
+
static void smc_close_cleanup_listen(struct sock *parent)
{
struct sock *sk;
@@ -320,6 +336,7 @@ static void smc_close_passive_work(struct work_struct *work)
close_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
struct smc_cdc_conn_state_flags *rxflags;
+ bool release_clcsock = false;
struct sock *sk = &smc->sk;
int old_state;
@@ -399,13 +416,13 @@ wakeup:
if ((sk->sk_state == SMC_CLOSED) &&
(sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
smc_conn_free(conn);
- if (smc->clcsock) {
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- }
+ if (smc->clcsock)
+ release_clcsock = true;
}
}
release_sock(sk);
+ if (release_clcsock)
+ smc_clcsock_release(smc);
sock_put(sk); /* sock_hold done by schedulers of close_work */
}
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index 6e18290720ce..00db139f7642 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -22,5 +22,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc);
int smc_close_active(struct smc_sock *smc);
int smc_close_shutdown_write(struct smc_sock *smc);
void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
#endif /* SMC_CLOSE_H */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 6faff5dd1c14..b38e35d1799a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -194,10 +194,7 @@ static void smc_lgr_free_work(struct work_struct *work)
}
/* create a new SMC link group */
-static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
- struct smc_ib_device *smcibdev, u8 ibport,
- char *peer_systemid, unsigned short vlan_id,
- struct smcd_dev *smcismdev, u64 peer_gid)
+static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
{
struct smc_link_group *lgr;
struct smc_link *lnk;
@@ -205,20 +202,21 @@ static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
int rc = 0;
int i;
- if (is_smcd && vlan_id) {
- rc = smc_ism_get_vlan(smcismdev, vlan_id);
- if (rc)
+ if (ini->is_smcd && ini->vlan_id) {
+ if (smc_ism_get_vlan(ini->ism_dev, ini->vlan_id)) {
+ rc = SMC_CLC_DECL_ISMVLANERR;
goto out;
+ }
}
lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
if (!lgr) {
- rc = -ENOMEM;
+ rc = SMC_CLC_DECL_MEM;
goto out;
}
- lgr->is_smcd = is_smcd;
+ lgr->is_smcd = ini->is_smcd;
lgr->sync_err = 0;
- lgr->vlan_id = vlan_id;
+ lgr->vlan_id = ini->vlan_id;
rwlock_init(&lgr->sndbufs_lock);
rwlock_init(&lgr->rmbs_lock);
rwlock_init(&lgr->conns_lock);
@@ -230,29 +228,32 @@ static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE);
INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
lgr->conns_all = RB_ROOT;
- if (is_smcd) {
+ if (ini->is_smcd) {
/* SMC-D specific settings */
- lgr->peer_gid = peer_gid;
- lgr->smcd = smcismdev;
+ lgr->peer_gid = ini->ism_gid;
+ lgr->smcd = ini->ism_dev;
} else {
/* SMC-R specific settings */
lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
+ memcpy(lgr->peer_systemid, ini->ib_lcl->id_for_peer,
+ SMC_SYSTEMID_LEN);
lnk = &lgr->lnk[SMC_SINGLE_LINK];
/* initialize link */
lnk->state = SMC_LNK_ACTIVATING;
lnk->link_id = SMC_SINGLE_LINK;
- lnk->smcibdev = smcibdev;
- lnk->ibport = ibport;
- lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
- if (!smcibdev->initialized)
- smc_ib_setup_per_ibdev(smcibdev);
+ lnk->smcibdev = ini->ib_dev;
+ lnk->ibport = ini->ib_port;
+ lnk->path_mtu =
+ ini->ib_dev->pattr[ini->ib_port - 1].active_mtu;
+ if (!ini->ib_dev->initialized)
+ smc_ib_setup_per_ibdev(ini->ib_dev);
get_random_bytes(rndvec, sizeof(rndvec));
lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
(rndvec[2] << 16);
rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport,
- vlan_id, lnk->gid, &lnk->sgid_index);
+ ini->vlan_id, lnk->gid,
+ &lnk->sgid_index);
if (rc)
goto free_lgr;
rc = smc_llc_link_init(lnk);
@@ -288,6 +289,12 @@ clear_llc_lnk:
free_lgr:
kfree(lgr);
out:
+ if (rc < 0) {
+ if (rc == -ENOMEM)
+ rc = SMC_CLC_DECL_MEM;
+ else
+ rc = SMC_CLC_DECL_INTERR;
+ }
return rc;
}
@@ -527,13 +534,13 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
/* Determine vlan of internal TCP socket.
* @vlan_id: address to store the determined vlan id into
*/
-int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
+int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
struct net_device *ndev;
int i, nest_lvl, rc = 0;
- *vlan_id = 0;
+ ini->vlan_id = 0;
if (!dst) {
rc = -ENOTCONN;
goto out;
@@ -545,7 +552,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
ndev = dst->dev;
if (is_vlan_dev(ndev)) {
- *vlan_id = vlan_dev_vlan_id(ndev);
+ ini->vlan_id = vlan_dev_vlan_id(ndev);
goto out_rel;
}
@@ -559,7 +566,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
lower = lower->next;
ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower);
if (is_vlan_dev(ndev)) {
- *vlan_id = vlan_dev_vlan_id(ndev);
+ ini->vlan_id = vlan_dev_vlan_id(ndev);
break;
}
}
@@ -593,24 +600,16 @@ static bool smcd_lgr_match(struct smc_link_group *lgr,
}
/* create a new SMC connection (and a new link group if necessary) */
-int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
- struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
- struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
- u64 peer_gid)
+int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
{
struct smc_connection *conn = &smc->conn;
- int local_contact = SMC_FIRST_CONTACT;
struct smc_link_group *lgr;
- unsigned short vlan_id;
enum smc_lgr_role role;
int rc = 0;
+ ini->cln_first_contact = SMC_FIRST_CONTACT;
role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- rc = smc_vlan_by_tcpsk(smc->clcsock, &vlan_id);
- if (rc)
- return rc;
-
- if ((role == SMC_CLNT) && srv_first_contact)
+ if (role == SMC_CLNT && ini->srv_first_contact)
/* create new link group as well */
goto create;
@@ -618,14 +617,15 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
spin_lock_bh(&smc_lgr_list.lock);
list_for_each_entry(lgr, &smc_lgr_list.list, list) {
write_lock_bh(&lgr->conns_lock);
- if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
- smcr_lgr_match(lgr, lcl, role, clcqpn)) &&
+ if ((ini->is_smcd ?
+ smcd_lgr_match(lgr, ini->ism_dev, ini->ism_gid) :
+ smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) &&
!lgr->sync_err &&
- lgr->vlan_id == vlan_id &&
+ lgr->vlan_id == ini->vlan_id &&
(role == SMC_CLNT ||
lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
/* link group found */
- local_contact = SMC_REUSE_CONTACT;
+ ini->cln_first_contact = SMC_REUSE_CONTACT;
conn->lgr = lgr;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
if (delayed_work_pending(&lgr->free_work))
@@ -637,19 +637,18 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
}
spin_unlock_bh(&smc_lgr_list.lock);
- if (role == SMC_CLNT && !srv_first_contact &&
- (local_contact == SMC_FIRST_CONTACT)) {
+ if (role == SMC_CLNT && !ini->srv_first_contact &&
+ ini->cln_first_contact == SMC_FIRST_CONTACT) {
/* Server reuses a link group, but Client wants to start
* a new one
* send out_of_sync decline, reason synchr. error
*/
- return -ENOLINK;
+ return SMC_CLC_DECL_SYNCERR;
}
create:
- if (local_contact == SMC_FIRST_CONTACT) {
- rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport,
- lcl->id_for_peer, vlan_id, smcd, peer_gid);
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
+ rc = smc_lgr_create(smc, ini);
if (rc)
goto out;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
@@ -657,7 +656,7 @@ create:
conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
conn->urg_state = SMC_URG_READ;
- if (is_smcd) {
+ if (ini->is_smcd) {
conn->rx_off = sizeof(struct smcd_cdc_msg);
smcd_cdc_rx_init(conn); /* init tasklet for this conn */
}
@@ -666,7 +665,7 @@ create:
#endif
out:
- return rc ? rc : local_contact;
+ return rc;
}
/* convert the RMB size into the compressed notation - minimum 16K.
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 2e7f505fcecc..3c5ebd5a6ce1 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -235,6 +235,24 @@ struct smc_link_group {
#endif
};
+struct smc_clc_msg_local;
+
+struct smc_init_info {
+ u8 is_smcd;
+ unsigned short vlan_id;
+ int srv_first_contact;
+ int cln_first_contact;
+ /* SMC-R */
+ struct smc_clc_msg_local *ib_lcl;
+ struct smc_ib_device *ib_dev;
+ u8 ib_gid[SMC_GID_SIZE];
+ u8 ib_port;
+ u32 ib_clcqpn;
+ /* SMC-D */
+ u64 ism_gid;
+ struct smcd_dev *ism_dev;
+};
+
/* Find the connection associated with the given alert token in the link group.
* To use rbtrees we have to implement our own search core.
* Requires @conns_lock
@@ -287,13 +305,10 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
-int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id);
+int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini);
void smc_conn_free(struct smc_connection *conn);
-int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
- struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
- struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
- u64 peer_gid);
+int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini);
void smcd_conn_free(struct smc_connection *conn);
void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
void smc_core_exit(void);
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 3d73ba315309..5fb6b178858c 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -145,17 +145,21 @@ out:
static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
{
- struct ib_gid_attr gattr;
- union ib_gid gid;
- int rc;
+ const struct ib_gid_attr *attr;
+ int rc = 0;
- rc = ib_query_gid(smcibdev->ibdev, ibport, 0, &gid, &gattr);
- if (rc || !gattr.ndev)
+ attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0);
+ if (IS_ERR(attr))
return -ENODEV;
- memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
- dev_put(gattr.ndev);
- return 0;
+ if (attr->ndev)
+ memcpy(smcibdev->mac[ibport - 1], attr->ndev->dev_addr,
+ ETH_ALEN);
+ else
+ rc = -ENODEV;
+
+ rdma_put_gid_attr(attr);
+ return rc;
}
/* Create an identifier unique for this instance of SMC-R.
@@ -180,29 +184,27 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
unsigned short vlan_id, u8 gid[], u8 *sgid_index)
{
- struct ib_gid_attr gattr;
- union ib_gid _gid;
+ const struct ib_gid_attr *attr;
int i;
for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
- memset(&_gid, 0, SMC_GID_SIZE);
- memset(&gattr, 0, sizeof(gattr));
- if (ib_query_gid(smcibdev->ibdev, ibport, i, &_gid, &gattr))
+ attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i);
+ if (IS_ERR(attr))
continue;
- if (!gattr.ndev)
- continue;
- if (((!vlan_id && !is_vlan_dev(gattr.ndev)) ||
- (vlan_id && is_vlan_dev(gattr.ndev) &&
- vlan_dev_vlan_id(gattr.ndev) == vlan_id)) &&
- gattr.gid_type == IB_GID_TYPE_IB) {
+
+ if (attr->ndev &&
+ ((!vlan_id && !is_vlan_dev(attr->ndev)) ||
+ (vlan_id && is_vlan_dev(attr->ndev) &&
+ vlan_dev_vlan_id(attr->ndev) == vlan_id)) &&
+ attr->gid_type == IB_GID_TYPE_ROCE) {
if (gid)
- memcpy(gid, &_gid, SMC_GID_SIZE);
+ memcpy(gid, &attr->gid, SMC_GID_SIZE);
if (sgid_index)
- *sgid_index = i;
- dev_put(gattr.ndev);
+ *sgid_index = attr->index;
+ rdma_put_gid_attr(attr);
return 0;
}
- dev_put(gattr.ndev);
+ rdma_put_gid_attr(attr);
}
return -ENODEV;
}
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 2fff79db1a59..e89e918b88e0 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -289,6 +289,11 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
INIT_LIST_HEAD(&smcd->vlan);
smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
WQ_MEM_RECLAIM, name);
+ if (!smcd->event_wq) {
+ kfree(smcd->conn);
+ kfree(smcd);
+ return NULL;
+ }
return smcd;
}
EXPORT_SYMBOL_GPL(smcd_alloc_dev);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 9aa8e8fcea95..64ea59cd9d59 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -25,6 +25,7 @@
#include "smc_pnet.h"
#include "smc_ib.h"
#include "smc_ism.h"
+#include "smc_core.h"
#define SMC_ASCII_BLANK 32
@@ -602,7 +603,8 @@ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
- return smc_pnet_remove_by_pnetid(net, NULL);
+ smc_pnet_remove_by_pnetid(net, NULL);
+ return 0;
}
/* SMC_PNETID generic netlink operation definition */
@@ -757,8 +759,7 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev,
* IB device and port
*/
static void smc_pnet_find_rdma_dev(struct net_device *netdev,
- struct smc_ib_device **smcibdev,
- u8 *ibport, unsigned short vlan_id, u8 gid[])
+ struct smc_init_info *ini)
{
struct smc_ib_device *ibdev;
@@ -778,10 +779,10 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev,
dev_put(ndev);
if (netdev == ndev &&
smc_ib_port_active(ibdev, i) &&
- !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
- NULL)) {
- *smcibdev = ibdev;
- *ibport = i;
+ !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
+ ini->ib_gid, NULL)) {
+ ini->ib_dev = ibdev;
+ ini->ib_port = i;
break;
}
}
@@ -796,9 +797,7 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev,
* If nothing found, try to use handshake device
*/
static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
- struct smc_ib_device **smcibdev,
- u8 *ibport, unsigned short vlan_id,
- u8 gid[])
+ struct smc_init_info *ini)
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct smc_ib_device *ibdev;
@@ -808,7 +807,7 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
ndev_pnetid) &&
smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) {
- smc_pnet_find_rdma_dev(ndev, smcibdev, ibport, vlan_id, gid);
+ smc_pnet_find_rdma_dev(ndev, ini);
return; /* pnetid could not be determined */
}
@@ -819,10 +818,10 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
continue;
if (smc_pnet_match(ibdev->pnetid[i - 1], ndev_pnetid) &&
smc_ib_port_active(ibdev, i) &&
- !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
- NULL)) {
- *smcibdev = ibdev;
- *ibport = i;
+ !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
+ ini->ib_gid, NULL)) {
+ ini->ib_dev = ibdev;
+ ini->ib_port = i;
goto out;
}
}
@@ -832,7 +831,7 @@ out:
}
static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
- struct smcd_dev **smcismdev)
+ struct smc_init_info *ini)
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct smcd_dev *ismdev;
@@ -846,7 +845,7 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
spin_lock(&smcd_dev_list.lock);
list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
if (smc_pnet_match(ismdev->pnetid, ndev_pnetid)) {
- *smcismdev = ismdev;
+ ini->ism_dev = ismdev;
break;
}
}
@@ -857,21 +856,18 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
* determine ib_device and port belonging to used internal TCP socket
* ethernet interface.
*/
-void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport,
- unsigned short vlan_id, u8 gid[])
+void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(sk);
- *smcibdev = NULL;
- *ibport = 0;
-
+ ini->ib_dev = NULL;
+ ini->ib_port = 0;
if (!dst)
goto out;
if (!dst->dev)
goto out_rel;
- smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport, vlan_id, gid);
+ smc_pnet_find_roce_by_pnetid(dst->dev, ini);
out_rel:
dst_release(dst);
@@ -879,17 +875,17 @@ out:
return;
}
-void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev)
+void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(sk);
- *smcismdev = NULL;
+ ini->ism_dev = NULL;
if (!dst)
goto out;
if (!dst->dev)
goto out_rel;
- smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev);
+ smc_pnet_find_ism_by_pnetid(dst->dev, ini);
out_rel:
dst_release(dst);
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 4fc8c496d107..251fda210d3a 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -17,6 +17,7 @@
struct smc_ib_device;
struct smcd_dev;
+struct smc_init_info;
/**
* struct smc_pnettable - SMC PNET table anchor
@@ -42,9 +43,7 @@ int smc_pnet_init(void) __init;
int smc_pnet_net_init(struct net *net);
void smc_pnet_exit(void);
void smc_pnet_net_exit(struct net *net);
-void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport,
- unsigned short vlan_id, u8 gid[]);
-void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
+void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini);
+void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini);
#endif
diff --git a/net/socket.c b/net/socket.c
index a06e597f2a06..47be9d784660 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -89,6 +89,7 @@
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/xattr.h>
+#include <linux/nospec.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
@@ -2445,6 +2446,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
if (call < 1 || call > SYS_SENDMMSG)
return -EINVAL;
+ call = array_index_nospec(call, SYS_SENDMMSG + 1);
len = nargs[call];
if (len > sizeof(a))
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 2ff751eba037..5ebeef8ae3fa 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -702,28 +702,27 @@ static int __init virtio_vsock_init(void)
if (!virtio_vsock_workqueue)
return -ENOMEM;
- ret = register_virtio_driver(&virtio_vsock_driver);
+ ret = vsock_core_init(&virtio_transport.transport);
if (ret)
goto out_wq;
- ret = vsock_core_init(&virtio_transport.transport);
+ ret = register_virtio_driver(&virtio_vsock_driver);
if (ret)
- goto out_vdr;
+ goto out_vci;
return 0;
-out_vdr:
- unregister_virtio_driver(&virtio_vsock_driver);
+out_vci:
+ vsock_core_exit();
out_wq:
destroy_workqueue(virtio_vsock_workqueue);
return ret;
-
}
static void __exit virtio_vsock_exit(void)
{
- vsock_core_exit();
unregister_virtio_driver(&virtio_vsock_driver);
+ vsock_core_exit();
destroy_workqueue(virtio_vsock_workqueue);
}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c50409a42fa9..f1fc0089ebe0 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13392,7 +13392,8 @@ static const struct genl_ops nl80211_ops[] = {
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEAUTHENTICATE,
@@ -13443,7 +13444,8 @@ static const struct genl_ops nl80211_ops[] = {
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
@@ -13451,7 +13453,8 @@ static const struct genl_ops nl80211_ops[] = {
.policy = nl80211_policy,
.flags = GENL_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DISCONNECT,
@@ -13480,7 +13483,8 @@ static const struct genl_ops nl80211_ops[] = {
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEL_PMKSA,
@@ -13832,7 +13836,8 @@ static const struct genl_ops nl80211_ops[] = {
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_WIPHY |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_SET_QOS_MAP,
@@ -13872,7 +13877,8 @@ static const struct genl_ops nl80211_ops[] = {
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_SET_MULTICAST_TO_UNICAST,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 310f1df4075f..a18b0e37b8eb 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -446,6 +446,7 @@ resume:
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
+ crypto_done = false;
} while (!err);
err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 736bddd6bf0d..c82c695fa3fd 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1864,7 +1864,10 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
/* Try to instantiate a bundle */
err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
if (err <= 0) {
- if (err != 0 && err != -EAGAIN)
+ if (err == 0)
+ return NULL;
+
+ if (err != -EAGAIN)
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
return ERR_PTR(err);
}
@@ -2350,6 +2353,9 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
return make_blackhole(net, dst_orig->ops->family, dst_orig);
+ if (IS_ERR(dst))
+ dst_release(dst_orig);
+
return dst;
}
EXPORT_SYMBOL(xfrm_lookup_route);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 00bdd1e18fc9..6931534be1bf 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -156,10 +156,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
err = -EINVAL;
switch (p->family) {
case AF_INET:
+ if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
+ goto out;
+
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
+ if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
+ goto out;
+
break;
#else
err = -EAFNOSUPPORT;
@@ -1352,10 +1358,16 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
switch (p->sel.family) {
case AF_INET:
+ if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
+ return -EINVAL;
+
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
+ if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
+ return -EINVAL;
+
break;
#else
return -EAFNOSUPPORT;
@@ -1642,9 +1654,11 @@ static inline size_t userpolicy_type_attrsize(void)
#ifdef CONFIG_XFRM_SUB_POLICY
static int copy_to_user_policy_type(u8 type, struct sk_buff *skb)
{
- struct xfrm_userpolicy_type upt = {
- .type = type,
- };
+ struct xfrm_userpolicy_type upt;
+
+ /* Sadly there are two holes in struct xfrm_userpolicy_type */
+ memset(&upt, 0, sizeof(upt));
+ upt.type = type;
return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt);
}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c53ca589c930..f83f21d64dd4 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -478,12 +478,45 @@ static void alc_auto_setup_eapd(struct hda_codec *codec, bool on)
set_eapd(codec, *p, on);
}
+static int find_ext_mic_pin(struct hda_codec *codec);
+
+static void alc_headset_mic_no_shutup(struct hda_codec *codec)
+{
+ const struct hda_pincfg *pin;
+ int mic_pin = find_ext_mic_pin(codec);
+ int i;
+
+ /* don't shut up pins when unloading the driver; otherwise it breaks
+ * the default pin setup at the next load of the driver
+ */
+ if (codec->bus->shutdown)
+ return;
+
+ snd_array_for_each(&codec->init_pins, i, pin) {
+ /* use read here for syncing after issuing each verb */
+ if (pin->nid != mic_pin)
+ snd_hda_codec_read(codec, pin->nid, 0,
+ AC_VERB_SET_PIN_WIDGET_CONTROL, 0);
+ }
+
+ codec->pins_shutup = 1;
+}
+
static void alc_shutup_pins(struct hda_codec *codec)
{
struct alc_spec *spec = codec->spec;
- if (!spec->no_shutup_pins)
- snd_hda_shutup_pins(codec);
+ switch (codec->core.vendor_id) {
+ case 0x10ec0286:
+ case 0x10ec0288:
+ case 0x10ec0298:
+ alc_headset_mic_no_shutup(codec);
+ break;
+ default:
+ if (!spec->no_shutup_pins)
+ snd_hda_shutup_pins(codec);
+ break;
+ }
}
/* generic shutup callback;
@@ -502,7 +535,6 @@ static void alc_eapd_shutup(struct hda_codec *codec)
/* generic EAPD initialization */
static void alc_auto_init_amp(struct hda_codec *codec, int type)
{
- alc_fill_eapd_coef(codec);
alc_auto_setup_eapd(codec, true);
alc_write_gpio(codec);
switch (type) {
@@ -797,10 +829,22 @@ static int alc_build_controls(struct hda_codec *codec)
* Common callbacks
*/
+static void alc_pre_init(struct hda_codec *codec)
+{
+ alc_fill_eapd_coef(codec);
+}
+
+#define is_s4_resume(codec) \
+ ((codec)->core.dev.power.power_state.event == PM_EVENT_RESTORE)
+
static int alc_init(struct hda_codec *codec)
{
struct alc_spec *spec = codec->spec;
+ /* hibernation resume needs the full chip initialization */
+ if (is_s4_resume(codec))
+ alc_pre_init(codec);
+
if (spec->init_hook)
spec->init_hook(codec);
@@ -1538,6 +1582,8 @@ static int patch_alc880(struct hda_codec *codec)
codec->patch_ops.unsol_event = alc880_unsol_event;
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, alc880_fixup_models, alc880_fixup_tbl,
alc880_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -1789,6 +1835,8 @@ static int patch_alc260(struct hda_codec *codec)
spec->shutup = alc_eapd_shutup;
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, alc260_fixup_models, alc260_fixup_tbl,
alc260_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -2492,6 +2540,8 @@ static int patch_alc882(struct hda_codec *codec)
break;
}
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, alc882_fixup_models, alc882_fixup_tbl,
alc882_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -2666,6 +2716,8 @@ static int patch_alc262(struct hda_codec *codec)
#endif
alc_fix_pll_init(codec, 0x20, 0x0a, 10);
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, alc262_fixup_models, alc262_fixup_tbl,
alc262_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -2810,6 +2862,8 @@ static int patch_alc268(struct hda_codec *codec)
spec->shutup = alc_eapd_shutup;
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, alc268_fixup_models, alc268_fixup_tbl, alc268_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -2924,27 +2978,6 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
return alc_parse_auto_config(codec, alc269_ignore, ssids);
}
-static int find_ext_mic_pin(struct hda_codec *codec);
-
-static void alc286_shutup(struct hda_codec *codec)
-{
- const struct hda_pincfg *pin;
- int i;
- int mic_pin = find_ext_mic_pin(codec);
- /* don't shut up pins when unloading the driver; otherwise it breaks
- * the default pin setup at the next load of the driver
- */
- if (codec->bus->shutdown)
- return;
- snd_array_for_each(&codec->init_pins, i, pin) {
- /* use read here for syncing after issuing each verb */
- if (pin->nid != mic_pin)
- snd_hda_codec_read(codec, pin->nid, 0,
- AC_VERB_SET_PIN_WIDGET_CONTROL, 0);
- }
- codec->pins_shutup = 1;
-}
-
static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up)
{
alc_update_coef_idx(codec, 0x04, 1 << 11, power_up ? (1 << 11) : 0);
@@ -6964,7 +6997,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x8550, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
- SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8551, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
@@ -7007,7 +7042,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
- SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
+ SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
SND_PCI_QUIRK(0x17aa, 0x501e, "Thinkpad L440", ALC292_FIXUP_TPT440_DOCK),
@@ -7736,7 +7771,6 @@ static int patch_alc269(struct hda_codec *codec)
case 0x10ec0286:
case 0x10ec0288:
spec->codec_variant = ALC269_TYPE_ALC286;
- spec->shutup = alc286_shutup;
break;
case 0x10ec0298:
spec->codec_variant = ALC269_TYPE_ALC298;
@@ -7805,6 +7839,8 @@ static int patch_alc269(struct hda_codec *codec)
spec->init_hook = alc5505_dsp_init;
}
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, alc269_fixup_models,
alc269_fixup_tbl, alc269_fixups);
snd_hda_pick_pin_fixup(codec, alc269_pin_fixup_tbl, alc269_fixups);
@@ -7947,6 +7983,8 @@ static int patch_alc861(struct hda_codec *codec)
spec->power_hook = alc_power_eapd;
#endif
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, NULL, alc861_fixup_tbl, alc861_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -8044,6 +8082,8 @@ static int patch_alc861vd(struct hda_codec *codec)
spec->shutup = alc_eapd_shutup;
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, NULL, alc861vd_fixup_tbl, alc861vd_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -8779,6 +8819,8 @@ static int patch_alc662(struct hda_codec *codec)
break;
}
+ alc_pre_init(codec);
+
snd_hda_pick_fixup(codec, alc662_fixup_models,
alc662_fixup_tbl, alc662_fixups);
snd_hda_pick_pin_fixup(codec, alc662_pin_fixup_tbl, alc662_fixups);
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 3955ba9e6fcb..7989dd6289e7 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2206,7 +2206,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
return val & 0xffffffff;
if (strcmp(type, "u64") == 0 ||
- strcmp(type, "s64"))
+ strcmp(type, "s64") == 0)
return val;
if (strcmp(type, "s8") == 0)
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index bf817beca0a8..9032c5d04bdf 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -155,7 +155,7 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
if (strstr(cpuid, "Intel")) {
kvm->exit_reasons = vmx_exit_reasons;
kvm->exit_reasons_isa = "VMX";
- } else if (strstr(cpuid, "AMD")) {
+ } else if (strstr(cpuid, "AMD") || strstr(cpuid, "Hygon")) {
kvm->exit_reasons = svm_exit_reasons;
kvm->exit_reasons_isa = "SVM";
} else
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index 3e701f0e9c14..45db3beb00c0 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -172,6 +172,7 @@ static int get_boost_mode(unsigned int cpu)
unsigned long pstates[MAX_HW_PSTATES] = {0,};
if (cpupower_cpu_info.vendor != X86_VENDOR_AMD &&
+ cpupower_cpu_info.vendor != X86_VENDOR_HYGON &&
cpupower_cpu_info.vendor != X86_VENDOR_INTEL)
return 0;
@@ -192,8 +193,9 @@ static int get_boost_mode(unsigned int cpu)
printf(_(" Supported: %s\n"), support ? _("yes") : _("no"));
printf(_(" Active: %s\n"), active ? _("yes") : _("no"));
- if (cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
- cpupower_cpu_info.family >= 0x10) {
+ if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
+ cpupower_cpu_info.family >= 0x10) ||
+ cpupower_cpu_info.vendor == X86_VENDOR_HYGON) {
ret = decode_pstates(cpu, cpupower_cpu_info.family, b_states,
pstates, &pstate_no);
if (ret)
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index 6437ef39aeea..05c27a916978 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -47,7 +47,6 @@ static int get_cof(int family, union msr_pstate pstate)
int fid, did;
did = get_did(family, pstate);
-
t = 0x10;
fid = pstate.bits.fid;
if (family == 0x11)
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 39c2c7d067bb..0a6080e4eea5 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -7,7 +7,7 @@
#include "helpers/helpers.h"
static const char *cpu_vendor_table[X86_VENDOR_MAX] = {
- "Unknown", "GenuineIntel", "AuthenticAMD",
+ "Unknown", "GenuineIntel", "AuthenticAMD", "HygonGenuine",
};
#if defined(__i386__) || defined(__x86_64__)
@@ -108,6 +108,7 @@ out:
fclose(fp);
/* Get some useful CPU capabilities from cpuid */
if (cpu_info->vendor != X86_VENDOR_AMD &&
+ cpu_info->vendor != X86_VENDOR_HYGON &&
cpu_info->vendor != X86_VENDOR_INTEL)
return ret;
@@ -123,8 +124,9 @@ out:
if (cpuid_level >= 6 && (cpuid_ecx(6) & 0x1))
cpu_info->caps |= CPUPOWER_CAP_APERF;
- /* AMD Boost state enable/disable register */
- if (cpu_info->vendor == X86_VENDOR_AMD) {
+ /* AMD or Hygon Boost state enable/disable register */
+ if (cpu_info->vendor == X86_VENDOR_AMD ||
+ cpu_info->vendor == X86_VENDOR_HYGON) {
if (ext_cpuid_level >= 0x80000007 &&
(cpuid_edx(0x80000007) & (1 << 9)))
cpu_info->caps |= CPUPOWER_CAP_AMD_CBP;
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index afb66f80554e..dbfd763ef8a6 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -60,7 +60,7 @@ extern int be_verbose;
/* cpuid and cpuinfo helpers **************************/
enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL,
- X86_VENDOR_AMD, X86_VENDOR_MAX};
+ X86_VENDOR_AMD, X86_VENDOR_HYGON, X86_VENDOR_MAX};
#define CPUPOWER_CAP_INV_TSC 0x00000001
#define CPUPOWER_CAP_APERF 0x00000002
diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
index c83f1606970b..08e00466a27d 100644
--- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
@@ -240,7 +240,8 @@ static int init_maxfreq_mode(void)
if (!(cpupower_cpu_info.caps & CPUPOWER_CAP_INV_TSC))
goto use_sysfs;
- if (cpupower_cpu_info.vendor == X86_VENDOR_AMD) {
+ if (cpupower_cpu_info.vendor == X86_VENDOR_AMD ||
+ cpupower_cpu_info.vendor == X86_VENDOR_HYGON) {
/* MSR_AMD_HWCR tells us whether TSC runs at P0/mperf
* freq.
* A test whether hwcr is accessable/available would be: