Merge tag 'seccomp-v4.8-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
Pull seccomp fix from Kees Cook:
"Fix fatal signal delivery after ptrace reordering"
* tag 'seccomp-v4.8-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
seccomp: Fix tracer exit notifications during fatal signals
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index c55df29..cd9c9f6 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -94,14 +94,11 @@
min_vecs argument set to this limit, and the PCI core will return -ENOSPC
if it can't meet the minimum number of vectors.
-The flags argument should normally be set to 0, but can be used to pass the
-PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support
-MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in
-case the device does not support legacy interrupt lines.
-
-By default this function will spread the interrupts around the available
-CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY
-flag.
+The flags argument is used to specify which type of interrupt can be used
+by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX).
+A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for
+any possible kind of interrupt. If the PCI_IRQ_AFFINITY flag is set,
+pci_alloc_irq_vectors() will spread the interrupts around the available CPUs.
To get the Linux IRQ numbers passed to request_irq() and free_irq() and the
vectors, use the following function:
@@ -131,7 +128,7 @@
capped to the supported limit, so there is no need to query the number of
vectors supported beforehand:
- nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0);
+ nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES)
if (nvec < 0)
goto out_err;
@@ -140,7 +137,7 @@
number to pci_alloc_irq_vectors() function as both 'min_vecs' and
'max_vecs' parameters:
- ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0);
+ ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES);
if (ret < 0)
goto out_err;
@@ -148,15 +145,14 @@
the single MSI mode for a device. It could be done by passing two 1s as
'min_vecs' and 'max_vecs':
- ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+ ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (ret < 0)
goto out_err;
Some devices might not support using legacy line interrupts, in which case
-the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform
-can't provide MSI or MSI-X interrupts:
+the driver can specify that only MSI or MSI-X is acceptable:
- nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY);
+ nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX);
if (nvec < 0)
goto out_err;
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index 4da60b4..ccc6032 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -53,6 +53,7 @@
| ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 |
| ARM | Cortex-A57 | #852523 | N/A |
| ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 |
+| ARM | Cortex-A72 | #853709 | N/A |
| ARM | MMU-500 | #841119,#826419 | N/A |
| | | | |
| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 |
diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
index 6f6c2f8..0741dff 100644
--- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
+++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
@@ -8,8 +8,6 @@
- interrupts: Interrupt number for McPDM
- interrupt-parent: The parent interrupt controller
- ti,hwmods: Name of the hwmod associated to the McPDM
-- clocks: phandle for the pdmclk provider, likely <&twl6040>
-- clock-names: Must be "pdmclk"
Example:
@@ -21,11 +19,3 @@
interrupt-parent = <&gic>;
ti,hwmods = "mcpdm";
};
-
-In board DTS file the pdmclk needs to be added:
-
-&mcpdm {
- clocks = <&twl6040>;
- clock-names = "pdmclk";
- status = "okay";
-};
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
index 41b817f..88b6ea1 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -62,7 +62,7 @@
Required properties:
- #cooling-cells: Used to provide cooling device specific information
Type: unsigned while referring to it. Must be at least 2, in order
- Size: one cell to specify minimum and maximum cooling state used
+ Size: one cell to specify minimum and maximum cooling state used
in the reference. The first cell is the minimum
cooling state requested and the second cell is
the maximum cooling state requested in the reference.
@@ -119,7 +119,7 @@
Optional property:
- contribution: The cooling contribution to the thermal zone of the
Type: unsigned referred cooling device at the referred trip point.
- Size: one cell The contribution is a ratio of the sum
+ Size: one cell The contribution is a ratio of the sum
of all cooling contributions within a thermal zone.
Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle
@@ -145,7 +145,7 @@
Size: one cell
- thermal-sensors: A list of thermal sensor phandles and sensor specifier
- Type: list of used while monitoring the thermal zone.
+ Type: list of used while monitoring the thermal zone.
phandles + sensor
specifier
@@ -473,7 +473,7 @@
<&adc>; /* pcb north */
/* hotspot = 100 * bandgap - 120 * adc + 484 */
- coefficients = <100 -120 484>;
+ coefficients = <100 -120 484>;
trips {
...
@@ -502,7 +502,7 @@
thermal-sensors = <&adc>;
/* hotspot = 1 * adc + 6000 */
- coefficients = <1 6000>;
+ coefficients = <1 6000>;
(d) - Board thermal
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 46c030a..a4f4d69 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3032,6 +3032,10 @@
PAGE_SIZE is used as alignment.
PCI-PCI bridge can be specified, if resource
windows need to be expanded.
+ To specify the alignment for several
+ instances of a device, the PCI vendor,
+ device, subvendor, and subdevice may be
+ specified, e.g., 4096@pci:8086:9c22:103c:198f
ecrc= Enable/disable PCIe ECRC (transaction layer
end-to-end CRC checking).
bios: Use BIOS/firmware settings. This is the
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt
index 9d05ed7..f20c884 100644
--- a/Documentation/networking/dsa/dsa.txt
+++ b/Documentation/networking/dsa/dsa.txt
@@ -587,26 +587,6 @@
TODO
====
-The platform device problem
----------------------------
-DSA is currently implemented as a platform device driver which is far from ideal
-as was discussed in this thread:
-
-http://permalink.gmane.org/gmane.linux.network/329848
-
-This basically prevents the device driver model to be properly used and applied,
-and support non-MDIO, non-MMIO Ethernet connected switches.
-
-Another problem with the platform device driver approach is that it prevents the
-use of a modular switch drivers build due to a circular dependency, illustrated
-here:
-
-http://comments.gmane.org/gmane.linux.network/345803
-
-Attempts of reworking this has been done here:
-
-https://lwn.net/Articles/643149/
-
Making SWITCHDEV and DSA converge towards an unified codebase
-------------------------------------------------------------
diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.txt
index ba0a2a4..e32fdbb 100644
--- a/Documentation/powerpc/transactional_memory.txt
+++ b/Documentation/powerpc/transactional_memory.txt
@@ -167,6 +167,8 @@
For signals taken in non-TM or suspended mode, we use the
normal/non-checkpointed stack pointer.
+Any transaction initiated inside a sighandler and suspended on return
+from the sighandler to the kernel will get reclaimed and discarded.
Failure cause codes used by kernel
==================================
diff --git a/MAINTAINERS b/MAINTAINERS
index 0bbe4b1..71aa5da 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -881,6 +881,15 @@
F: drivers/gpu/drm/arc/
F: Documentation/devicetree/bindings/display/snps,arcpgu.txt
+ARM ARCHITECTED TIMER DRIVER
+M: Mark Rutland <mark.rutland@arm.com>
+M: Marc Zyngier <marc.zyngier@arm.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: arch/arm/include/asm/arch_timer.h
+F: arch/arm64/include/asm/arch_timer.h
+F: drivers/clocksource/arm_arch_timer.c
+
ARM HDLCD DRM DRIVER
M: Liviu Dudau <liviu.dudau@arm.com>
S: Supported
@@ -7661,7 +7670,7 @@
S: Supported
W: https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home
Q: http://patchwork.kernel.org/project/linux-rdma/list/
-F: drivers/infiniband/hw/rxe/
+F: drivers/infiniband/sw/rxe/
F: include/uapi/rdma/rdma_user_rxe.h
MEMBARRIER SUPPORT
diff --git a/Makefile b/Makefile
index 3537aa2..67f42d5 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
PATCHLEVEL = 8
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
NAME = Psychotic Stoned Sheep
# *DOCUMENTATION*
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index bda27b6..29d0b23 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1309,7 +1309,7 @@
smp_rmb();
pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
- if (is_error_pfn(pfn))
+ if (is_error_noslot_pfn(pfn))
return -EFAULT;
if (kvm_is_device_pfn(pfn)) {
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index c410d84..66070ac 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -83,7 +83,8 @@
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_USE_DMA | SMC91X_NOWAIT,
};
static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index 3f06cd9..056369e 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -120,7 +120,8 @@
};
static struct smc91x_platdata xcep_smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT | SMC91X_USE_DMA,
};
static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index baf1745..a0ead0a 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -93,7 +93,8 @@
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
};
static struct platform_device realview_eth_device = {
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 1525d7b..88149f8 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -45,7 +45,7 @@
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT,
};
static struct platform_device smc91x_device = {
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index b0b82f5..3d2cef6 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -50,7 +50,7 @@
static struct vcpu_info __percpu *xen_vcpu_info;
/* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
/* These are unused until we support booting "pre-ballooned" */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b77f583..3e7b050 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -757,6 +757,9 @@
isb
bl __create_page_tables // recreate kernel mapping
+ tlbi vmalle1 // Remove any stale TLB entries
+ dsb nsh
+
msr sctlr_el1, x19 // re-enable the MMU
isb
ic iallu // flush instructions fetched
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index ae7855f..5a84b45 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -256,7 +256,7 @@
/*
* We must restore the 32-bit state before the sysregs, thanks
- * to Cortex-A57 erratum #852523.
+ * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
*/
__sysreg32_restore_state(vcpu);
__sysreg_restore_guest_state(guest_ctxt);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index b0b225c..e51367d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -823,14 +823,6 @@
* Architected system registers.
* Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
*
- * We could trap ID_DFR0 and tell the guest we don't support performance
- * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was
- * NAKed, so it will read the PMCR anyway.
- *
- * Therefore we tell the guest we have 0 counters. Unfortunately, we
- * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
- * all PM registers, which doesn't crash the guest kernel at least.
- *
* Debug handling: We do trap most, if not all debug related system
* registers. The implementation is good enough to ensure that a guest
* can use these with minimal performance degradation. The drawback is
@@ -1360,7 +1352,7 @@
{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
/* ICC_SRE */
- { Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },
+ { Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre },
{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index c6db52b..10c5777 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -146,7 +146,8 @@
#include <linux/smc91x.h>
static struct smc91x_platdata smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
.leda = RPC_LED_100_10,
.ledb = RPC_LED_TX_RX,
};
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index f35525b..57d1c43 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -134,7 +134,8 @@
#include <linux/smc91x.h>
static struct smc91x_platdata smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
.leda = RPC_LED_100_10,
.ledb = RPC_LED_TX_RX,
};
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ea0cd97..5f98759 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -164,7 +164,7 @@
*/
static inline unsigned long ___pa(unsigned long x)
{
- if (config_enabled(CONFIG_64BIT)) {
+ if (IS_ENABLED(CONFIG_64BIT)) {
/*
* For MIPS64 the virtual address may either be in one of
* the compatibility segements ckseg0 or ckseg1, or it may
@@ -173,7 +173,7 @@
return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x);
}
- if (!config_enabled(CONFIG_EVA)) {
+ if (!IS_ENABLED(CONFIG_EVA)) {
/*
* We're using the standard MIPS32 legacy memory map, ie.
* the address x is going to be in kseg0 or kseg1. We can
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 6cfdcf5..121008c 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -40,7 +40,7 @@
srcu_idx = srcu_read_lock(&kvm->srcu);
pfn = gfn_to_pfn(kvm, gfn);
- if (is_error_pfn(pfn)) {
+ if (is_error_noslot_pfn(pfn)) {
kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn);
err = -EFAULT;
goto out;
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index cd87781..af12c2d 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -1,6 +1,5 @@
config PARISC
def_bool y
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_MIGHT_HAVE_PC_PARPORT
select HAVE_IDE
select HAVE_OPROFILE
diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig
index 1a8f6f95..f6a4c01 100644
--- a/arch/parisc/configs/c8000_defconfig
+++ b/arch/parisc/configs/c8000_defconfig
@@ -245,7 +245,6 @@
CONFIG_PROVE_RCU_DELAY=y
CONFIG_DEBUG_BLOCK_EXT_DEVT=y
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_KEYS=y
# CONFIG_CRYPTO_HW is not set
CONFIG_FONTS=y
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index 7e07926..c564e6e 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -291,7 +291,6 @@
CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
# CONFIG_SCHED_DEBUG is not set
CONFIG_TIMER_STATS=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_PCBC=m
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 0f59fd9..e915048 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -208,13 +208,13 @@
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
-extern void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
- __compiletime_error("copy_from_user() buffer size is not provably correct")
-#else
- __compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
static inline unsigned long __must_check copy_from_user(void *to,
const void __user *from,
@@ -223,10 +223,12 @@
int sz = __compiletime_object_size(to);
int ret = -EFAULT;
- if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n))
+ if (likely(sz == -1 || sz >= n))
ret = __copy_from_user(to, from, n);
- else
- copy_from_user_overflow();
+ else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
+ else
+ __bad_copy_user();
return ret;
}
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 666bef4e..9377bdf 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -3,6 +3,7 @@
#ifndef __ASSEMBLY__
#include <linux/cpumask.h>
+#include <asm/cpu_has_feature.h>
/*
* Mapping of threads to cores
diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h
index 88b4901..85b7a1a 100644
--- a/arch/powerpc/include/asm/hmi.h
+++ b/arch/powerpc/include/asm/hmi.h
@@ -21,7 +21,7 @@
#ifndef __ASM_PPC64_HMI_H__
#define __ASM_PPC64_HMI_H__
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
#define CORE_TB_RESYNC_REQ_BIT 63
#define MAX_SUBCORE_PER_CORE 4
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 148303e7..6a6792b 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -183,11 +183,6 @@
*/
u16 in_mce;
u8 hmi_event_available; /* HMI event is available */
- /*
- * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
- * more details
- */
- struct sibling_subcore_state *sibling_subcore_state;
#endif
/* Stuff for accurate time accounting */
@@ -202,6 +197,13 @@
struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
#endif
struct kvmppc_host_state kvm_hstate;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /*
+ * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+ * more details
+ */
+ struct sibling_subcore_state *sibling_subcore_state;
+#endif
#endif
};
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index b5e88e4..c0309c5 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -301,6 +301,7 @@
/* Allocate & free a PCI host bridge structure */
extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge);
#ifdef CONFIG_PCI
extern int pcibios_vaddr_is_ioport(void __iomem *address);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b2027a5..fe4c075 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -41,7 +41,7 @@
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o hmi.o
+obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
obj-$(CONFIG_PPC64) += vdso64/
obj-$(CONFIG_ALTIVEC) += vecemu.o
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6b8bc0d..5afd03e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -368,13 +368,13 @@
tabort_syscall:
/* Firstly we need to enable TM in the kernel */
mfmsr r10
- li r13, 1
- rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+ li r9, 1
+ rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG
mtmsrd r10, 0
/* tabort, this dooms the transaction, nothing else */
- li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
- TABORT(R13)
+ li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+ TABORT(R9)
/*
* Return directly to userspace. We have corrupted user register state,
@@ -382,8 +382,8 @@
* resume after the tbegin of the aborted transaction with the
* checkpointed register state.
*/
- li r13, MSR_RI
- andc r10, r10, r13
+ li r9, MSR_RI
+ andc r10, r10, r9
mtmsrd r10, 1
mtspr SPRN_SRR0, r11
mtspr SPRN_SRR1, r12
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index df6d45e..bffec73 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -485,7 +485,23 @@
EXCEPTION_PROLOG_0(PACA_EXMC)
machine_check_pSeries_0:
EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200)
- EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD)
+ /*
+ * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the
+ * difference that MSR_RI is not enabled, because PACA_EXMC is being
+ * used, so nested machine check corrupts it. machine_check_common
+ * enables MSR_RI.
+ */
+ ld r12,PACAKBASE(r13)
+ ld r10,PACAKMSR(r13)
+ xori r10,r10,MSR_RI
+ mfspr r11,SPRN_SRR0
+ LOAD_HANDLER(r12, machine_check_common)
+ mtspr SPRN_SRR0,r12
+ mfspr r12,SPRN_SRR1
+ mtspr SPRN_SRR1,r10
+ rfid
+ b . /* prevent speculative execution */
+
KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
@@ -969,14 +985,17 @@
machine_check_common:
mfspr r10,SPRN_DAR
- std r10,PACA_EXGEN+EX_DAR(r13)
+ std r10,PACA_EXMC+EX_DAR(r13)
mfspr r10,SPRN_DSISR
- stw r10,PACA_EXGEN+EX_DSISR(r13)
+ stw r10,PACA_EXMC+EX_DSISR(r13)
EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
FINISH_NAP
RECONCILE_IRQ_STATE(r10, r11)
- ld r3,PACA_EXGEN+EX_DAR(r13)
- lwz r4,PACA_EXGEN+EX_DSISR(r13)
+ ld r3,PACA_EXMC+EX_DAR(r13)
+ lwz r4,PACA_EXMC+EX_DSISR(r13)
+ /* Enable MSR_RI when finished with PACA_EXMC */
+ li r10,MSR_RI
+ mtmsrd r10,1
std r3,_DAR(r1)
std r4,_DSISR(r1)
bl save_nvgprs
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 3ed8ec09..e785cc9 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -29,7 +29,7 @@
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/preempt.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
#include <asm/code-patching.h>
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 7fdf324..e589080 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -154,6 +154,42 @@
EXPORT_SYMBOL_GPL(pcibios_free_controller);
/*
+ * This function is used to call pcibios_free_controller()
+ * in a deferred manner: a callback from the PCI subsystem.
+ *
+ * _*DO NOT*_ call pcibios_free_controller() explicitly if
+ * this is used (or it may access an invalid *phb pointer).
+ *
+ * The callback occurs when all references to the root bus
+ * are dropped (e.g., child buses/devices and their users).
+ *
+ * It's called as .release_fn() of 'struct pci_host_bridge'
+ * which is associated with the 'struct pci_controller.bus'
+ * (root bus) - it expects .release_data to hold a pointer
+ * to 'struct pci_controller'.
+ *
+ * In order to use it, register .release_fn()/release_data
+ * like this:
+ *
+ * pci_set_host_bridge_release(bridge,
+ * pcibios_free_controller_deferred
+ * (void *) phb);
+ *
+ * e.g. in the pcibios_root_bridge_prepare() callback from
+ * pci_create_root_bus().
+ */
+void pcibios_free_controller_deferred(struct pci_host_bridge *bridge)
+{
+ struct pci_controller *phb = (struct pci_controller *)
+ bridge->release_data;
+
+ pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic);
+
+ pcibios_free_controller(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred);
+
+/*
* The function is used to return the minimal alignment
* for memory or I/O windows of the associated P2P bridge.
* By default, 4KiB alignment for I/O windows and 1MiB for
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 4e74fc5..d3eff99 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -695,7 +695,7 @@
OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */
/* option vector 5: PAPR/OF options */
- VECTOR_LENGTH(18), /* length */
+ VECTOR_LENGTH(21), /* length */
0, /* don't ignore, don't halt */
OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -726,8 +726,11 @@
0,
0,
OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
- OV5_FEAT(OV5_PFO_HW_842),
- OV5_FEAT(OV5_SUB_PROCESSORS),
+ OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */
+ 0, /* Byte 18 */
+ 0, /* Byte 19 */
+ 0, /* Byte 20 */
+ OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */
/* option vector 6: IBM PAPR hints */
VECTOR_LENGTH(3), /* length */
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index b6aa378..a7daf74 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1226,7 +1226,21 @@
(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf)))
goto bad;
+
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * If there is a transactional state then throw it away.
+ * The purpose of a sigreturn is to destroy all traces of the
+ * signal frame, this includes any transactional state created
+ * within in. We only check for suspended as we can never be
+ * active in the kernel, we are active, there is nothing better to
+ * do than go ahead and Bad Thing later.
+ * The cause is not important as there will never be a
+ * recheckpoint so it's not user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+
if (__get_user(tmp, &rt_sf->uc.uc_link))
goto bad;
uc_transact = (struct ucontext __user *)(uintptr_t)tmp;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 7e49984..70409bb 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -676,7 +676,21 @@
if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
goto badframe;
set_current_blocked(&set);
+
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * If there is a transactional state then throw it away.
+ * The purpose of a sigreturn is to destroy all traces of the
+ * signal frame, this includes any transactional state created
+ * within in. We only check for suspended as we can never be
+ * active in the kernel, we are active, there is nothing better to
+ * do than go ahead and Bad Thing later.
+ * The cause is not important as there will never be a
+ * recheckpoint so it's not user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+
if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
goto badframe;
if (MSR_TM_ACTIVE(msr)) {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 25a3905..9c6f3fd 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -830,7 +830,7 @@
/* Update sibling maps */
base = cpu_first_thread_sibling(cpu);
- for (i = 0; i < threads_per_core; i++) {
+ for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) {
cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));
cpumask_clear_cpu(cpu, cpu_core_mask(base + i));
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 2cb5892..62859eb 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -25,7 +25,8 @@
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
+#include <linux/module.h> /* print_modules */
#include <linux/prctl.h>
#include <linux/delay.h>
#include <linux/kprobes.h>
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 1f9e552..855d4b9 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -78,6 +78,7 @@
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+ book3s_hv_hmi.o \
book3s_hv_rmhandlers.o \
book3s_hv_rm_mmu.o \
book3s_hv_ras.o \
diff --git a/arch/powerpc/kernel/hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c
similarity index 100%
rename from arch/powerpc/kernel/hmi.c
rename to arch/powerpc/kvm/book3s_hv_hmi.c
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index a4db22f..bb1ffc5 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -26,7 +26,7 @@
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/perf_event.h>
diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index 8eb82b0..d93dd4a 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -528,7 +528,6 @@
.remove = mpc512x_lpbfifo_remove,
.driver = {
.name = DRV_NAME,
- .owner = THIS_MODULE,
.of_match_table = mpc512x_lpbfifo_match,
},
};
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index dbcd030..63c5ab64 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -222,7 +222,6 @@
static struct i2c_driver mcu_driver = {
.driver = {
.name = "mcu-mpc8349emitx",
- .owner = THIS_MODULE,
.of_match_table = mcu_of_match_table,
},
.probe = mcu_probe,
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index dafba10..dfd3100 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -26,7 +26,7 @@
#include <linux/tty.h>
#include <linux/serial_core.h>
#include <linux/of_platform.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <asm/time.h>
#include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index 80804f9..f97bab8 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -23,7 +23,7 @@
#include <linux/pci.h>
#include <linux/kdev_t.h>
#include <linux/console.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/seq_file.h>
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 2ee9643..4c82782 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -370,6 +370,7 @@
uint32_t dump_id, dump_size, dump_type;
struct dump_obj *dump;
char name[22];
+ struct kobject *kobj;
rc = dump_read_info(&dump_id, &dump_size, &dump_type);
if (rc != OPAL_SUCCESS)
@@ -381,8 +382,12 @@
* that gracefully and not create two conflicting
* entries.
*/
- if (kset_find_obj(dump_kset, name))
+ kobj = kset_find_obj(dump_kset, name);
+ if (kobj) {
+ /* Drop reference added by kset_find_obj() */
+ kobject_put(kobj);
return 0;
+ }
dump = create_dump_obj(dump_id, dump_size, dump_type);
if (!dump)
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 37f959b..f2344cb 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -247,6 +247,7 @@
uint64_t elog_type;
int rc;
char name[2+16+1];
+ struct kobject *kobj;
rc = opal_get_elog_size(&id, &size, &type);
if (rc != OPAL_SUCCESS) {
@@ -269,8 +270,12 @@
* that gracefully and not create two conflicting
* entries.
*/
- if (kset_find_obj(elog_kset, name))
+ kobj = kset_find_obj(elog_kset, name);
+ if (kobj) {
+ /* Drop reference added by kset_find_obj() */
+ kobject_put(kobj);
return IRQ_HANDLED;
+ }
create_elog_obj(log_id, elog_size, elog_type);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index fd9444f..1321826 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -149,7 +149,7 @@
static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
{
- unsigned long pe = phb->ioda.total_pe_num - 1;
+ long pe;
for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
if (!test_and_set_bit(pe, phb->ioda.pe_alloc))
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index fe16a50..09eba5a 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -119,6 +119,10 @@
bus = bridge->bus;
+ /* Rely on the pcibios_free_controller_deferred() callback. */
+ pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred,
+ (void *) pci_bus_to_host(bus));
+
dn = pcibios_get_phb_of_node(bus);
if (!dn)
return 0;
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 906dbaa..547fd13 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -106,8 +106,11 @@
release_resource(res);
}
- /* Free pci_controller data structure */
- pcibios_free_controller(phb);
+ /*
+ * The pci_controller data structure is freed by
+ * the pcibios_free_controller_deferred() callback;
+ * see pseries_root_bridge_prepare().
+ */
return 0;
}
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 6c11099..81d4947 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -534,7 +534,8 @@
static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm1_gpio16_chip *cpm1_gc =
+ container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc);
struct cpm_ioport16 __iomem *iop = mm_gc->regs;
cpm1_gc->cpdata = in_be16(&iop->dat);
@@ -649,7 +650,8 @@
static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm1_gpio32_chip *cpm1_gc =
+ container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc);
struct cpm_ioport32b __iomem *iop = mm_gc->regs;
cpm1_gc->cpdata = in_be32(&iop->dat);
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 911456d..947f420 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -94,7 +94,8 @@
static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm2_gpio32_chip *cpm2_gc =
+ container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc);
struct cpm2_ioports __iomem *iop = mm_gc->regs;
cpm2_gc->cpdata = in_be32(&iop->dat);
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 68e7c0d..3cc7cac 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -23,7 +23,7 @@
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/types.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e751fe2..c109f07 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -68,7 +68,6 @@
config S390
def_bool y
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 26e0c7f..412b1bd 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -602,7 +602,6 @@
CONFIG_FAULT_INJECTION_DEBUG_FS=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_IRQSOFF_TRACER=y
CONFIG_PREEMPT_TRACER=y
CONFIG_SCHED_TRACER=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 24879da..bec279e 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -552,7 +552,6 @@
CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
CONFIG_PM_NOTIFIER_ERROR_INJECT=m
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_BLK_DEV_IO_TRACE=y
# CONFIG_KPROBE_EVENT is not set
CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index a5c1e5f..1751446 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -549,7 +549,6 @@
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_STACK_TRACER=y
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 73610f2..2d40ef0 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -172,7 +172,6 @@
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_RCU_TRACE=y
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 9b49cf1..95aefdb 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -311,6 +311,14 @@
#define __put_user_unaligned __put_user
#define __get_user_unaligned __get_user
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
/**
* copy_to_user: - Copy a block of data into user space.
* @to: Destination address, in user space.
@@ -332,12 +340,6 @@
return __copy_to_user(to, from, n);
}
-void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-__compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
-
/**
* copy_from_user: - Copy a block of data from user space.
* @to: Destination address, in kernel space.
@@ -362,7 +364,10 @@
might_fault();
if (unlikely(sz != -1 && sz < n)) {
- copy_from_user_overflow();
+ if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
+ else
+ __bad_copy_user();
return n;
}
return __copy_from_user(to, from, n);
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ba5f456..7f7ba5f2 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -204,11 +204,9 @@
#endif
}
} else if (MACHINE_IS_KVM) {
- if (sclp.has_vt220 &&
- config_enabled(CONFIG_SCLP_VT220_CONSOLE))
+ if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE))
SET_CONSOLE_VT220;
- else if (sclp.has_linemode &&
- config_enabled(CONFIG_SCLP_CONSOLE))
+ else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE))
SET_CONSOLE_SCLP;
else
SET_CONSOLE_HVC;
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 4820a02..78da75b 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -4,7 +4,6 @@
config TILE
def_bool y
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index 0a9c4265..a77369e 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -416,14 +416,13 @@
return n;
}
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-/*
- * There are still unprovable places in the generic code as of 2.6.34, so this
- * option is not really compatible with -Werror, which is more useful in
- * general.
- */
-extern void copy_from_user_overflow(void)
- __compiletime_warning("copy_from_user() size is not provably correct");
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
static inline unsigned long __must_check copy_from_user(void *to,
const void __user *from,
@@ -433,14 +432,13 @@
if (likely(sz == -1 || sz >= n))
n = _copy_from_user(to, from, n);
+ else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
else
- copy_from_user_overflow();
+ __bad_copy_user();
return n;
}
-#else
-#define copy_from_user _copy_from_user
-#endif
#ifdef __tilegx__
/**
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index 1dd5bd8..1330553 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -81,7 +81,7 @@
.altinstr_replacement : { *(.altinstr_replacement) }
/* .exit.text is discard at runtime, not link time, to deal with references
from .altinstructions and .eh_frame */
- .exit.text : { *(.exit.text) }
+ .exit.text : { EXIT_TEXT }
.exit.data : { *(.exit.data) }
.preinit_array : {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c580d8c..2a1f0ce 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,7 +24,6 @@
select ARCH_DISCARD_MEMBLOCK
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
index 89fa85e..6f97fb3 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -485,10 +485,10 @@
req = cast_mcryptd_ctx_to_req(req_ctx);
if (irqs_disabled())
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
else {
local_bh_disable();
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
local_bh_enable();
}
}
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
index b691da9..a78a069 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -265,13 +265,14 @@
vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
- movl _args_digest+4*32(state, idx, 4), tmp2_w
+ vmovd _args_digest(state , idx, 4) , %xmm0
vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
- vmovdqu %xmm0, _result_digest(job_rax)
- movl tmp2_w, _result_digest+1*16(job_rax)
+ vmovdqu %xmm0, _result_digest(job_rax)
+ offset = (_result_digest + 1*16)
+ vmovdqu %xmm1, offset(job_rax)
pop %rbx
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index f4cf5b7..d210174 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -497,10 +497,10 @@
req = cast_mcryptd_ctx_to_req(req_ctx);
if (irqs_disabled())
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
else {
local_bh_disable();
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
local_bh_enable();
}
}
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a0ae610..c3f2911 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -697,43 +697,14 @@
unsigned long __must_check _copy_to_user(void __user *to, const void *from,
unsigned n);
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-# define copy_user_diag __compiletime_error
-#else
-# define copy_user_diag __compiletime_warning
-#endif
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
-extern void copy_user_diag("copy_from_user() buffer size is too small")
-copy_from_user_overflow(void);
-extern void copy_user_diag("copy_to_user() buffer size is too small")
-copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
-
-#undef copy_user_diag
-
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-
-extern void
-__compiletime_warning("copy_from_user() buffer size is not provably correct")
-__copy_from_user_overflow(void) __asm__("copy_from_user_overflow");
-#define __copy_from_user_overflow(size, count) __copy_from_user_overflow()
-
-extern void
-__compiletime_warning("copy_to_user() buffer size is not provably correct")
-__copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
-#define __copy_to_user_overflow(size, count) __copy_to_user_overflow()
-
-#else
-
-static inline void
-__copy_from_user_overflow(int size, unsigned long count)
+static inline void copy_user_overflow(int size, unsigned long count)
{
WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
}
-#define __copy_to_user_overflow __copy_from_user_overflow
-
-#endif
-
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
@@ -743,31 +714,13 @@
kasan_check_write(to, n);
- /*
- * While we would like to have the compiler do the checking for us
- * even in the non-constant size case, any false positives there are
- * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even
- * without - the [hopefully] dangerous looking nature of the warning
- * would make people go look at the respecitive call sites over and
- * over again just to find that there's no problem).
- *
- * And there are cases where it's just not realistic for the compiler
- * to prove the count to be in range. For example when multiple call
- * sites of a helper function - perhaps in different source files -
- * all doing proper range checking, yet the helper function not doing
- * so again.
- *
- * Therefore limit the compile time checking to the constant size
- * case, and do only runtime checking for non-constant sizes.
- */
-
if (likely(sz < 0 || sz >= n)) {
check_object_size(to, n, false);
n = _copy_from_user(to, from, n);
- } else if (__builtin_constant_p(n))
- copy_from_user_overflow();
+ } else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
else
- __copy_from_user_overflow(sz, n);
+ __bad_copy_user();
return n;
}
@@ -781,21 +734,17 @@
might_fault();
- /* See the comment in copy_from_user() above. */
if (likely(sz < 0 || sz >= n)) {
check_object_size(from, n, true);
n = _copy_to_user(to, from, n);
- } else if (__builtin_constant_p(n))
- copy_to_user_overflow();
+ } else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
else
- __copy_to_user_overflow(sz, n);
+ __bad_copy_user();
return n;
}
-#undef __copy_from_user_overflow
-#undef __copy_to_user_overflow
-
/*
* We rely on the nested NMI work to allow atomic faults from the NMI path; the
* nested NMI paths are careful to preserve CR2.
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index cea4fc1..50c95af 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1623,6 +1623,9 @@
unsigned long flags;
int ret, ir_stat;
+ if (skip_ioapic_setup)
+ return;
+
ir_stat = irq_remapping_prepare();
if (ir_stat < 0 && !x2apic_supported())
return;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a45d858..5cede40 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -422,6 +422,7 @@
struct list_head vmcs02_pool;
int vmcs02_num;
u64 vmcs01_tsc_offset;
+ bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
/*
@@ -435,6 +436,8 @@
bool pi_pending;
u16 posted_intr_nv;
+ unsigned long *msr_bitmap;
+
struct hrtimer preemption_timer;
bool preemption_timer_expired;
@@ -924,7 +927,6 @@
static unsigned long *vmx_msr_bitmap_longmode;
static unsigned long *vmx_msr_bitmap_legacy_x2apic;
static unsigned long *vmx_msr_bitmap_longmode_x2apic;
-static unsigned long *vmx_msr_bitmap_nested;
static unsigned long *vmx_vmread_bitmap;
static unsigned long *vmx_vmwrite_bitmap;
@@ -2198,6 +2200,12 @@
new.control) != old.control);
}
+static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
+{
+ vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+}
+
/*
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
@@ -2256,10 +2264,8 @@
/* Setup TSC multiplier */
if (kvm_has_tsc_control &&
- vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
- vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
- vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
- }
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
+ decache_tsc_multiplier(vmx);
vmx_vcpu_pi_load(vcpu, cpu);
vmx->host_pkru = read_pkru();
@@ -2508,7 +2514,7 @@
unsigned long *msr_bitmap;
if (is_guest_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_nested;
+ msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
else if (cpu_has_secondary_exec_ctrls() &&
(vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
@@ -6363,13 +6369,6 @@
if (!vmx_msr_bitmap_longmode_x2apic)
goto out4;
- if (nested) {
- vmx_msr_bitmap_nested =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_nested)
- goto out5;
- }
-
vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_vmread_bitmap)
goto out6;
@@ -6392,8 +6391,6 @@
memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
- if (nested)
- memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE);
if (setup_vmcs_config(&vmcs_config) < 0) {
r = -EIO;
@@ -6529,9 +6526,6 @@
out7:
free_page((unsigned long)vmx_vmread_bitmap);
out6:
- if (nested)
- free_page((unsigned long)vmx_msr_bitmap_nested);
-out5:
free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
out4:
free_page((unsigned long)vmx_msr_bitmap_longmode);
@@ -6557,8 +6551,6 @@
free_page((unsigned long)vmx_io_bitmap_a);
free_page((unsigned long)vmx_vmwrite_bitmap);
free_page((unsigned long)vmx_vmread_bitmap);
- if (nested)
- free_page((unsigned long)vmx_msr_bitmap_nested);
free_kvm_area();
}
@@ -6995,16 +6987,21 @@
return 1;
}
+ if (cpu_has_vmx_msr_bitmap()) {
+ vmx->nested.msr_bitmap =
+ (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx->nested.msr_bitmap)
+ goto out_msr_bitmap;
+ }
+
vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_vmcs12)
- return -ENOMEM;
+ goto out_cached_vmcs12;
if (enable_shadow_vmcs) {
shadow_vmcs = alloc_vmcs();
- if (!shadow_vmcs) {
- kfree(vmx->nested.cached_vmcs12);
- return -ENOMEM;
- }
+ if (!shadow_vmcs)
+ goto out_shadow_vmcs;
/* mark vmcs as shadow */
shadow_vmcs->revision_id |= (1u << 31);
/* init shadow vmcs */
@@ -7024,6 +7021,15 @@
skip_emulated_instruction(vcpu);
nested_vmx_succeed(vcpu);
return 1;
+
+out_shadow_vmcs:
+ kfree(vmx->nested.cached_vmcs12);
+
+out_cached_vmcs12:
+ free_page((unsigned long)vmx->nested.msr_bitmap);
+
+out_msr_bitmap:
+ return -ENOMEM;
}
/*
@@ -7098,6 +7104,10 @@
vmx->nested.vmxon = false;
free_vpid(vmx->nested.vpid02);
nested_release_vmcs12(vmx);
+ if (vmx->nested.msr_bitmap) {
+ free_page((unsigned long)vmx->nested.msr_bitmap);
+ vmx->nested.msr_bitmap = NULL;
+ }
if (enable_shadow_vmcs)
free_vmcs(vmx->nested.current_shadow_vmcs);
kfree(vmx->nested.cached_vmcs12);
@@ -8419,6 +8429,12 @@
{
u32 sec_exec_control;
+ /* Postpone execution until vmcs01 is the current VMCS. */
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+ return;
+ }
+
/*
* There is not point to enable virtualize x2apic without enable
* apicv
@@ -9472,8 +9488,10 @@
{
int msr;
struct page *page;
- unsigned long *msr_bitmap;
+ unsigned long *msr_bitmap_l1;
+ unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap;
+ /* This shortcut is ok because we support only x2APIC MSRs so far. */
if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
return false;
@@ -9482,63 +9500,37 @@
WARN_ON(1);
return false;
}
- msr_bitmap = (unsigned long *)kmap(page);
- if (!msr_bitmap) {
+ msr_bitmap_l1 = (unsigned long *)kmap(page);
+ if (!msr_bitmap_l1) {
nested_release_page_clean(page);
WARN_ON(1);
return false;
}
+ memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
+
if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
if (nested_cpu_has_apic_reg_virt(vmcs12))
for (msr = 0x800; msr <= 0x8ff; msr++)
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
msr, MSR_TYPE_R);
- /* TPR is allowed */
- nested_vmx_disable_intercept_for_msr(msr_bitmap,
- vmx_msr_bitmap_nested,
+
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_TASKPRI >> 4),
MSR_TYPE_R | MSR_TYPE_W);
+
if (nested_cpu_has_vid(vmcs12)) {
- /* EOI and self-IPI are allowed */
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_EOI >> 4),
MSR_TYPE_W);
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
MSR_TYPE_W);
}
- } else {
- /*
- * Enable reading intercept of all the x2apic
- * MSRs. We should not rely on vmcs12 to do any
- * optimizations here, it may have been modified
- * by L1.
- */
- for (msr = 0x800; msr <= 0x8ff; msr++)
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- msr,
- MSR_TYPE_R);
-
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_TASKPRI >> 4),
- MSR_TYPE_W);
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_EOI >> 4),
- MSR_TYPE_W);
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
- MSR_TYPE_W);
}
kunmap(page);
nested_release_page_clean(page);
@@ -9957,10 +9949,10 @@
}
if (cpu_has_vmx_msr_bitmap() &&
- exec_control & CPU_BASED_USE_MSR_BITMAPS) {
- nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
- /* MSR_BITMAP will be set by following vmx_set_efer. */
- } else
+ exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+ nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
+ ; /* MSR_BITMAP will be set by following vmx_set_efer. */
+ else
exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
/*
@@ -10011,6 +10003,8 @@
vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
else
vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+ if (kvm_has_tsc_control)
+ decache_tsc_multiplier(vmx);
if (enable_vpid) {
/*
@@ -10767,6 +10761,14 @@
else
vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
PIN_BASED_VMX_PREEMPTION_TIMER);
+ if (kvm_has_tsc_control)
+ decache_tsc_multiplier(vmx);
+
+ if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+ vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+ vmx_set_virtual_x2apic_mode(vcpu,
+ vcpu->arch.apic_base & X2APIC_ENABLE);
+ }
/* This is needed for same reason as it was needed in prepare_vmcs02 */
vmx->host_rsp = 0;
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index ec8654f..bda8d5e 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -77,7 +77,7 @@
*/
static inline bool kaslr_memory_enabled(void)
{
- return kaslr_enabled() && !config_enabled(CONFIG_KASAN);
+ return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN);
}
/* Initialize base and padding for each memory region randomized with KASLR */
diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c
index b814ca6..7948be3 100644
--- a/arch/x86/pci/vmd.c
+++ b/arch/x86/pci/vmd.c
@@ -41,6 +41,7 @@
* @node: list item for parent traversal.
* @rcu: RCU callback item for freeing.
* @irq: back pointer to parent.
+ * @enabled: true if driver enabled IRQ
* @virq: the virtual IRQ value provided to the requesting driver.
*
* Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
@@ -50,6 +51,7 @@
struct list_head node;
struct rcu_head rcu;
struct vmd_irq_list *irq;
+ bool enabled;
unsigned int virq;
};
@@ -122,7 +124,9 @@
unsigned long flags;
raw_spin_lock_irqsave(&list_lock, flags);
+ WARN_ON(vmdirq->enabled);
list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
+ vmdirq->enabled = true;
raw_spin_unlock_irqrestore(&list_lock, flags);
data->chip->irq_unmask(data);
@@ -136,8 +140,10 @@
data->chip->irq_mask(data);
raw_spin_lock_irqsave(&list_lock, flags);
- list_del_rcu(&vmdirq->node);
- INIT_LIST_HEAD_RCU(&vmdirq->node);
+ if (vmdirq->enabled) {
+ list_del_rcu(&vmdirq->node);
+ vmdirq->enabled = false;
+ }
raw_spin_unlock_irqrestore(&list_lock, flags);
}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 8ffb089..b86ebb1 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -118,7 +118,7 @@
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
/* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
enum xen_domain_type xen_domain_type = XEN_NATIVE;
diff --git a/block/bio.c b/block/bio.c
index f394775..aa73540 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -667,18 +667,19 @@
bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
- if (bio_op(bio) == REQ_OP_DISCARD)
- goto integrity_clone;
-
- if (bio_op(bio) == REQ_OP_WRITE_SAME) {
+ switch (bio_op(bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
+ break;
+ case REQ_OP_WRITE_SAME:
bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
- goto integrity_clone;
+ break;
+ default:
+ bio_for_each_segment(bv, bio_src, iter)
+ bio->bi_io_vec[bio->bi_vcnt++] = bv;
+ break;
}
- bio_for_each_segment(bv, bio_src, iter)
- bio->bi_io_vec[bio->bi_vcnt++] = bv;
-
-integrity_clone:
if (bio_integrity(bio_src)) {
int ret;
@@ -1788,7 +1789,7 @@
* Discards need a mutable bio_vec to accommodate the payload
* required by the DSM TRIM and UNMAP commands.
*/
- if (bio_op(bio) == REQ_OP_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
split = bio_clone_bioset(bio, gfp, bs);
else
split = bio_clone_fast(bio, gfp, bs);
diff --git a/block/blk-core.c b/block/blk-core.c
index 999442e..36c7ac3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -515,7 +515,9 @@
void blk_set_queue_dying(struct request_queue *q)
{
- queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+ spin_lock_irq(q->queue_lock);
+ queue_flag_set(QUEUE_FLAG_DYING, q);
+ spin_unlock_irq(q->queue_lock);
if (q->mq_ops)
blk_mq_wake_waiters(q);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3eec75a..2642e5f 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -94,9 +94,31 @@
bool do_split = true;
struct bio *new = NULL;
const unsigned max_sectors = get_max_io_size(q, bio);
+ unsigned bvecs = 0;
bio_for_each_segment(bv, bio, iter) {
/*
+ * With arbitrary bio size, the incoming bio may be very
+ * big. We have to split the bio into small bios so that
+ * each holds at most BIO_MAX_PAGES bvecs because
+ * bio_clone() can fail to allocate big bvecs.
+ *
+ * It should have been better to apply the limit per
+ * request queue in which bio_clone() is involved,
+ * instead of globally. The biggest blocker is the
+ * bio_clone() in bio bounce.
+ *
+ * If bio is splitted by this reason, we should have
+ * allowed to continue bios merging, but don't do
+ * that now for making the change simple.
+ *
+ * TODO: deal with bio bounce's bio_clone() gracefully
+ * and convert the global limit into per-queue limit.
+ */
+ if (bvecs++ >= BIO_MAX_PAGES)
+ goto split;
+
+ /*
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
*/
@@ -172,12 +194,18 @@
struct bio *split, *res;
unsigned nsegs;
- if (bio_op(*bio) == REQ_OP_DISCARD)
+ switch (bio_op(*bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
split = blk_bio_discard_split(q, *bio, bs, &nsegs);
- else if (bio_op(*bio) == REQ_OP_WRITE_SAME)
+ break;
+ case REQ_OP_WRITE_SAME:
split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
- else
+ break;
+ default:
split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+ break;
+ }
/* physical segments can be figured out during splitting */
res = split ? split : *bio;
@@ -213,7 +241,7 @@
* This should probably be returning 0, but blk_add_request_payload()
* (Christoph!!!!)
*/
- if (bio_op(bio) == REQ_OP_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
return 1;
if (bio_op(bio) == REQ_OP_WRITE_SAME)
@@ -385,7 +413,9 @@
nsegs = 0;
cluster = blk_queue_cluster(q);
- if (bio_op(bio) == REQ_OP_DISCARD) {
+ switch (bio_op(bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
/*
* This is a hack - drivers should be neither modifying the
* biovec, nor relying on bi_vcnt - but because of
@@ -393,19 +423,16 @@
* a payload we need to set up here (thank you Christoph) and
* bi_vcnt is really the only way of telling if we need to.
*/
-
- if (bio->bi_vcnt)
- goto single_segment;
-
- return 0;
- }
-
- if (bio_op(bio) == REQ_OP_WRITE_SAME) {
-single_segment:
+ if (!bio->bi_vcnt)
+ return 0;
+ /* Fall through */
+ case REQ_OP_WRITE_SAME:
*sg = sglist;
bvec = bio_iovec(bio);
sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
return 1;
+ default:
+ break;
}
for_each_bio(bio)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e931a0e..13f5a6c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -793,11 +793,12 @@
struct list_head *dptr;
int queued;
- WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
-
if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
return;
+ WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+ cpu_online(hctx->next_cpu));
+
hctx->run++;
/*
@@ -1036,10 +1037,11 @@
EXPORT_SYMBOL(blk_mq_delay_queue);
static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
- struct blk_mq_ctx *ctx,
struct request *rq,
bool at_head)
{
+ struct blk_mq_ctx *ctx = rq->mq_ctx;
+
trace_block_rq_insert(hctx->queue, rq);
if (at_head)
@@ -1053,20 +1055,16 @@
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
- __blk_mq_insert_req_list(hctx, ctx, rq, at_head);
+ __blk_mq_insert_req_list(hctx, rq, at_head);
blk_mq_hctx_mark_pending(hctx, ctx);
}
void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
- bool async)
+ bool async)
{
+ struct blk_mq_ctx *ctx = rq->mq_ctx;
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
-
- current_ctx = blk_mq_get_ctx(q);
- if (!cpu_online(ctx->cpu))
- rq->mq_ctx = ctx = current_ctx;
hctx = q->mq_ops->map_queue(q, ctx->cpu);
@@ -1076,8 +1074,6 @@
if (run_queue)
blk_mq_run_hw_queue(hctx, async);
-
- blk_mq_put_ctx(current_ctx);
}
static void blk_mq_insert_requests(struct request_queue *q,
@@ -1088,14 +1084,9 @@
{
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *current_ctx;
trace_block_unplug(q, depth, !from_schedule);
- current_ctx = blk_mq_get_ctx(q);
-
- if (!cpu_online(ctx->cpu))
- ctx = current_ctx;
hctx = q->mq_ops->map_queue(q, ctx->cpu);
/*
@@ -1107,15 +1098,14 @@
struct request *rq;
rq = list_first_entry(list, struct request, queuelist);
+ BUG_ON(rq->mq_ctx != ctx);
list_del_init(&rq->queuelist);
- rq->mq_ctx = ctx;
- __blk_mq_insert_req_list(hctx, ctx, rq, false);
+ __blk_mq_insert_req_list(hctx, rq, false);
}
blk_mq_hctx_mark_pending(hctx, ctx);
spin_unlock(&ctx->lock);
blk_mq_run_hw_queue(hctx, from_schedule);
- blk_mq_put_ctx(current_ctx);
}
static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1630,16 +1620,17 @@
return 0;
}
+/*
+ * 'cpu' is going away. splice any existing rq_list entries from this
+ * software queue to the hw queue dispatch list, and ensure that it
+ * gets run.
+ */
static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
{
- struct request_queue *q = hctx->queue;
struct blk_mq_ctx *ctx;
LIST_HEAD(tmp);
- /*
- * Move ctx entries to new CPU, if this one is going away.
- */
- ctx = __blk_mq_get_ctx(q, cpu);
+ ctx = __blk_mq_get_ctx(hctx->queue, cpu);
spin_lock(&ctx->lock);
if (!list_empty(&ctx->rq_list)) {
@@ -1651,24 +1642,11 @@
if (list_empty(&tmp))
return NOTIFY_OK;
- ctx = blk_mq_get_ctx(q);
- spin_lock(&ctx->lock);
-
- while (!list_empty(&tmp)) {
- struct request *rq;
-
- rq = list_first_entry(&tmp, struct request, queuelist);
- rq->mq_ctx = ctx;
- list_move_tail(&rq->queuelist, &ctx->rq_list);
- }
-
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
- blk_mq_hctx_mark_pending(hctx, ctx);
-
- spin_unlock(&ctx->lock);
+ spin_lock(&hctx->lock);
+ list_splice_tail_init(&tmp, &hctx->dispatch);
+ spin_unlock(&hctx->lock);
blk_mq_run_hw_queue(hctx, true);
- blk_mq_put_ctx(ctx);
return NOTIFY_OK;
}
diff --git a/block/elevator.c b/block/elevator.c
index 7096c22..f7d973a 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -366,7 +366,7 @@
list_for_each_prev(entry, &q->queue_head) {
struct request *pos = list_entry_rq(entry);
- if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
+ if (req_op(rq) != req_op(pos))
break;
if (rq_data_dir(rq) != rq_data_dir(pos))
break;
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 7461a58..dcf2c72 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -2524,7 +2524,7 @@
/* Do not receive interrupts sent by dummy ports */
if (!pp) {
- disable_irq(irq + i);
+ disable_irq(irq);
continue;
}
diff --git a/drivers/ata/pata_ninja32.c b/drivers/ata/pata_ninja32.c
index 633aa29..44f97ad 100644
--- a/drivers/ata/pata_ninja32.c
+++ b/drivers/ata/pata_ninja32.c
@@ -144,7 +144,7 @@
ap->ioaddr.altstatus_addr = base + 0x1E;
ap->ioaddr.bmdma_addr = base;
ata_sff_std_ports(&ap->ioaddr);
- ap->pflags = ATA_PFLAG_PIO32 | ATA_PFLAG_PIO32CHANGE;
+ ap->pflags |= ATA_PFLAG_PIO32 | ATA_PFLAG_PIO32CHANGE;
ninja32_program(base);
/* FIXME: Should we disable them at remove ? */
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index b71a9c7..e3d8e4c 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3706,22 +3706,21 @@
if (UFDCS->rawcmd == 1)
UFDCS->rawcmd = 2;
- if (mode & (FMODE_READ|FMODE_WRITE)) {
- UDRS->last_checked = 0;
- clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
- check_disk_change(bdev);
- if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
- goto out;
- if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+ if (!(mode & FMODE_NDELAY)) {
+ if (mode & (FMODE_READ|FMODE_WRITE)) {
+ UDRS->last_checked = 0;
+ clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+ check_disk_change(bdev);
+ if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+ goto out;
+ if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+ goto out;
+ }
+ res = -EROFS;
+ if ((mode & FMODE_WRITE) &&
+ !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
goto out;
}
-
- res = -EROFS;
-
- if ((mode & FMODE_WRITE) &&
- !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
- goto out;
-
mutex_unlock(&open_lock);
mutex_unlock(&floppy_mutex);
return 0;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index be4fea6..88ef6d4 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -189,6 +189,8 @@
struct mutex mutex;
struct xenbus_device *xbdev;
struct gendisk *gd;
+ u16 sector_size;
+ unsigned int physical_sector_size;
int vdevice;
blkif_vdev_t handle;
enum blkif_state connected;
@@ -910,9 +912,45 @@
.map_queue = blk_mq_map_queue,
};
+static void blkif_set_queue_limits(struct blkfront_info *info)
+{
+ struct request_queue *rq = info->rq;
+ struct gendisk *gd = info->gd;
+ unsigned int segments = info->max_indirect_segments ? :
+ BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+ queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+
+ if (info->feature_discard) {
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
+ blk_queue_max_discard_sectors(rq, get_capacity(gd));
+ rq->limits.discard_granularity = info->discard_granularity;
+ rq->limits.discard_alignment = info->discard_alignment;
+ if (info->feature_secdiscard)
+ queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
+ }
+
+ /* Hard sector size and max sectors impersonate the equiv. hardware. */
+ blk_queue_logical_block_size(rq, info->sector_size);
+ blk_queue_physical_block_size(rq, info->physical_sector_size);
+ blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+
+ /* Each segment in a request is up to an aligned page in size. */
+ blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
+ blk_queue_max_segment_size(rq, PAGE_SIZE);
+
+ /* Ensure a merged request will fit in a single I/O ring slot. */
+ blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+
+ /* Make sure buffer addresses are sector-aligned. */
+ blk_queue_dma_alignment(rq, 511);
+
+ /* Make sure we don't use bounce buffers. */
+ blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
+}
+
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
- unsigned int physical_sector_size,
- unsigned int segments)
+ unsigned int physical_sector_size)
{
struct request_queue *rq;
struct blkfront_info *info = gd->private_data;
@@ -944,36 +982,11 @@
}
rq->queuedata = info;
- queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
-
- if (info->feature_discard) {
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
- blk_queue_max_discard_sectors(rq, get_capacity(gd));
- rq->limits.discard_granularity = info->discard_granularity;
- rq->limits.discard_alignment = info->discard_alignment;
- if (info->feature_secdiscard)
- queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
- }
-
- /* Hard sector size and max sectors impersonate the equiv. hardware. */
- blk_queue_logical_block_size(rq, sector_size);
- blk_queue_physical_block_size(rq, physical_sector_size);
- blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
-
- /* Each segment in a request is up to an aligned page in size. */
- blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
- blk_queue_max_segment_size(rq, PAGE_SIZE);
-
- /* Ensure a merged request will fit in a single I/O ring slot. */
- blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
-
- /* Make sure buffer addresses are sector-aligned. */
- blk_queue_dma_alignment(rq, 511);
-
- /* Make sure we don't use bounce buffers. */
- blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
-
- gd->queue = rq;
+ info->rq = gd->queue = rq;
+ info->gd = gd;
+ info->sector_size = sector_size;
+ info->physical_sector_size = physical_sector_size;
+ blkif_set_queue_limits(info);
return 0;
}
@@ -1136,16 +1149,11 @@
gd->private_data = info;
set_capacity(gd, capacity);
- if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
- info->max_indirect_segments ? :
- BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
+ if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) {
del_gendisk(gd);
goto release;
}
- info->rq = gd->queue;
- info->gd = gd;
-
xlvbd_flush(info);
if (vdisk_info & VDISK_READONLY)
@@ -1315,7 +1323,7 @@
rinfo->ring_ref[i] = GRANT_INVALID_REF;
}
}
- free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE));
+ free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
rinfo->ring.sring = NULL;
if (rinfo->irq)
@@ -2007,8 +2015,10 @@
struct split_bio *split_bio;
blkfront_gather_backend_features(info);
+ /* Reset limits changed by blk_mq_update_nr_hw_queues(). */
+ blkif_set_queue_limits(info);
segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
- blk_queue_max_segments(info->rq, segs);
+ blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
for (r_index = 0; r_index < info->nr_rings; r_index++) {
struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
@@ -2432,7 +2442,7 @@
if (err) {
xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
info->xbdev->otherend);
- return;
+ goto fail;
}
xenbus_switch_state(info->xbdev, XenbusStateConnected);
@@ -2445,6 +2455,11 @@
device_add_disk(&info->xbdev->dev, info->gd);
info->is_ready = 1;
+ return;
+
+fail:
+ blkif_free(info, 0);
+ return;
}
/**
diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c
index 937e10b..3e1cb51 100644
--- a/drivers/clocksource/pxa_timer.c
+++ b/drivers/clocksource/pxa_timer.c
@@ -21,6 +21,8 @@
#include <linux/of_irq.h>
#include <linux/sched_clock.h>
+#include <clocksource/pxa.h>
+
#include <asm/div64.h>
#define OSMR0 0x00 /* OS Timer 0 Match Register */
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index 97669ee..c83452c 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -123,12 +123,16 @@
.set_next_event = sun4i_clkevt_next_event,
};
+static void sun4i_timer_clear_interrupt(void)
+{
+ writel(TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_ST_REG);
+}
static irqreturn_t sun4i_timer_interrupt(int irq, void *dev_id)
{
struct clock_event_device *evt = (struct clock_event_device *)dev_id;
- writel(0x1, timer_base + TIMER_IRQ_ST_REG);
+ sun4i_timer_clear_interrupt();
evt->event_handler(evt);
return IRQ_HANDLED;
@@ -208,6 +212,9 @@
/* Make sure timer is stopped before playing with interrupts */
sun4i_clkevt_time_stop(0);
+ /* clear timer0 interrupt */
+ sun4i_timer_clear_interrupt();
+
sun4i_clockevent.cpumask = cpu_possible_mask;
sun4i_clockevent.irq = irq;
diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c
index a7d9a08..a8e6c7d 100644
--- a/drivers/clocksource/time-pistachio.c
+++ b/drivers/clocksource/time-pistachio.c
@@ -202,10 +202,10 @@
rate = clk_get_rate(fast_clk);
/* Disable irq's for clocksource usage */
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 0);
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 1);
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 2);
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 3);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 0);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 1);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 2);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 3);
/* Enable timer block */
writel(TIMER_ME_GLOBAL, pcs_gpt.base);
diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
index 1ffac0c..3494bc5 100644
--- a/drivers/clocksource/timer-atmel-pit.c
+++ b/drivers/clocksource/timer-atmel-pit.c
@@ -261,6 +261,12 @@
return PTR_ERR(data->mck);
}
+ ret = clk_prepare_enable(data->mck);
+ if (ret) {
+ pr_err("Unable to enable mck\n");
+ return ret;
+ }
+
/* Get the interrupts property */
data->irq = irq_of_parse_and_map(node, 0);
if (!data->irq) {
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index dfb1685..1f01e98 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -116,6 +116,9 @@
if (rc)
return rc;
+ /* adjust the dax_region resource to the start of data */
+ res.start += le64_to_cpu(pfn_sb->dataoff);
+
nd_region = to_nd_region(dev->parent);
dax_region = alloc_dax_region(dev, nd_region->id, &res,
le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 8c704c8..700c56b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -426,6 +426,8 @@
/* custom LRU management */
struct amdgpu_mman_lru log2_size[AMDGPU_TTM_LRU_SIZE];
+ /* guard for log2_size array, don't add anything in between */
+ struct amdgpu_mman_lru guard;
};
int amdgpu_copy_buffer(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 9831753..fe872b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -321,6 +321,19 @@
(le16_to_cpu(path->usConnObjectId) &
OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
+ /* Skip TV/CV support */
+ if ((le16_to_cpu(path->usDeviceTag) ==
+ ATOM_DEVICE_TV1_SUPPORT) ||
+ (le16_to_cpu(path->usDeviceTag) ==
+ ATOM_DEVICE_CV_SUPPORT))
+ continue;
+
+ if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) {
+ DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n",
+ con_obj_id, le16_to_cpu(path->usDeviceTag));
+ continue;
+ }
+
connector_type =
object_connector_convert[con_obj_id];
connector_object_id = con_obj_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9b61c8b..716f2af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -251,8 +251,8 @@
adev = amdgpu_get_adev(bo->bdev);
ring = adev->mman.buffer_funcs_ring;
- old_start = old_mem->start << PAGE_SHIFT;
- new_start = new_mem->start << PAGE_SHIFT;
+ old_start = (u64)old_mem->start << PAGE_SHIFT;
+ new_start = (u64)new_mem->start << PAGE_SHIFT;
switch (old_mem->mem_type) {
case TTM_PL_VRAM:
@@ -950,6 +950,8 @@
struct list_head *res = lru->lru[tbo->mem.mem_type];
lru->lru[tbo->mem.mem_type] = &tbo->lru;
+ while ((++lru)->lru[tbo->mem.mem_type] == res)
+ lru->lru[tbo->mem.mem_type] = &tbo->lru;
return res;
}
@@ -960,6 +962,8 @@
struct list_head *res = lru->swap_lru;
lru->swap_lru = &tbo->swap;
+ while ((++lru)->swap_lru == res)
+ lru->swap_lru = &tbo->swap;
return res;
}
@@ -1011,6 +1015,10 @@
lru->swap_lru = &adev->mman.bdev.glob->swap_lru;
}
+ for (j = 0; j < TTM_NUM_MEM_TYPES; ++j)
+ adev->mman.guard.lru[j] = NULL;
+ adev->mman.guard.swap_lru = NULL;
+
adev->mman.initialized = true;
r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_VRAM,
adev->mc.real_vram_size >> PAGE_SHIFT);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 1351c7e..a64715d 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -714,7 +714,7 @@
DRM_ERROR("amdgpu: IB test timed out\n");
r = -ETIMEDOUT;
goto err1;
- } else if (r) {
+ } else if (r < 0) {
DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
goto err1;
}
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index ef312bb..963a24d 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -405,7 +405,7 @@
spin_lock(&sched->job_list_lock);
s_job = list_first_entry_or_null(&sched->ring_mirror_list,
struct amd_sched_job, node);
- if (s_job)
+ if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT)
schedule_delayed_work(&s_job->work_tdr, sched->timeout);
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index fa39307..2a3ded4 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -475,7 +475,7 @@
val,
-1,
&replaced);
- state->color_mgmt_changed = replaced;
+ state->color_mgmt_changed |= replaced;
return ret;
} else if (property == config->ctm_property) {
ret = drm_atomic_replace_property_blob_from_id(crtc,
@@ -483,7 +483,7 @@
val,
sizeof(struct drm_color_ctm),
&replaced);
- state->color_mgmt_changed = replaced;
+ state->color_mgmt_changed |= replaced;
return ret;
} else if (property == config->gamma_lut_property) {
ret = drm_atomic_replace_property_blob_from_id(crtc,
@@ -491,7 +491,7 @@
val,
-1,
&replaced);
- state->color_mgmt_changed = replaced;
+ state->color_mgmt_changed |= replaced;
return ret;
} else if (crtc->funcs->atomic_set_property)
return crtc->funcs->atomic_set_property(crtc, state, property, val);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index b1dbb60..ddebe54 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -5404,6 +5404,9 @@
struct drm_pending_vblank_event *e = NULL;
int ret = -EINVAL;
+ if (!drm_core_check_feature(dev, DRIVER_MODESET))
+ return -EINVAL;
+
if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS ||
page_flip->reserved != 0)
return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 20fe9d5..f68c789 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -882,11 +882,12 @@
struct i915_ctx_hang_stats hang_stats;
- /* Unique identifier for this context, used by the hw for tracking */
unsigned long flags;
#define CONTEXT_NO_ZEROMAP BIT(0)
#define CONTEXT_NO_ERROR_CAPTURE BIT(1)
- unsigned hw_id;
+
+ /* Unique identifier for this context, used by the hw for tracking */
+ unsigned int hw_id;
u32 user_handle;
u32 ggtt_alignment;
@@ -1963,6 +1964,13 @@
struct i915_suspend_saved_registers regfile;
struct vlv_s0ix_state vlv_s0ix_state;
+ enum {
+ I915_SKL_SAGV_UNKNOWN = 0,
+ I915_SKL_SAGV_DISABLED,
+ I915_SKL_SAGV_ENABLED,
+ I915_SKL_SAGV_NOT_CONTROLLED
+ } skl_sagv_status;
+
struct {
/*
* Raw watermark latency values:
@@ -3591,6 +3599,7 @@
/* belongs in i915_gem_gtt.h */
static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv)
{
+ wmb();
if (INTEL_GEN(dev_priv) < 6)
intel_gtt_chipset_flush();
}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 1978633..b35e5b6 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -943,8 +943,6 @@
{
const unsigned other_rings = ~intel_engine_flag(req->engine);
struct i915_vma *vma;
- uint32_t flush_domains = 0;
- bool flush_chipset = false;
int ret;
list_for_each_entry(vma, vmas, exec_list) {
@@ -957,16 +955,11 @@
}
if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
- flush_chipset |= i915_gem_clflush_object(obj, false);
-
- flush_domains |= obj->base.write_domain;
+ i915_gem_clflush_object(obj, false);
}
- if (flush_chipset)
- i915_gem_chipset_flush(req->engine->i915);
-
- if (flush_domains & I915_GEM_DOMAIN_GTT)
- wmb();
+ /* Unconditionally flush any chipset caches (for streaming writes). */
+ i915_gem_chipset_flush(req->engine->i915);
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5c06413..bf2cad3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7145,6 +7145,15 @@
#define GEN6_PCODE_MAILBOX _MMIO(0x138124)
#define GEN6_PCODE_READY (1<<31)
+#define GEN6_PCODE_ERROR_MASK 0xFF
+#define GEN6_PCODE_SUCCESS 0x0
+#define GEN6_PCODE_ILLEGAL_CMD 0x1
+#define GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x2
+#define GEN6_PCODE_TIMEOUT 0x3
+#define GEN6_PCODE_UNIMPLEMENTED_CMD 0xFF
+#define GEN7_PCODE_TIMEOUT 0x2
+#define GEN7_PCODE_ILLEGAL_DATA 0x3
+#define GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10
#define GEN6_PCODE_WRITE_RC6VIDS 0x4
#define GEN6_PCODE_READ_RC6VIDS 0x5
#define GEN6_ENCODE_RC6_VID(mv) (((mv) - 245) / 5)
@@ -7166,6 +7175,10 @@
#define HSW_PCODE_DE_WRITE_FREQ_REQ 0x17
#define DISPLAY_IPS_CONTROL 0x19
#define HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL 0x1A
+#define GEN9_PCODE_SAGV_CONTROL 0x21
+#define GEN9_SAGV_DISABLE 0x0
+#define GEN9_SAGV_IS_DISABLED 0x1
+#define GEN9_SAGV_ENABLE 0x3
#define GEN6_PCODE_DATA _MMIO(0x138128)
#define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8
#define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 3edb958..c3b33a1 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -41,15 +41,15 @@
* be moved to FW_FAILED.
*/
-#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin"
+#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin"
MODULE_FIRMWARE(I915_CSR_KBL);
#define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1)
-#define I915_CSR_SKL "i915/skl_dmc_ver1.bin"
+#define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin"
MODULE_FIRMWARE(I915_CSR_SKL);
-#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23)
+#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 26)
-#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin"
+#define I915_CSR_BXT "i915/bxt_dmc_ver1_07.bin"
MODULE_FIRMWARE(I915_CSR_BXT);
#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2a751b6..175595f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13759,6 +13759,13 @@
intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco))
dev_priv->display.modeset_commit_cdclk(state);
+ /*
+ * SKL workaround: bspec recommends we disable the SAGV when we
+ * have more then one pipe enabled
+ */
+ if (IS_SKYLAKE(dev_priv) && !skl_can_enable_sagv(state))
+ skl_disable_sagv(dev_priv);
+
intel_modeset_verify_disabled(dev);
}
@@ -13832,6 +13839,10 @@
intel_modeset_verify_crtc(crtc, old_crtc_state, crtc->state);
}
+ if (IS_SKYLAKE(dev_priv) && intel_state->modeset &&
+ skl_can_enable_sagv(state))
+ skl_enable_sagv(dev_priv);
+
drm_atomic_helper_commit_hw_done(state);
if (intel_state->modeset)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index cc937a1..ff399b9 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1716,6 +1716,9 @@
void skl_wm_get_hw_state(struct drm_device *dev);
void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
struct skl_ddb_allocation *ddb /* out */);
+bool skl_can_enable_sagv(struct drm_atomic_state *state);
+int skl_enable_sagv(struct drm_i915_private *dev_priv);
+int skl_disable_sagv(struct drm_i915_private *dev_priv);
uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config);
bool ilk_disable_lp_wm(struct drm_device *dev);
int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d5deb58..53e13c1 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2852,6 +2852,7 @@
#define SKL_DDB_SIZE 896 /* in blocks */
#define BXT_DDB_SIZE 512
+#define SKL_SAGV_BLOCK_TIME 30 /* µs */
/*
* Return the index of a plane in the SKL DDB and wm result arrays. Primary
@@ -2875,6 +2876,153 @@
}
}
+/*
+ * SAGV dynamically adjusts the system agent voltage and clock frequencies
+ * depending on power and performance requirements. The display engine access
+ * to system memory is blocked during the adjustment time. Because of the
+ * blocking time, having this enabled can cause full system hangs and/or pipe
+ * underruns if we don't meet all of the following requirements:
+ *
+ * - <= 1 pipe enabled
+ * - All planes can enable watermarks for latencies >= SAGV engine block time
+ * - We're not using an interlaced display configuration
+ */
+int
+skl_enable_sagv(struct drm_i915_private *dev_priv)
+{
+ int ret;
+
+ if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
+ dev_priv->skl_sagv_status == I915_SKL_SAGV_ENABLED)
+ return 0;
+
+ DRM_DEBUG_KMS("Enabling the SAGV\n");
+ mutex_lock(&dev_priv->rps.hw_lock);
+
+ ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+ GEN9_SAGV_ENABLE);
+
+ /* We don't need to wait for the SAGV when enabling */
+ mutex_unlock(&dev_priv->rps.hw_lock);
+
+ /*
+ * Some skl systems, pre-release machines in particular,
+ * don't actually have an SAGV.
+ */
+ if (ret == -ENXIO) {
+ DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+ return 0;
+ } else if (ret < 0) {
+ DRM_ERROR("Failed to enable the SAGV\n");
+ return ret;
+ }
+
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_ENABLED;
+ return 0;
+}
+
+static int
+skl_do_sagv_disable(struct drm_i915_private *dev_priv)
+{
+ int ret;
+ uint32_t temp = GEN9_SAGV_DISABLE;
+
+ ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+ &temp);
+ if (ret)
+ return ret;
+ else
+ return temp & GEN9_SAGV_IS_DISABLED;
+}
+
+int
+skl_disable_sagv(struct drm_i915_private *dev_priv)
+{
+ int ret, result;
+
+ if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
+ dev_priv->skl_sagv_status == I915_SKL_SAGV_DISABLED)
+ return 0;
+
+ DRM_DEBUG_KMS("Disabling the SAGV\n");
+ mutex_lock(&dev_priv->rps.hw_lock);
+
+ /* bspec says to keep retrying for at least 1 ms */
+ ret = wait_for(result = skl_do_sagv_disable(dev_priv), 1);
+ mutex_unlock(&dev_priv->rps.hw_lock);
+
+ if (ret == -ETIMEDOUT) {
+ DRM_ERROR("Request to disable SAGV timed out\n");
+ return -ETIMEDOUT;
+ }
+
+ /*
+ * Some skl systems, pre-release machines in particular,
+ * don't actually have an SAGV.
+ */
+ if (result == -ENXIO) {
+ DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+ return 0;
+ } else if (result < 0) {
+ DRM_ERROR("Failed to disable the SAGV\n");
+ return result;
+ }
+
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_DISABLED;
+ return 0;
+}
+
+bool skl_can_enable_sagv(struct drm_atomic_state *state)
+{
+ struct drm_device *dev = state->dev;
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+ struct drm_crtc *crtc;
+ enum pipe pipe;
+ int level, plane;
+
+ /*
+ * SKL workaround: bspec recommends we disable the SAGV when we have
+ * more then one pipe enabled
+ *
+ * If there are no active CRTCs, no additional checks need be performed
+ */
+ if (hweight32(intel_state->active_crtcs) == 0)
+ return true;
+ else if (hweight32(intel_state->active_crtcs) > 1)
+ return false;
+
+ /* Since we're now guaranteed to only have one active CRTC... */
+ pipe = ffs(intel_state->active_crtcs) - 1;
+ crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+
+ if (crtc->state->mode.flags & DRM_MODE_FLAG_INTERLACE)
+ return false;
+
+ for_each_plane(dev_priv, pipe, plane) {
+ /* Skip this plane if it's not enabled */
+ if (intel_state->wm_results.plane[pipe][plane][0] == 0)
+ continue;
+
+ /* Find the highest enabled wm level for this plane */
+ for (level = ilk_wm_max_level(dev);
+ intel_state->wm_results.plane[pipe][plane][level] == 0; --level)
+ { }
+
+ /*
+ * If any of the planes on this pipe don't enable wm levels
+ * that incur memory latencies higher then 30µs we can't enable
+ * the SAGV
+ */
+ if (dev_priv->wm.skl_latency[level] < SKL_SAGV_BLOCK_TIME)
+ return false;
+ }
+
+ return true;
+}
+
static void
skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
const struct intel_crtc_state *cstate,
@@ -3107,8 +3255,6 @@
total_data_rate += intel_cstate->wm.skl.plane_y_data_rate[id];
}
- WARN_ON(cstate->plane_mask && total_data_rate == 0);
-
return total_data_rate;
}
@@ -3912,9 +4058,24 @@
* pretend that all pipes switched active status so that we'll
* ensure a full DDB recompute.
*/
- if (dev_priv->wm.distrust_bios_wm)
+ if (dev_priv->wm.distrust_bios_wm) {
+ ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
+ state->acquire_ctx);
+ if (ret)
+ return ret;
+
intel_state->active_pipe_changes = ~0;
+ /*
+ * We usually only initialize intel_state->active_crtcs if we
+ * we're doing a modeset; make sure this field is always
+ * initialized during the sanitization process that happens
+ * on the first commit too.
+ */
+ if (!intel_state->modeset)
+ intel_state->active_crtcs = dev_priv->active_crtcs;
+ }
+
/*
* If the modeset changes which CRTC's are active, we need to
* recompute the DDB allocation for *all* active pipes, even
@@ -3943,11 +4104,33 @@
ret = skl_allocate_pipe_ddb(cstate, ddb);
if (ret)
return ret;
+
+ ret = drm_atomic_add_affected_planes(state, &intel_crtc->base);
+ if (ret)
+ return ret;
}
return 0;
}
+static void
+skl_copy_wm_for_pipe(struct skl_wm_values *dst,
+ struct skl_wm_values *src,
+ enum pipe pipe)
+{
+ dst->wm_linetime[pipe] = src->wm_linetime[pipe];
+ memcpy(dst->plane[pipe], src->plane[pipe],
+ sizeof(dst->plane[pipe]));
+ memcpy(dst->plane_trans[pipe], src->plane_trans[pipe],
+ sizeof(dst->plane_trans[pipe]));
+
+ dst->ddb.pipe[pipe] = src->ddb.pipe[pipe];
+ memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe],
+ sizeof(dst->ddb.y_plane[pipe]));
+ memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
+ sizeof(dst->ddb.plane[pipe]));
+}
+
static int
skl_compute_wm(struct drm_atomic_state *state)
{
@@ -4020,8 +4203,10 @@
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = to_i915(dev);
struct skl_wm_values *results = &dev_priv->wm.skl_results;
+ struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw;
struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
+ int pipe;
if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
return;
@@ -4033,8 +4218,12 @@
skl_write_wm_values(dev_priv, results);
skl_flush_wm_values(dev_priv, results);
- /* store the new configuration */
- dev_priv->wm.skl_hw = *results;
+ /*
+ * Store the new configuration (but only for the pipes that have
+ * changed; the other values weren't recomputed).
+ */
+ for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes)
+ skl_copy_wm_for_pipe(hw_vals, results, pipe);
mutex_unlock(&dev_priv->wm.wm_mutex);
}
@@ -7658,8 +7847,53 @@
}
}
+static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv)
+{
+ uint32_t flags =
+ I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
+
+ switch (flags) {
+ case GEN6_PCODE_SUCCESS:
+ return 0;
+ case GEN6_PCODE_UNIMPLEMENTED_CMD:
+ case GEN6_PCODE_ILLEGAL_CMD:
+ return -ENXIO;
+ case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+ return -EOVERFLOW;
+ case GEN6_PCODE_TIMEOUT:
+ return -ETIMEDOUT;
+ default:
+ MISSING_CASE(flags)
+ return 0;
+ }
+}
+
+static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv)
+{
+ uint32_t flags =
+ I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
+
+ switch (flags) {
+ case GEN6_PCODE_SUCCESS:
+ return 0;
+ case GEN6_PCODE_ILLEGAL_CMD:
+ return -ENXIO;
+ case GEN7_PCODE_TIMEOUT:
+ return -ETIMEDOUT;
+ case GEN7_PCODE_ILLEGAL_DATA:
+ return -EINVAL;
+ case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+ return -EOVERFLOW;
+ default:
+ MISSING_CASE(flags);
+ return 0;
+ }
+}
+
int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val)
{
+ int status;
+
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
/* GEN6_PCODE_* are outside of the forcewake domain, we can
@@ -7686,12 +7920,25 @@
*val = I915_READ_FW(GEN6_PCODE_DATA);
I915_WRITE_FW(GEN6_PCODE_DATA, 0);
+ if (INTEL_GEN(dev_priv) > 6)
+ status = gen7_check_mailbox_status(dev_priv);
+ else
+ status = gen6_check_mailbox_status(dev_priv);
+
+ if (status) {
+ DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed: %d\n",
+ status);
+ return status;
+ }
+
return 0;
}
int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
- u32 mbox, u32 val)
+ u32 mbox, u32 val)
{
+ int status;
+
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
/* GEN6_PCODE_* are outside of the forcewake domain, we can
@@ -7716,6 +7963,17 @@
I915_WRITE_FW(GEN6_PCODE_DATA, 0);
+ if (INTEL_GEN(dev_priv) > 6)
+ status = gen7_check_mailbox_status(dev_priv);
+ else
+ status = gen6_check_mailbox_status(dev_priv);
+
+ if (status) {
+ DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed: %d\n",
+ status);
+ return status;
+ }
+
return 0;
}
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index df26570..28c1423 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -73,10 +73,12 @@
}
}
+#ifdef CONFIG_DRM_FBDEV_EMULATION
static struct fb_deferred_io qxl_defio = {
.delay = QXL_DIRTY_DELAY,
.deferred_io = drm_fb_helper_deferred_io,
};
+#endif
static struct fb_ops qxlfb_ops = {
.owner = THIS_MODULE,
@@ -313,8 +315,10 @@
goto out_destroy_fbi;
}
+#ifdef CONFIG_DRM_FBDEV_EMULATION
info->fbdefio = &qxl_defio;
fb_deferred_io_init(info);
+#endif
qdev->fbdev_info = info;
qdev->fbdev_qfb = &qfbdev->qfb;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index a97abc8..1dcf390 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -627,7 +627,9 @@
if (radeon_crtc->ss.refdiv) {
radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv;
- if (rdev->family >= CHIP_RV770)
+ if (ASIC_IS_AVIVO(rdev) &&
+ rdev->family != CHIP_RS780 &&
+ rdev->family != CHIP_RS880)
radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
}
}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 0c00e19..c2e0a1c 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -263,8 +263,8 @@
rdev = radeon_get_rdev(bo->bdev);
ridx = radeon_copy_ring_index(rdev);
- old_start = old_mem->start << PAGE_SHIFT;
- new_start = new_mem->start << PAGE_SHIFT;
+ old_start = (u64)old_mem->start << PAGE_SHIFT;
+ new_start = (u64)new_mem->start << PAGE_SHIFT;
switch (old_mem->mem_type) {
case TTM_PL_VRAM:
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 3d228ad..3dea121 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -840,6 +840,21 @@
.destroy = tegra_output_encoder_destroy,
};
+static void tegra_dsi_unprepare(struct tegra_dsi *dsi)
+{
+ int err;
+
+ if (dsi->slave)
+ tegra_dsi_unprepare(dsi->slave);
+
+ err = tegra_mipi_disable(dsi->mipi);
+ if (err < 0)
+ dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n",
+ err);
+
+ pm_runtime_put(dsi->dev);
+}
+
static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
{
struct tegra_output *output = encoder_to_output(encoder);
@@ -876,7 +891,26 @@
tegra_dsi_disable(dsi);
- pm_runtime_put(dsi->dev);
+ tegra_dsi_unprepare(dsi);
+}
+
+static void tegra_dsi_prepare(struct tegra_dsi *dsi)
+{
+ int err;
+
+ pm_runtime_get_sync(dsi->dev);
+
+ err = tegra_mipi_enable(dsi->mipi);
+ if (err < 0)
+ dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n",
+ err);
+
+ err = tegra_dsi_pad_calibrate(dsi);
+ if (err < 0)
+ dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+
+ if (dsi->slave)
+ tegra_dsi_prepare(dsi->slave);
}
static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
@@ -887,13 +921,8 @@
struct tegra_dsi *dsi = to_dsi(output);
struct tegra_dsi_state *state;
u32 value;
- int err;
- pm_runtime_get_sync(dsi->dev);
-
- err = tegra_dsi_pad_calibrate(dsi);
- if (err < 0)
- dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+ tegra_dsi_prepare(dsi);
state = tegra_dsi_get_state(dsi);
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index d5df555..9688bfa 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -203,6 +203,7 @@
ufbdev->fb_count++;
+#ifdef CONFIG_DRM_FBDEV_EMULATION
if (fb_defio && (info->fbdefio == NULL)) {
/* enable defio at last moment if not disabled by client */
@@ -218,6 +219,7 @@
info->fbdefio = fbdefio;
fb_deferred_io_init(info);
}
+#endif
pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n",
info->node, user, info, ufbdev->fb_count);
@@ -235,12 +237,14 @@
ufbdev->fb_count--;
+#ifdef CONFIG_DRM_FBDEV_EMULATION
if ((ufbdev->fb_count == 0) && (info->fbdefio)) {
fb_deferred_io_cleanup(info);
kfree(info->fbdefio);
info->fbdefio = NULL;
info->fbops->fb_mmap = udl_fb_mmap;
}
+#endif
pr_warn("released /dev/fb%d user=%d count=%d\n",
info->node, user, ufbdev->fb_count);
diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c
index 52a6fd2..e00809d 100644
--- a/drivers/gpu/host1x/mipi.c
+++ b/drivers/gpu/host1x/mipi.c
@@ -242,20 +242,6 @@
dev->pads = args.args[0];
dev->device = device;
- mutex_lock(&dev->mipi->lock);
-
- if (dev->mipi->usage_count++ == 0) {
- err = tegra_mipi_power_up(dev->mipi);
- if (err < 0) {
- dev_err(dev->mipi->dev,
- "failed to power up MIPI bricks: %d\n",
- err);
- return ERR_PTR(err);
- }
- }
-
- mutex_unlock(&dev->mipi->lock);
-
return dev;
put:
@@ -270,30 +256,43 @@
void tegra_mipi_free(struct tegra_mipi_device *device)
{
- int err;
-
- mutex_lock(&device->mipi->lock);
-
- if (--device->mipi->usage_count == 0) {
- err = tegra_mipi_power_down(device->mipi);
- if (err < 0) {
- /*
- * Not much that can be done here, so an error message
- * will have to do.
- */
- dev_err(device->mipi->dev,
- "failed to power down MIPI bricks: %d\n",
- err);
- }
- }
-
- mutex_unlock(&device->mipi->lock);
-
platform_device_put(device->pdev);
kfree(device);
}
EXPORT_SYMBOL(tegra_mipi_free);
+int tegra_mipi_enable(struct tegra_mipi_device *dev)
+{
+ int err = 0;
+
+ mutex_lock(&dev->mipi->lock);
+
+ if (dev->mipi->usage_count++ == 0)
+ err = tegra_mipi_power_up(dev->mipi);
+
+ mutex_unlock(&dev->mipi->lock);
+
+ return err;
+
+}
+EXPORT_SYMBOL(tegra_mipi_enable);
+
+int tegra_mipi_disable(struct tegra_mipi_device *dev)
+{
+ int err = 0;
+
+ mutex_lock(&dev->mipi->lock);
+
+ if (--dev->mipi->usage_count == 0)
+ err = tegra_mipi_power_down(dev->mipi);
+
+ mutex_unlock(&dev->mipi->lock);
+
+ return err;
+
+}
+EXPORT_SYMBOL(tegra_mipi_disable);
+
static int tegra_mipi_wait(struct tegra_mipi *mipi)
{
unsigned long timeout = jiffies + msecs_to_jiffies(250);
diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index d0203a1..4667012 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -2015,6 +2015,7 @@
&sensor_dev_attr_in10_input.dev_attr.attr, /* 41 */
&sensor_dev_attr_in11_input.dev_attr.attr, /* 41 */
&sensor_dev_attr_in12_input.dev_attr.attr, /* 41 */
+ NULL
};
static const struct attribute_group it87_group_in = {
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index e6dfa1b..5f65a78 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2462,18 +2462,24 @@
if (addr->dev_addr.bound_dev_if) {
ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if);
- if (!ndev)
- return -ENODEV;
+ if (!ndev) {
+ ret = -ENODEV;
+ goto err2;
+ }
if (ndev->flags & IFF_LOOPBACK) {
dev_put(ndev);
- if (!id_priv->id.device->get_netdev)
- return -EOPNOTSUPP;
+ if (!id_priv->id.device->get_netdev) {
+ ret = -EOPNOTSUPP;
+ goto err2;
+ }
ndev = id_priv->id.device->get_netdev(id_priv->id.device,
id_priv->id.port_num);
- if (!ndev)
- return -ENODEV;
+ if (!ndev) {
+ ret = -ENODEV;
+ goto err2;
+ }
}
route->path_rec->net = &init_net;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 3aca7f6..b6a953a 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1827,8 +1827,12 @@
(ep->mpa_pkt + sizeof(*mpa));
ep->ird = ntohs(mpa_v2_params->ird) &
MPA_V2_IRD_ORD_MASK;
+ ep->ird = min_t(u32, ep->ird,
+ cur_max_read_depth(ep->com.dev));
ep->ord = ntohs(mpa_v2_params->ord) &
MPA_V2_IRD_ORD_MASK;
+ ep->ord = min_t(u32, ep->ord,
+ cur_max_read_depth(ep->com.dev));
PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird,
ep->ord);
if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL)
@@ -3136,7 +3140,7 @@
if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) {
if (conn_param->ord > ep->ird) {
if (RELAXED_IRD_NEGOTIATION) {
- ep->ord = ep->ird;
+ conn_param->ord = ep->ird;
} else {
ep->ird = conn_param->ird;
ep->ord = conn_param->ord;
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 812ab72..ac926c9 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -1016,15 +1016,15 @@
int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
{
struct c4iw_cq *chp;
- int ret;
+ int ret = 0;
unsigned long flag;
chp = to_c4iw_cq(ibcq);
spin_lock_irqsave(&chp->lock, flag);
- ret = t4_arm_cq(&chp->cq,
- (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED);
+ t4_arm_cq(&chp->cq,
+ (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED);
+ if (flags & IB_CQ_REPORT_MISSED_EVENTS)
+ ret = t4_cq_notempty(&chp->cq);
spin_unlock_irqrestore(&chp->lock, flag);
- if (ret && !(flags & IB_CQ_REPORT_MISSED_EVENTS))
- ret = 0;
return ret;
}
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 6126bbe..02173f4 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -634,6 +634,11 @@
return (CQE_GENBIT(cqe) == cq->gen);
}
+static inline int t4_cq_notempty(struct t4_cq *cq)
+{
+ return cq->sw_in_use || t4_valid_cqe(cq, &cq->queue[cq->cidx]);
+}
+
static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe)
{
int ret;
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 79575ee..0566393 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -47,7 +47,6 @@
#include <linux/topology.h>
#include <linux/cpumask.h>
#include <linux/module.h>
-#include <linux/cpumask.h>
#include "hfi.h"
#include "affinity.h"
@@ -682,7 +681,7 @@
size_t count)
{
struct hfi1_affinity_node *entry;
- struct cpumask mask;
+ cpumask_var_t mask;
int ret, i;
spin_lock(&node_affinity.lock);
@@ -692,19 +691,24 @@
if (!entry)
return -EINVAL;
- ret = cpulist_parse(buf, &mask);
- if (ret)
- return ret;
+ ret = zalloc_cpumask_var(&mask, GFP_KERNEL);
+ if (!ret)
+ return -ENOMEM;
- if (!cpumask_subset(&mask, cpu_online_mask) || cpumask_empty(&mask)) {
+ ret = cpulist_parse(buf, mask);
+ if (ret)
+ goto out;
+
+ if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) {
dd_dev_warn(dd, "Invalid CPU mask\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
mutex_lock(&sdma_affinity_mutex);
/* reset the SDMA interrupt affinity details */
init_cpu_mask_set(&entry->def_intr);
- cpumask_copy(&entry->def_intr.mask, &mask);
+ cpumask_copy(&entry->def_intr.mask, mask);
/*
* Reassign the affinity for each SDMA interrupt.
*/
@@ -720,8 +724,9 @@
if (ret)
break;
}
-
mutex_unlock(&sdma_affinity_mutex);
+out:
+ free_cpumask_var(mask);
return ret ? ret : strnlen(buf, PAGE_SIZE);
}
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index dbab9d9..a49cc88 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -223,28 +223,32 @@
DEBUGFS_FILE_OPS(ctx_stats);
static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
+ __acquires(RCU)
{
struct qp_iter *iter;
loff_t n = *pos;
- rcu_read_lock();
iter = qp_iter_init(s->private);
+
+ /* stop calls rcu_read_unlock */
+ rcu_read_lock();
+
if (!iter)
return NULL;
- while (n--) {
+ do {
if (qp_iter_next(iter)) {
kfree(iter);
return NULL;
}
- }
+ } while (n--);
return iter;
}
static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr,
loff_t *pos)
+ __must_hold(RCU)
{
struct qp_iter *iter = iter_ptr;
@@ -259,7 +263,7 @@
}
static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr)
-__releases(RCU)
+ __releases(RCU)
{
rcu_read_unlock();
}
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 8246dc7..303f105 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -888,14 +888,15 @@
}
static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
- struct hfi1_packet packet,
+ struct hfi1_packet *packet,
struct hfi1_devdata *dd)
{
struct work_struct *lsaw = &rcd->ppd->linkstate_active_work;
- struct hfi1_message_header *hdr = hfi1_get_msgheader(packet.rcd->dd,
- packet.rhf_addr);
+ struct hfi1_message_header *hdr = hfi1_get_msgheader(packet->rcd->dd,
+ packet->rhf_addr);
+ u8 etype = rhf_rcv_type(packet->rhf);
- if (hdr2sc(hdr, packet.rhf) != 0xf) {
+ if (etype == RHF_RCV_TYPE_IB && hdr2sc(hdr, packet->rhf) != 0xf) {
int hwstate = read_logical_state(dd);
if (hwstate != LSTATE_ACTIVE) {
@@ -979,7 +980,7 @@
/* Auto activate link on non-SC15 packet receive */
if (unlikely(rcd->ppd->host_link_state ==
HLS_UP_ARMED) &&
- set_armed_to_active(rcd, packet, dd))
+ set_armed_to_active(rcd, &packet, dd))
goto bail;
last = process_rcv_packet(&packet, thread);
}
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 1ecbec1..7e03ccd 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -183,6 +183,7 @@
if (fd) {
fd->rec_cpu_num = -1; /* no cpu affinity by default */
fd->mm = current->mm;
+ atomic_inc(&fd->mm->mm_count);
}
fp->private_data = fd;
@@ -222,7 +223,7 @@
ret = assign_ctxt(fp, &uinfo);
if (ret < 0)
return ret;
- setup_ctxt(fp);
+ ret = setup_ctxt(fp);
if (ret)
return ret;
ret = user_init(fp);
@@ -779,6 +780,7 @@
mutex_unlock(&hfi1_mutex);
hfi1_free_ctxtdata(dd, uctxt);
done:
+ mmdrop(fdata->mm);
kobject_put(&dd->kobj);
kfree(fdata);
return 0;
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 1000e0f..a021e66 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1272,9 +1272,26 @@
((!!(rhf_dc_info(rhf))) << 4);
}
+#define HFI1_JKEY_WIDTH 16
+#define HFI1_JKEY_MASK (BIT(16) - 1)
+#define HFI1_ADMIN_JKEY_RANGE 32
+
+/*
+ * J_KEYs are split and allocated in the following groups:
+ * 0 - 31 - users with administrator privileges
+ * 32 - 63 - kernel protocols using KDETH packets
+ * 64 - 65535 - all other users using KDETH packets
+ */
static inline u16 generate_jkey(kuid_t uid)
{
- return from_kuid(current_user_ns(), uid) & 0xffff;
+ u16 jkey = from_kuid(current_user_ns(), uid) & HFI1_JKEY_MASK;
+
+ if (capable(CAP_SYS_ADMIN))
+ jkey &= HFI1_ADMIN_JKEY_RANGE - 1;
+ else if (jkey < 64)
+ jkey |= BIT(HFI1_JKEY_WIDTH - 1);
+
+ return jkey;
}
/*
@@ -1656,7 +1673,6 @@
struct hfi1_devdata *hfi1_init_dd(struct pci_dev *,
const struct pci_device_id *);
void hfi1_free_devdata(struct hfi1_devdata *);
-void cc_state_reclaim(struct rcu_head *rcu);
struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra);
/* LED beaconing functions */
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index a358d23..b793545 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1333,7 +1333,7 @@
spin_unlock(&ppd->cc_state_lock);
if (cc_state)
- call_rcu(&cc_state->rcu, cc_state_reclaim);
+ kfree_rcu(cc_state, rcu);
}
free_credit_return(dd);
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 1263abe..39e42c3 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -1819,6 +1819,11 @@
u32 len = OPA_AM_CI_LEN(am) + 1;
int ret;
+ if (dd->pport->port_type != PORT_TYPE_QSFP) {
+ smp->status |= IB_SMP_INVALID_FIELD;
+ return reply((struct ib_mad_hdr *)smp);
+ }
+
#define __CI_PAGE_SIZE BIT(7) /* 128 bytes */
#define __CI_PAGE_MASK ~(__CI_PAGE_SIZE - 1)
#define __CI_PAGE_NUM(a) ((a) & __CI_PAGE_MASK)
@@ -3398,7 +3403,7 @@
spin_unlock(&ppd->cc_state_lock);
- call_rcu(&old_cc_state->rcu, cc_state_reclaim);
+ kfree_rcu(old_cc_state, rcu);
}
static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
@@ -3553,13 +3558,6 @@
return reply((struct ib_mad_hdr *)smp);
}
-void cc_state_reclaim(struct rcu_head *rcu)
-{
- struct cc_state *cc_state = container_of(rcu, struct cc_state, rcu);
-
- kfree(cc_state);
-}
-
static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
struct ib_device *ibdev, u8 port,
u32 *resp_len)
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index a5aa351..4e4d831 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -656,10 +656,6 @@
iter->dev = dev;
iter->specials = dev->rdi.ibdev.phys_port_cnt * 2;
- if (qp_iter_next(iter)) {
- kfree(iter);
- return NULL;
- }
return iter;
}
diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c
index a207717..4e95ad8 100644
--- a/drivers/infiniband/hw/hfi1/qsfp.c
+++ b/drivers/infiniband/hw/hfi1/qsfp.c
@@ -706,8 +706,8 @@
u8 *data)
{
struct hfi1_pportdata *ppd;
- u32 excess_len = 0;
- int ret = 0;
+ u32 excess_len = len;
+ int ret = 0, offset = 0;
if (port_num > dd->num_pports || port_num < 1) {
dd_dev_info(dd, "%s: Invalid port number %d\n",
@@ -740,6 +740,34 @@
}
memcpy(data, &ppd->qsfp_info.cache[addr], len);
+
+ if (addr <= QSFP_MONITOR_VAL_END &&
+ (addr + len) >= QSFP_MONITOR_VAL_START) {
+ /* Overlap with the dynamic channel monitor range */
+ if (addr < QSFP_MONITOR_VAL_START) {
+ if (addr + len <= QSFP_MONITOR_VAL_END)
+ len = addr + len - QSFP_MONITOR_VAL_START;
+ else
+ len = QSFP_MONITOR_RANGE;
+ offset = QSFP_MONITOR_VAL_START - addr;
+ addr = QSFP_MONITOR_VAL_START;
+ } else if (addr == QSFP_MONITOR_VAL_START) {
+ offset = 0;
+ if (addr + len > QSFP_MONITOR_VAL_END)
+ len = QSFP_MONITOR_RANGE;
+ } else {
+ offset = 0;
+ if (addr + len > QSFP_MONITOR_VAL_END)
+ len = QSFP_MONITOR_VAL_END - addr + 1;
+ }
+ /* Refresh the values of the dynamic monitors from the cable */
+ ret = one_qsfp_read(ppd, dd->hfi1_id, addr, data + offset, len);
+ if (ret != len) {
+ ret = -EAGAIN;
+ goto set_zeroes;
+ }
+ }
+
return 0;
set_zeroes:
diff --git a/drivers/infiniband/hw/hfi1/qsfp.h b/drivers/infiniband/hw/hfi1/qsfp.h
index 69275eb..36cf523 100644
--- a/drivers/infiniband/hw/hfi1/qsfp.h
+++ b/drivers/infiniband/hw/hfi1/qsfp.h
@@ -74,6 +74,9 @@
/* Defined fields that Intel requires of qualified cables */
/* Byte 0 is Identifier, not checked */
/* Byte 1 is reserved "status MSB" */
+#define QSFP_MONITOR_VAL_START 22
+#define QSFP_MONITOR_VAL_END 81
+#define QSFP_MONITOR_RANGE (QSFP_MONITOR_VAL_END - QSFP_MONITOR_VAL_START + 1)
#define QSFP_TX_CTRL_BYTE_OFFS 86
#define QSFP_PWR_CTRL_BYTE_OFFS 93
#define QSFP_CDR_CTRL_BYTE_OFFS 98
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index b738acd..8ec09e4 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -232,7 +232,7 @@
struct i40e_client *client;
struct i40iw_hw hw;
struct i40iw_cm_core cm_core;
- unsigned long *mem_resources;
+ u8 *mem_resources;
unsigned long *allocated_qps;
unsigned long *allocated_cqs;
unsigned long *allocated_mrs;
@@ -435,8 +435,8 @@
*next = resource_num + 1;
if (*next == max_resources)
*next = 0;
- spin_unlock_irqrestore(&iwdev->resource_lock, flags);
*req_resource_num = resource_num;
+ spin_unlock_irqrestore(&iwdev->resource_lock, flags);
return 0;
}
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 5026dc7..7ca0638 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -535,8 +535,8 @@
buf += hdr_len;
}
- if (pd_len)
- memcpy(buf, pdata->addr, pd_len);
+ if (pdata && pdata->addr)
+ memcpy(buf, pdata->addr, pdata->size);
atomic_set(&sqbuf->refcount, 1);
@@ -3347,26 +3347,6 @@
}
/**
- * i40iw_loopback_nop - Send a nop
- * @qp: associated hw qp
- */
-static void i40iw_loopback_nop(struct i40iw_sc_qp *qp)
-{
- u64 *wqe;
- u64 header;
-
- wqe = qp->qp_uk.sq_base->elem;
- set_64bit_val(wqe, 0, 0);
- set_64bit_val(wqe, 8, 0);
- set_64bit_val(wqe, 16, 0);
-
- header = LS_64(I40IWQP_OP_NOP, I40IWQPSQ_OPCODE) |
- LS_64(0, I40IWQPSQ_SIGCOMPL) |
- LS_64(qp->qp_uk.swqe_polarity, I40IWQPSQ_VALID);
- set_64bit_val(wqe, 24, header);
-}
-
-/**
* i40iw_qp_disconnect - free qp and close cm
* @iwqp: associate qp for the connection
*/
@@ -3638,7 +3618,7 @@
} else {
if (iwqp->page)
iwqp->sc_qp.qp_uk.sq_base = kmap(iwqp->page);
- i40iw_loopback_nop(&iwqp->sc_qp);
+ dev->iw_priv_qp_ops->qp_send_lsmm(&iwqp->sc_qp, NULL, 0, 0);
}
if (iwqp->page)
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index 6e90813..0cbbe40 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -1558,6 +1558,10 @@
enum i40iw_status_code status;
struct i40iw_handler *hdl;
+ hdl = i40iw_find_netdev(ldev->netdev);
+ if (hdl)
+ return 0;
+
hdl = kzalloc(sizeof(*hdl), GFP_KERNEL);
if (!hdl)
return -ENOMEM;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index 0e8db0a..6fd043b 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -673,8 +673,11 @@
{
if (!mem)
return I40IW_ERR_PARAM;
+ /*
+ * mem->va points to the parent of mem, so both mem and mem->va
+ * can not be touched once mem->va is freed
+ */
kfree(mem->va);
- mem->va = NULL;
return 0;
}
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 2360338..6329c97 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -794,7 +794,6 @@
return &iwqp->ibqp;
error:
i40iw_free_qp_resources(iwdev, iwqp, qp_num);
- kfree(mem);
return ERR_PTR(err_code);
}
@@ -1926,8 +1925,7 @@
}
if (iwpbl->pbl_allocated)
i40iw_free_pble(iwdev->pble_rsrc, palloc);
- kfree(iwpbl->iwmr);
- iwpbl->iwmr = NULL;
+ kfree(iwmr);
return 0;
}
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index d6fc8a6..006db64 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -576,8 +576,8 @@
checksum == cpu_to_be16(0xffff);
}
-static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
- unsigned tail, struct mlx4_cqe *cqe, int is_eth)
+static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
+ unsigned tail, struct mlx4_cqe *cqe, int is_eth)
{
struct mlx4_ib_proxy_sqp_hdr *hdr;
@@ -600,8 +600,6 @@
wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32);
wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
}
-
- return 0;
}
static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries,
@@ -692,7 +690,7 @@
if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP &&
is_send)) {
pr_warn("Completion for NOP opcode detected!\n");
- return -EINVAL;
+ return -EAGAIN;
}
/* Resize CQ in progress */
@@ -723,7 +721,7 @@
if (unlikely(!mqp)) {
pr_warn("CQ %06x with entry for unknown QPN %06x\n",
cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK);
- return -EINVAL;
+ return -EAGAIN;
}
*cur_qp = to_mibqp(mqp);
@@ -741,7 +739,7 @@
if (unlikely(!msrq)) {
pr_warn("CQ %06x with entry for unknown SRQN %06x\n",
cq->mcq.cqn, srq_num);
- return -EINVAL;
+ return -EAGAIN;
}
}
@@ -852,9 +850,11 @@
if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) {
if ((*cur_qp)->mlx4_ib_qp_type &
(MLX4_IB_QPT_PROXY_SMI_OWNER |
- MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
- return use_tunnel_data(*cur_qp, cq, wc, tail,
- cqe, is_eth);
+ MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) {
+ use_tunnel_data(*cur_qp, cq, wc, tail, cqe,
+ is_eth);
+ return 0;
+ }
}
wc->slid = be16_to_cpu(cqe->rlid);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index a84bb76..1b4094b 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -37,7 +37,6 @@
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
-#include <linux/io-mapping.h>
#if defined(CONFIG_X86)
#include <asm/pat.h>
#endif
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 16740dc..67fc0b6 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -1156,18 +1156,18 @@
attr->max_srq =
(rsp->max_srq_rpir_qps & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_OFFSET;
- attr->max_send_sge = ((rsp->max_write_send_sge &
+ attr->max_send_sge = ((rsp->max_recv_send_sge &
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT);
- attr->max_recv_sge = (rsp->max_write_send_sge &
- OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >>
- OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT;
+ attr->max_recv_sge = (rsp->max_recv_send_sge &
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK) >>
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT;
attr->max_srq_sge = (rsp->max_srq_rqe_sge &
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET;
- attr->max_rdma_sge = (rsp->max_write_send_sge &
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK) >>
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT;
+ attr->max_rdma_sge = (rsp->max_wr_rd_sge &
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK) >>
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT;
attr->max_ord_per_qp = (rsp->max_ird_ord_per_qp &
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
index 0efc966..37df448 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
@@ -554,9 +554,9 @@
OCRDMA_MBX_QUERY_CFG_L3_TYPE_MASK = 0x18,
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT = 0,
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK = 0xFFFF,
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT = 16,
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK = 0xFFFF <<
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT,
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT = 16,
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK = 0xFFFF <<
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT,
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT = 0,
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK = 0xFFFF,
@@ -612,6 +612,8 @@
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET = 0,
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK = 0xFFFF <<
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET,
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT = 0,
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK = 0xFFFF,
};
struct ocrdma_mbx_query_config {
@@ -619,7 +621,7 @@
struct ocrdma_mbx_rsp rsp;
u32 qp_srq_cq_ird_ord;
u32 max_pd_ca_ack_delay;
- u32 max_write_send_sge;
+ u32 max_recv_send_sge;
u32 max_ird_ord_per_qp;
u32 max_shared_ird_ord;
u32 max_mr;
@@ -639,6 +641,8 @@
u32 max_wqes_rqes_per_q;
u32 max_cq_cqes_per_cq;
u32 max_srq_rqe_sge;
+ u32 max_wr_rd_sge;
+ u32 ird_pgsz_num_pages;
};
struct ocrdma_fw_ver_rsp {
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index b1a3d91..0aa8547 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -125,8 +125,8 @@
IB_DEVICE_SYS_IMAGE_GUID |
IB_DEVICE_LOCAL_DMA_LKEY |
IB_DEVICE_MEM_MGT_EXTENSIONS;
- attr->max_sge = dev->attr.max_send_sge;
- attr->max_sge_rd = attr->max_sge;
+ attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_recv_sge);
+ attr->max_sge_rd = dev->attr.max_rdma_sge;
attr->max_cq = dev->attr.max_cq;
attr->max_cqe = dev->attr.max_cqe;
attr->max_mr = dev->attr.max_mr;
diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c
index 5e75b43..5bad8e3 100644
--- a/drivers/infiniband/hw/qib/qib_debugfs.c
+++ b/drivers/infiniband/hw/qib/qib_debugfs.c
@@ -189,27 +189,32 @@
DEBUGFS_FILE(ctx_stats)
static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
+ __acquires(RCU)
{
struct qib_qp_iter *iter;
loff_t n = *pos;
- rcu_read_lock();
iter = qib_qp_iter_init(s->private);
+
+ /* stop calls rcu_read_unlock */
+ rcu_read_lock();
+
if (!iter)
return NULL;
- while (n--) {
+ do {
if (qib_qp_iter_next(iter)) {
kfree(iter);
return NULL;
}
- }
+ } while (n--);
return iter;
}
static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr,
loff_t *pos)
+ __must_hold(RCU)
{
struct qib_qp_iter *iter = iter_ptr;
@@ -224,6 +229,7 @@
}
static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr)
+ __releases(RCU)
{
rcu_read_unlock();
}
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index fcdf3791..c3edc03 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -328,26 +328,12 @@
pos = *ppos;
- if (pos != 0) {
- ret = -EINVAL;
- goto bail;
- }
+ if (pos != 0 || count != sizeof(struct qib_flash))
+ return -EINVAL;
- if (count != sizeof(struct qib_flash)) {
- ret = -EINVAL;
- goto bail;
- }
-
- tmp = kmalloc(count, GFP_KERNEL);
- if (!tmp) {
- ret = -ENOMEM;
- goto bail;
- }
-
- if (copy_from_user(tmp, buf, count)) {
- ret = -EFAULT;
- goto bail_tmp;
- }
+ tmp = memdup_user(buf, count);
+ if (IS_ERR(tmp))
+ return PTR_ERR(tmp);
dd = private2dd(file);
if (qib_eeprom_write(dd, pos, tmp, count)) {
@@ -361,8 +347,6 @@
bail_tmp:
kfree(tmp);
-
-bail:
return ret;
}
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 9cc0aae..f9b8cd2 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -573,10 +573,6 @@
return NULL;
iter->dev = dev;
- if (qib_qp_iter_next(iter)) {
- kfree(iter);
- return NULL;
- }
return iter;
}
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index c229b9f..0a89a95 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -664,7 +664,8 @@
return err;
}
- if (pci_register_driver(&usnic_ib_pci_driver)) {
+ err = pci_register_driver(&usnic_ib_pci_driver);
+ if (err) {
usnic_err("Unable to register with PCI\n");
goto out_umem_fini;
}
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index bdb540f..870b4f2 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -873,7 +873,8 @@
free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
bail_rq_wq:
- vfree(qp->r_rq.wq);
+ if (!qp->ip)
+ vfree(qp->r_rq.wq);
bail_driver_priv:
rdi->driver_f.qp_priv_free(rdi, qp);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index ba6be06..7914c14 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -448,7 +448,7 @@
isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL);
if (!isert_conn->login_rsp_buf) {
- isert_err("Unable to allocate isert_conn->login_rspbuf\n");
+ ret = -ENOMEM;
goto out_unmap_login_req_buf;
}
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index dfa23b0..883bbfe 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -522,6 +522,11 @@
if (ret)
goto err_query_port;
+ snprintf(sport->port_guid, sizeof(sport->port_guid),
+ "0x%016llx%016llx",
+ be64_to_cpu(sport->gid.global.subnet_prefix),
+ be64_to_cpu(sport->gid.global.interface_id));
+
if (!sport->mad_agent) {
memset(®_req, 0, sizeof(reg_req));
reg_req.mgmt_class = IB_MGMT_CLASS_DEVICE_MGMT;
@@ -2548,10 +2553,6 @@
sdev->device->name, i);
goto err_ring;
}
- snprintf(sport->port_guid, sizeof(sport->port_guid),
- "0x%016llx%016llx",
- be64_to_cpu(sport->gid.global.subnet_prefix),
- be64_to_cpu(sport->gid.global.interface_id));
}
spin_lock(&srpt_dev_lock);
diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c
index 7d61439..0c07e10 100644
--- a/drivers/input/keyboard/tegra-kbc.c
+++ b/drivers/input/keyboard/tegra-kbc.c
@@ -376,7 +376,7 @@
/* Reset the KBC controller to clear all previous status.*/
reset_control_assert(kbc->rst);
udelay(100);
- reset_control_assert(kbc->rst);
+ reset_control_deassert(kbc->rst);
udelay(100);
tegra_kbc_config_pins(kbc);
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index faa295e..c83bce8 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -553,7 +553,6 @@
goto free_struct_buff;
reg = find_first_bit(rdesc->presense_map, RMI_REG_DESC_PRESENSE_BITS);
- map_offset = 0;
for (i = 0; i < rdesc->num_registers; i++) {
struct rmi_register_desc_item *item = &rdesc->registers[i];
int reg_size = struct_buf[offset];
@@ -576,6 +575,8 @@
item->reg = reg;
item->reg_size = reg_size;
+ map_offset = 0;
+
do {
for (b = 0; b < 7; b++) {
if (struct_buf[offset] & (0x1 << b))
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index b4d3408..405252a 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -1305,6 +1305,7 @@
serio->write = i8042_aux_write;
serio->start = i8042_start;
serio->stop = i8042_stop;
+ serio->ps2_cmd_mutex = &i8042_mutex;
serio->port_data = port;
serio->dev.parent = &i8042_platform_device->dev;
if (idx < 0) {
diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index a61b215..1ce3ecb 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -1473,7 +1473,6 @@
ads784x_hwmon_unregister(spi, ts);
- regulator_disable(ts->reg);
regulator_put(ts->reg);
if (!ts->get_pendown_state) {
diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c
index 7379fe1..b2744a6 100644
--- a/drivers/input/touchscreen/silead.c
+++ b/drivers/input/touchscreen/silead.c
@@ -464,7 +464,7 @@
return -ENODEV;
/* Power GPIO pin */
- data->gpio_power = gpiod_get_optional(dev, "power", GPIOD_OUT_LOW);
+ data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW);
if (IS_ERR(data->gpio_power)) {
if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER)
dev_err(dev, "Shutdown GPIO request failed\n");
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index ce80117..641e887 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -879,7 +879,7 @@
* We may have concurrent producers, so we need to be careful
* not to touch any of the shadow cmdq state.
*/
- queue_read(cmd, Q_ENT(q, idx), q->ent_dwords);
+ queue_read(cmd, Q_ENT(q, cons), q->ent_dwords);
dev_err(smmu->dev, "skipping command in error state:\n");
for (i = 0; i < ARRAY_SIZE(cmd); ++i)
dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
@@ -890,7 +890,7 @@
return;
}
- queue_write(cmd, Q_ENT(q, idx), q->ent_dwords);
+ queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
}
static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
@@ -1034,6 +1034,9 @@
case STRTAB_STE_0_CFG_S2_TRANS:
ste_live = true;
break;
+ case STRTAB_STE_0_CFG_ABORT:
+ if (disable_bypass)
+ break;
default:
BUG(); /* STE corruption */
}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 4f49fe2..2db74eb 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -686,8 +686,7 @@
static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
{
- int flags, ret;
- u32 fsr, fsynr, resume;
+ u32 fsr, fsynr;
unsigned long iova;
struct iommu_domain *domain = dev;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -701,34 +700,15 @@
if (!(fsr & FSR_FAULT))
return IRQ_NONE;
- if (fsr & FSR_IGN)
- dev_err_ratelimited(smmu->dev,
- "Unexpected context fault (fsr 0x%x)\n",
- fsr);
-
fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
- flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;
-
iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR);
- if (!report_iommu_fault(domain, smmu->dev, iova, flags)) {
- ret = IRQ_HANDLED;
- resume = RESUME_RETRY;
- } else {
- dev_err_ratelimited(smmu->dev,
- "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n",
- iova, fsynr, cfg->cbndx);
- ret = IRQ_NONE;
- resume = RESUME_TERMINATE;
- }
- /* Clear the faulting FSR */
+ dev_err_ratelimited(smmu->dev,
+ "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n",
+ fsr, iova, fsynr, cfg->cbndx);
+
writel(fsr, cb_base + ARM_SMMU_CB_FSR);
-
- /* Retry or terminate any stalled transactions */
- if (fsr & FSR_SS)
- writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME);
-
- return ret;
+ return IRQ_HANDLED;
}
static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
@@ -837,7 +817,7 @@
}
/* SCTLR */
- reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
+ reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
if (stage1)
reg |= SCTLR_S1_ASIDPNE;
#ifdef __BIG_ENDIAN
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 8c61399..def8ca1 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -286,12 +286,14 @@
int prot = IOMMU_READ;
arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl);
- if (attr & ARM_V7S_PTE_AP_RDONLY)
+ if (!(attr & ARM_V7S_PTE_AP_RDONLY))
prot |= IOMMU_WRITE;
if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
prot |= IOMMU_MMIO;
else if (pte & ARM_V7S_ATTR_C)
prot |= IOMMU_CACHE;
+ if (pte & ARM_V7S_ATTR_XN(lvl))
+ prot |= IOMMU_NOEXEC;
return prot;
}
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 7ceaba8..36b9c28 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1545,7 +1545,12 @@
u32 val;
val = readl_relaxed(base + GITS_CTLR);
- if (val & GITS_CTLR_QUIESCENT)
+ /*
+ * GIC architecture specification requires the ITS to be both
+ * disabled and quiescent for writes to GITS_BASER<n> or
+ * GITS_CBASER to not have UNPREDICTABLE results.
+ */
+ if ((val & GITS_CTLR_QUIESCENT) && !(val & GITS_CTLR_ENABLE))
return 0;
/* Disable the generation of all interrupts to this ITS */
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 6fc56c3..ede5672 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -667,13 +667,20 @@
#endif
#ifdef CONFIG_CPU_PM
+/* Check whether it's single security state view */
+static bool gic_dist_security_disabled(void)
+{
+ return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS;
+}
+
static int gic_cpu_pm_notifier(struct notifier_block *self,
unsigned long cmd, void *v)
{
if (cmd == CPU_PM_EXIT) {
- gic_enable_redist(true);
+ if (gic_dist_security_disabled())
+ gic_enable_redist(true);
gic_cpu_sys_reg_init();
- } else if (cmd == CPU_PM_ENTER) {
+ } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) {
gic_write_grpen1(0);
gic_enable_redist(false);
}
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index c2cab57..390fac5 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -769,6 +769,13 @@
int cpu;
unsigned long flags, map = 0;
+ if (unlikely(nr_cpu_ids == 1)) {
+ /* Only one CPU? let's do a self-IPI... */
+ writel_relaxed(2 << 24 | irq,
+ gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+ return;
+ }
+
raw_spin_lock_irqsave(&irq_controller_lock, flags);
/* Convert our logical CPU mask into a physical one. */
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index c5f33c3..83f4983 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -713,9 +713,6 @@
unsigned long flags;
int i;
- irq_set_chip_and_handler(virq, &gic_level_irq_controller,
- handle_level_irq);
-
spin_lock_irqsave(&gic_lock, flags);
gic_map_to_pin(intr, gic_cpu_pin);
gic_map_to_vpe(intr, mips_cm_vp_id(vpe));
@@ -732,6 +729,10 @@
{
if (GIC_HWIRQ_TO_LOCAL(hw) < GIC_NUM_LOCAL_INTRS)
return gic_local_irq_domain_map(d, virq, hw);
+
+ irq_set_chip_and_handler(virq, &gic_level_irq_controller,
+ handle_level_irq);
+
return gic_shared_irq_domain_map(d, virq, hw, 0);
}
@@ -771,11 +772,13 @@
hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i);
ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq,
- &gic_edge_irq_controller,
+ &gic_level_irq_controller,
NULL);
if (ret)
goto error;
+ irq_set_handler(virq + i, handle_level_irq);
+
ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu);
if (ret)
goto error;
@@ -890,10 +893,17 @@
return;
}
+static void gic_dev_domain_activate(struct irq_domain *domain,
+ struct irq_data *d)
+{
+ gic_shared_irq_domain_map(domain, d->irq, d->hwirq, 0);
+}
+
static struct irq_domain_ops gic_dev_domain_ops = {
.xlate = gic_dev_domain_xlate,
.alloc = gic_dev_domain_alloc,
.free = gic_dev_domain_free,
+ .activate = gic_dev_domain_activate,
};
static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
diff --git a/drivers/macintosh/ams/ams-i2c.c b/drivers/macintosh/ams/ams-i2c.c
index 978eda8..8a3ba56 100644
--- a/drivers/macintosh/ams/ams-i2c.c
+++ b/drivers/macintosh/ams/ams-i2c.c
@@ -73,7 +73,6 @@
static struct i2c_driver ams_i2c_driver = {
.driver = {
.name = "ams",
- .owner = THIS_MODULE,
},
.probe = ams_i2c_probe,
.remove = ams_i2c_remove,
diff --git a/drivers/macintosh/windfarm_pm112.c b/drivers/macintosh/windfarm_pm112.c
index 3024685..96d16fc 100644
--- a/drivers/macintosh/windfarm_pm112.c
+++ b/drivers/macintosh/windfarm_pm112.c
@@ -668,7 +668,6 @@
.remove = wf_pm112_remove,
.driver = {
.name = "windfarm",
- .owner = THIS_MODULE,
},
};
diff --git a/drivers/macintosh/windfarm_pm72.c b/drivers/macintosh/windfarm_pm72.c
index 2f506b9..e88cfb3 100644
--- a/drivers/macintosh/windfarm_pm72.c
+++ b/drivers/macintosh/windfarm_pm72.c
@@ -789,7 +789,6 @@
.remove = wf_pm72_remove,
.driver = {
.name = "windfarm",
- .owner = THIS_MODULE,
},
};
diff --git a/drivers/macintosh/windfarm_rm31.c b/drivers/macintosh/windfarm_rm31.c
index 82fc86a..bdfcb8a 100644
--- a/drivers/macintosh/windfarm_rm31.c
+++ b/drivers/macintosh/windfarm_rm31.c
@@ -682,7 +682,6 @@
.remove = wf_rm31_remove,
.driver = {
.name = "windfarm",
- .owner = THIS_MODULE,
},
};
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 95a4ca6..849ad44 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -760,7 +760,8 @@
if (!d->nr_stripes ||
d->nr_stripes > INT_MAX ||
d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
- pr_err("nr_stripes too large");
+ pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
+ (unsigned)d->nr_stripes);
return -ENOMEM;
}
@@ -1820,7 +1821,7 @@
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
- !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
+ !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) ||
@@ -1844,7 +1845,7 @@
struct block_device *bdev, struct cache *ca)
{
char name[BDEVNAME_SIZE];
- const char *err = NULL;
+ const char *err = NULL; /* must be set for any error case */
int ret = 0;
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
@@ -1861,8 +1862,13 @@
ca->discard = CACHE_DISCARD(&ca->sb);
ret = cache_alloc(ca);
- if (ret != 0)
+ if (ret != 0) {
+ if (ret == -ENOMEM)
+ err = "cache_alloc(): -ENOMEM";
+ else
+ err = "cache_alloc(): unknown error";
goto err;
+ }
if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
err = "error calling kobject_add";
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 6fff794..13041ee 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -2183,19 +2183,29 @@
static ssize_t
location_store(struct mddev *mddev, const char *buf, size_t len)
{
+ int rv;
+ rv = mddev_lock(mddev);
+ if (rv)
+ return rv;
if (mddev->pers) {
- if (!mddev->pers->quiesce)
- return -EBUSY;
- if (mddev->recovery || mddev->sync_thread)
- return -EBUSY;
+ if (!mddev->pers->quiesce) {
+ rv = -EBUSY;
+ goto out;
+ }
+ if (mddev->recovery || mddev->sync_thread) {
+ rv = -EBUSY;
+ goto out;
+ }
}
if (mddev->bitmap || mddev->bitmap_info.file ||
mddev->bitmap_info.offset) {
/* bitmap already configured. Only option is to clear it */
- if (strncmp(buf, "none", 4) != 0)
- return -EBUSY;
+ if (strncmp(buf, "none", 4) != 0) {
+ rv = -EBUSY;
+ goto out;
+ }
if (mddev->pers) {
mddev->pers->quiesce(mddev, 1);
bitmap_destroy(mddev);
@@ -2214,21 +2224,25 @@
/* nothing to be done */;
else if (strncmp(buf, "file:", 5) == 0) {
/* Not supported yet */
- return -EINVAL;
+ rv = -EINVAL;
+ goto out;
} else {
- int rv;
if (buf[0] == '+')
rv = kstrtoll(buf+1, 10, &offset);
else
rv = kstrtoll(buf, 10, &offset);
if (rv)
- return rv;
- if (offset == 0)
- return -EINVAL;
+ goto out;
+ if (offset == 0) {
+ rv = -EINVAL;
+ goto out;
+ }
if (mddev->bitmap_info.external == 0 &&
mddev->major_version == 0 &&
- offset != mddev->bitmap_info.default_offset)
- return -EINVAL;
+ offset != mddev->bitmap_info.default_offset) {
+ rv = -EINVAL;
+ goto out;
+ }
mddev->bitmap_info.offset = offset;
if (mddev->pers) {
struct bitmap *bitmap;
@@ -2245,7 +2259,7 @@
mddev->pers->quiesce(mddev, 0);
if (rv) {
bitmap_destroy(mddev);
- return rv;
+ goto out;
}
}
}
@@ -2257,6 +2271,11 @@
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
}
+ rv = 0;
+out:
+ mddev_unlock(mddev);
+ if (rv)
+ return rv;
return len;
}
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 97e446d..6a2e8dd 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -289,15 +289,13 @@
pb->bio_submitted = true;
/*
- * Map reads as normal only if corrupt_bio_byte set.
+ * Error reads if neither corrupt_bio_byte or drop_writes are set.
+ * Otherwise, flakey_end_io() will decide if the reads should be modified.
*/
if (bio_data_dir(bio) == READ) {
- /* If flags were specified, only corrupt those that match. */
- if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
- all_corrupt_bio_flags_match(bio, fc))
- goto map_bio;
- else
+ if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags))
return -EIO;
+ goto map_bio;
}
/*
@@ -334,14 +332,21 @@
struct flakey_c *fc = ti->private;
struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
- /*
- * Corrupt successful READs while in down state.
- */
if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
- if (fc->corrupt_bio_byte)
+ if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
+ all_corrupt_bio_flags_match(bio, fc)) {
+ /*
+ * Corrupt successful matching READs while in down state.
+ */
corrupt_bio_data(bio, fc);
- else
+
+ } else if (!test_bit(DROP_WRITES, &fc->flags)) {
+ /*
+ * Error read during the down_interval if drop_writes
+ * wasn't configured.
+ */
return -EIO;
+ }
}
return error;
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 4ca2d1d..07fc1ad 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -291,9 +291,10 @@
core->nr_regions = le64_to_cpu(disk->nr_regions);
}
-static int rw_header(struct log_c *lc, int rw)
+static int rw_header(struct log_c *lc, int op)
{
- lc->io_req.bi_op = rw;
+ lc->io_req.bi_op = op;
+ lc->io_req.bi_op_flags = 0;
return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
}
@@ -316,7 +317,7 @@
{
int r;
- r = rw_header(log, READ);
+ r = rw_header(log, REQ_OP_READ);
if (r)
return r;
@@ -630,7 +631,7 @@
header_to_disk(&lc->header, lc->disk_header);
/* write the new header */
- r = rw_header(lc, WRITE);
+ r = rw_header(lc, REQ_OP_WRITE);
if (!r) {
r = flush_header(lc);
if (r)
@@ -698,7 +699,7 @@
log_clear_bit(lc, lc->clean_bits, i);
}
- r = rw_header(lc, WRITE);
+ r = rw_header(lc, REQ_OP_WRITE);
if (r)
fail_log_device(lc);
else {
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 41573f1..34a840d 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -834,8 +834,10 @@
goto err;
}
cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0);
- if (!cinfo->ack_lockres)
+ if (!cinfo->ack_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
/* get sync CR lock on ACK. */
if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR))
pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n",
@@ -849,8 +851,10 @@
pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
- if (!cinfo->bitmap_lockres)
+ if (!cinfo->bitmap_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
pr_err("Failed to get bitmap lock\n");
ret = -EINVAL;
@@ -858,8 +862,10 @@
}
cinfo->resync_lockres = lockres_init(mddev, "resync", NULL, 0);
- if (!cinfo->resync_lockres)
+ if (!cinfo->resync_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
return 0;
err:
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d646f6e..67642ba 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1604,11 +1604,8 @@
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
- if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) {
+ if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
set_bit(MD_HAS_JOURNAL, &mddev->flags);
- if (mddev->recovery_cp == MaxSector)
- set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
- }
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling, except for
* spares (which don't need an event count) */
@@ -5851,6 +5848,9 @@
working++;
if (test_bit(In_sync, &rdev->flags))
insync++;
+ else if (test_bit(Journal, &rdev->flags))
+ /* TODO: add journal count to md_u.h */
+ ;
else
spare++;
}
@@ -7862,6 +7862,7 @@
*/
do {
+ int mddev2_minor = -1;
mddev->curr_resync = 2;
try_again:
@@ -7891,10 +7892,14 @@
prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
mddev2->curr_resync >= mddev->curr_resync) {
- printk(KERN_INFO "md: delaying %s of %s"
- " until %s has finished (they"
- " share one or more physical units)\n",
- desc, mdname(mddev), mdname(mddev2));
+ if (mddev2_minor != mddev2->md_minor) {
+ mddev2_minor = mddev2->md_minor;
+ printk(KERN_INFO "md: delaying %s of %s"
+ " until %s has finished (they"
+ " share one or more physical units)\n",
+ desc, mdname(mddev),
+ mdname(mddev2));
+ }
mddev_put(mddev2);
if (signal_pending(current))
flush_signals(current);
@@ -8275,16 +8280,13 @@
static void md_start_sync(struct work_struct *ws)
{
struct mddev *mddev = container_of(ws, struct mddev, del_work);
- int ret = 0;
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
"resync");
if (!mddev->sync_thread) {
- if (!(mddev_is_clustered(mddev) && ret == -EAGAIN))
- printk(KERN_ERR "%s: could not start resync"
- " thread...\n",
- mdname(mddev));
+ printk(KERN_ERR "%s: could not start resync thread...\n",
+ mdname(mddev));
/* leave the spares where they are, it shouldn't hurt */
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0e4efcd..be1a9fc 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1064,6 +1064,8 @@
int max_sectors;
int sectors;
+ md_write_start(mddev, bio);
+
/*
* Register the new request and wait if the reconstruction
* thread has put up a bar for new requests.
@@ -1445,8 +1447,6 @@
return;
}
- md_write_start(mddev, bio);
-
do {
/*
@@ -2465,20 +2465,21 @@
while (sect_to_write) {
struct bio *wbio;
+ sector_t wsector;
if (sectors > sect_to_write)
sectors = sect_to_write;
/* Write at 'sector' for 'sectors' */
wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
- wbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+
- choose_data_offset(r10_bio, rdev) +
- (sector - r10_bio->sector));
+ wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
+ wbio->bi_iter.bi_sector = wsector +
+ choose_data_offset(r10_bio, rdev);
wbio->bi_bdev = rdev->bdev;
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
if (submit_bio_wait(wbio) < 0)
/* Failure! */
- ok = rdev_set_badblocks(rdev, sector,
+ ok = rdev_set_badblocks(rdev, wsector,
sectors, 0)
&& ok;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8912407..da583bb 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -659,6 +659,7 @@
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(sector);
+ int inc_empty_inactive_list_flag;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
@@ -703,7 +704,12 @@
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&sh->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (sh->group) {
sh->group->stripes_cnt--;
sh->group = NULL;
@@ -762,6 +768,7 @@
sector_t head_sector, tmp_sec;
int hash;
int dd_idx;
+ int inc_empty_inactive_list_flag;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
@@ -779,7 +786,12 @@
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
!test_bit(STRIPE_EXPANDING, &head->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&head->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (head->group) {
head->group->stripes_cnt--;
head->group = NULL;
@@ -993,7 +1005,6 @@
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(bi);
bi->bi_bdev = rdev->bdev;
bio_set_op_attrs(bi, op, op_flags);
bi->bi_end_io = op_is_write(op)
@@ -1045,7 +1056,6 @@
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(rbi);
rbi->bi_bdev = rrdev->bdev;
bio_set_op_attrs(rbi, op, op_flags);
BUG_ON(!op_is_write(op));
@@ -1978,9 +1988,11 @@
put_cpu();
}
-static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
+ int disks)
{
struct stripe_head *sh;
+ int i;
sh = kmem_cache_zalloc(sc, gfp);
if (sh) {
@@ -1989,6 +2001,17 @@
INIT_LIST_HEAD(&sh->batch_list);
INIT_LIST_HEAD(&sh->lru);
atomic_set(&sh->count, 1);
+ for (i = 0; i < disks; i++) {
+ struct r5dev *dev = &sh->dev[i];
+
+ bio_init(&dev->req);
+ dev->req.bi_io_vec = &dev->vec;
+ dev->req.bi_max_vecs = 1;
+
+ bio_init(&dev->rreq);
+ dev->rreq.bi_io_vec = &dev->rvec;
+ dev->rreq.bi_max_vecs = 1;
+ }
}
return sh;
}
@@ -1996,7 +2019,7 @@
{
struct stripe_head *sh;
- sh = alloc_stripe(conf->slab_cache, gfp);
+ sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
if (!sh)
return 0;
@@ -2167,7 +2190,7 @@
mutex_lock(&conf->cache_size_mutex);
for (i = conf->max_nr_stripes; i; i--) {
- nsh = alloc_stripe(sc, GFP_KERNEL);
+ nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
if (!nsh)
break;
@@ -2299,6 +2322,7 @@
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
@@ -2402,6 +2426,7 @@
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
+ bio_reset(bi);
}
static void raid5_end_write_request(struct bio *bi)
@@ -2436,6 +2461,7 @@
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
@@ -2479,22 +2505,13 @@
if (sh->batch_head && sh != sh->batch_head)
raid5_release_stripe(sh->batch_head);
+ bio_reset(bi);
}
static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
struct r5dev *dev = &sh->dev[i];
- bio_init(&dev->req);
- dev->req.bi_io_vec = &dev->vec;
- dev->req.bi_max_vecs = 1;
- dev->req.bi_private = sh;
-
- bio_init(&dev->rreq);
- dev->rreq.bi_io_vec = &dev->rvec;
- dev->rreq.bi_max_vecs = 1;
- dev->rreq.bi_private = sh;
-
dev->flags = 0;
dev->sector = raid5_compute_blocknr(sh, i, previous);
}
@@ -4628,7 +4645,9 @@
}
if (!bio_list_empty(&s.return_bi)) {
- if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+ if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) &&
+ (s.failed <= conf->max_degraded ||
+ conf->mddev->external == 0)) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->return_bi, &s.return_bi);
spin_unlock_irq(&conf->device_lock);
@@ -6826,11 +6845,14 @@
if (IS_ERR(conf))
return PTR_ERR(conf);
- if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
- printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
- mdname(mddev));
- mddev->ro = 1;
- set_disk_ro(mddev->gendisk, 1);
+ if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+ if (!journal_dev) {
+ pr_err("md/raid:%s: journal disk is missing, force array readonly\n",
+ mdname(mddev));
+ mddev->ro = 1;
+ set_disk_ro(mddev->gendisk, 1);
+ } else if (mddev->recovery_cp == MaxSector)
+ set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
}
conf->min_offset_diff = min_offset_diff;
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index 7ada5f1..3519ace 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -230,6 +230,11 @@
if (phb->bus == NULL)
return -ENXIO;
+ /* Set release hook on root bus */
+ pci_set_host_bridge_release(to_pci_host_bridge(phb->bus->bridge),
+ pcibios_free_controller_deferred,
+ (void *) phb);
+
/* Claim resources. This might need some rework as well depending
* whether we are doing probe-only or not, like assigning unassigned
* resources etc...
@@ -256,7 +261,10 @@
afu->phb = NULL;
pci_remove_root_bus(phb->bus);
- pcibios_free_controller(phb);
+ /*
+ * We don't free phb here - that's handled by
+ * pcibios_free_controller_deferred()
+ */
}
static bool _cxl_pci_is_vphb_device(struct pci_controller *phb)
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 48a5dd7..2206d44 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1726,6 +1726,7 @@
break;
if (req_op(next) == REQ_OP_DISCARD ||
+ req_op(next) == REQ_OP_SECURE_ERASE ||
req_op(next) == REQ_OP_FLUSH)
break;
@@ -2150,6 +2151,7 @@
struct mmc_card *card = md->queue.card;
struct mmc_host *host = card->host;
unsigned long flags;
+ bool req_is_special = mmc_req_is_special(req);
if (req && !mq->mqrq_prev->req)
/* claim host only for the first request */
@@ -2190,8 +2192,7 @@
}
out:
- if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
- mmc_req_is_special(req))
+ if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special)
/*
* Release host when there are no more requests
* and after special request(discard, flush) is done.
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index bf14642..7080572 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -33,7 +33,8 @@
/*
* We only like normal block requests and discards.
*/
- if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) {
+ if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
+ req_op(req) != REQ_OP_SECURE_ERASE) {
blk_dump_rq_flags(req, "MMC bad request");
return BLKPREP_KILL;
}
@@ -64,6 +65,8 @@
spin_unlock_irq(q->queue_lock);
if (req || mq->mqrq_prev->req) {
+ bool req_is_special = mmc_req_is_special(req);
+
set_current_state(TASK_RUNNING);
mq->issue_fn(mq, req);
cond_resched();
@@ -79,7 +82,7 @@
* has been finished. Do not assign it to previous
* request.
*/
- if (mmc_req_is_special(req))
+ if (req_is_special)
mq->mqrq_cur->req = NULL;
mq->mqrq_prev->brq.mrq.data = NULL;
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index d625311..fee5e12 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -4,7 +4,9 @@
static inline bool mmc_req_is_special(struct request *req)
{
return req &&
- (req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD);
+ (req_op(req) == REQ_OP_FLUSH ||
+ req_op(req) == REQ_OP_DISCARD ||
+ req_op(req) == REQ_OP_SECURE_ERASE);
}
struct request;
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 463bed8..dd446e4 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -205,8 +205,8 @@
static inline void intrl2_##which##_mask_clear(struct bcm_sf2_priv *priv, \
u32 mask) \
{ \
- intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \
priv->irq##which##_mask &= ~(mask); \
+ intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \
} \
static inline void intrl2_##which##_mask_set(struct bcm_sf2_priv *priv, \
u32 mask) \
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index d1d9d3c..7106790 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2656,15 +2656,19 @@
return ret;
}
+ /* Rate Control: disable ingress rate limiting. */
if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
- mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) ||
mv88e6xxx_6320_family(chip)) {
- /* Rate Control: disable ingress rate limiting. */
ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
PORT_RATE_CONTROL, 0x0001);
if (ret)
return ret;
+ } else if (mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip)) {
+ ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
+ PORT_RATE_CONTROL, 0x0000);
+ if (ret)
+ return ret;
}
/* Port Control 1: disable trunking, disable sending
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 6453148..4eb17da 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1545,6 +1545,8 @@
.driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2400),
.driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
+ { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2500),
+ .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8162),
.driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8171) },
diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h
index 0959e68..1fc2d85 100644
--- a/drivers/net/ethernet/atheros/alx/reg.h
+++ b/drivers/net/ethernet/atheros/alx/reg.h
@@ -38,6 +38,7 @@
#define ALX_DEV_ID_AR8161 0x1091
#define ALX_DEV_ID_E2200 0xe091
#define ALX_DEV_ID_E2400 0xe0a1
+#define ALX_DEV_ID_E2500 0xe0b1
#define ALX_DEV_ID_AR8162 0x1090
#define ALX_DEV_ID_AR8171 0x10A1
#define ALX_DEV_ID_AR8172 0x10A0
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 9a9745c4..625235d 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -159,7 +159,7 @@
if (!bgmac_is_bcm4707_family(core)) {
mii_bus = bcma_mdio_mii_register(core, bgmac->phyaddr);
- if (!IS_ERR(mii_bus)) {
+ if (IS_ERR(mii_bus)) {
err = PTR_ERR(mii_bus);
goto err;
}
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index afb10e3..fab35a5 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -170,7 +170,6 @@
#define NIC_QSET_SQ_0_7_DOOR (0x010838)
#define NIC_QSET_SQ_0_7_STATUS (0x010840)
#define NIC_QSET_SQ_0_7_DEBUG (0x010848)
-#define NIC_QSET_SQ_0_7_CNM_CHG (0x010860)
#define NIC_QSET_SQ_0_7_STAT_0_1 (0x010900)
#define NIC_QSET_RBDR_0_1_CFG (0x010C00)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index d2d8ef2..ad4fddb 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -382,7 +382,10 @@
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q);
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q);
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q);
- p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q);
+ /* Padding, was NIC_QSET_SQ_0_7_CNM_CHG, which
+ * produces bus errors when read
+ */
+ p[i++] = 0;
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q);
reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3);
p[i++] = nicvf_queue_reg_read(nic, reg_offset, q);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index c45de49..c762a8c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -4335,6 +4335,11 @@
#endif
int ciq_size;
+ /* Reduce memory usage in kdump environment, disable all offload.
+ */
+ if (is_kdump_kernel())
+ adap->params.offload = 0;
+
for_each_port(adap, i)
n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
#ifdef CONFIG_CHELSIO_T4_DCB
@@ -4365,11 +4370,6 @@
if (q10g > netif_get_num_default_rss_queues())
q10g = netif_get_num_default_rss_queues();
- /* Reduce memory usage in kdump environment, disable all offload.
- */
- if (is_kdump_kernel())
- adap->params.offload = 0;
-
for_each_port(adap, i) {
struct port_info *pi = adap2pinfo(adap, i);
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index d20935d..4b4f5bc 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2922,17 +2922,25 @@
{
unsigned int size = lstatus & BD_LENGTH_MASK;
struct page *page = rxb->page;
+ bool last = !!(lstatus & BD_LFLAG(RXBD_LAST));
/* Remove the FCS from the packet length */
- if (likely(lstatus & BD_LFLAG(RXBD_LAST)))
+ if (last)
size -= ETH_FCS_LEN;
- if (likely(first))
+ if (likely(first)) {
skb_put(skb, size);
- else
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
- rxb->page_offset + RXBUF_ALIGNMENT,
- size, GFAR_RXB_TRUESIZE);
+ } else {
+ /* the last fragments' length contains the full frame length */
+ if (last)
+ size -= skb->len;
+
+ /* in case the last fragment consisted only of the FCS */
+ if (size > 0)
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+ rxb->page_offset + RXBUF_ALIGNMENT,
+ size, GFAR_RXB_TRUESIZE);
+ }
/* try reuse page */
if (unlikely(page_count(page) != 1))
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 373fd09..6e8a9c8 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -100,7 +100,8 @@
#define DEFAULT_RX_LFC_THR 16
#define DEFAULT_LFC_PTVVAL 4
-#define GFAR_RXB_SIZE 1536
+/* prevent fragmenation by HW in DSA environments */
+#define GFAR_RXB_SIZE roundup(1536 + 8, 64)
#define GFAR_SKBFRAG_SIZE (RXBUF_ALIGNMENT + GFAR_RXB_SIZE \
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
#define GFAR_RXB_TRUESIZE 2048
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index ff8b6a4..6ea8722 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -328,9 +328,10 @@
static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
{
u32 port;
- struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev;
if (ppe_cb->ppe_common_cb) {
+ struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev;
+
port = ppe_cb->index;
dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 0);
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index e1370c5..618f184 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -199,6 +199,7 @@
void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi)
{
struct i40e_client_instance *cdev;
+ int ret = 0;
if (!vsi)
return;
@@ -211,7 +212,14 @@
"Cannot locate client instance open routine\n");
continue;
}
- cdev->client->ops->open(&cdev->lan_info, cdev->client);
+ if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED,
+ &cdev->state))) {
+ ret = cdev->client->ops->open(&cdev->lan_info,
+ cdev->client);
+ if (!ret)
+ set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+ &cdev->state);
+ }
}
}
mutex_unlock(&i40e_client_instance_mutex);
@@ -407,12 +415,14 @@
* i40e_client_add_instance - add a client instance struct to the instance list
* @pf: pointer to the board struct
* @client: pointer to a client struct in the client list.
+ * @existing: if there was already an existing instance
*
- * Returns cdev ptr on success, NULL on failure
+ * Returns cdev ptr on success or if already exists, NULL on failure
**/
static
struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
- struct i40e_client *client)
+ struct i40e_client *client,
+ bool *existing)
{
struct i40e_client_instance *cdev;
struct netdev_hw_addr *mac = NULL;
@@ -421,7 +431,7 @@
mutex_lock(&i40e_client_instance_mutex);
list_for_each_entry(cdev, &i40e_client_instances, list) {
if ((cdev->lan_info.pf == pf) && (cdev->client == client)) {
- cdev = NULL;
+ *existing = true;
goto out;
}
}
@@ -505,6 +515,7 @@
{
struct i40e_client_instance *cdev;
struct i40e_client *client;
+ bool existing = false;
int ret = 0;
if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED))
@@ -528,18 +539,25 @@
/* check if L2 VSI is up, if not we are not ready */
if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
continue;
+ } else {
+ dev_warn(&pf->pdev->dev, "This client %s is being instanciated at probe\n",
+ client->name);
}
/* Add the client instance to the instance list */
- cdev = i40e_client_add_instance(pf, client);
+ cdev = i40e_client_add_instance(pf, client, &existing);
if (!cdev)
continue;
- /* Also up the ref_cnt of no. of instances of this client */
- atomic_inc(&client->ref_cnt);
- dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
- client->name, pf->hw.pf_id,
- pf->hw.bus.device, pf->hw.bus.func);
+ if (!existing) {
+ /* Also up the ref_cnt for no. of instances of this
+ * client.
+ */
+ atomic_inc(&client->ref_cnt);
+ dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
+ client->name, pf->hw.pf_id,
+ pf->hw.bus.device, pf->hw.bus.func);
+ }
/* Send an Open request to the client */
atomic_inc(&cdev->ref_cnt);
@@ -588,7 +606,8 @@
pf->hw.pf_id, pf->hw.bus.device, pf->hw.bus.func);
/* Since in some cases register may have happened before a device gets
- * added, we can schedule a subtask to go initiate the clients.
+ * added, we can schedule a subtask to go initiate the clients if
+ * they can be launched at probe time.
*/
pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
i40e_service_event_schedule(pf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index c6ac7a6..828ed28 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5431,7 +5431,6 @@
wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16);
udp_tunnel_get_rx_info(netdev);
- i40e_notify_client_of_netdev_open(vsi);
return 0;
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index b4217f3..c47b605 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -2958,8 +2958,10 @@
}
/* was that the last pool using this rar? */
- if (mpsar_lo == 0 && mpsar_hi == 0 && rar != 0)
+ if (mpsar_lo == 0 && mpsar_hi == 0 &&
+ rar != 0 && rar != hw->mac.san_mac_rar_index)
hw->mac.ops.clear_rar(hw, rar);
+
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d6e2a1c..c2ec01a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -143,13 +143,14 @@
return cmd->cmd_buf + (idx << cmd->log_stride);
}
-static u8 xor8_buf(void *buf, int len)
+static u8 xor8_buf(void *buf, size_t offset, int len)
{
u8 *ptr = buf;
u8 sum = 0;
int i;
+ int end = len + offset;
- for (i = 0; i < len; i++)
+ for (i = offset; i < end; i++)
sum ^= ptr[i];
return sum;
@@ -157,41 +158,49 @@
static int verify_block_sig(struct mlx5_cmd_prot_block *block)
{
- if (xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 1) != 0xff)
+ size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+ int xor_len = sizeof(*block) - sizeof(block->data) - 1;
+
+ if (xor8_buf(block, rsvd0_off, xor_len) != 0xff)
return -EINVAL;
- if (xor8_buf(block, sizeof(*block)) != 0xff)
+ if (xor8_buf(block, 0, sizeof(*block)) != 0xff)
return -EINVAL;
return 0;
}
-static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token,
- int csum)
+static void calc_block_sig(struct mlx5_cmd_prot_block *block)
{
- block->token = token;
- if (csum) {
- block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) -
- sizeof(block->data) - 2);
- block->sig = ~xor8_buf(block, sizeof(*block) - 1);
- }
+ int ctrl_xor_len = sizeof(*block) - sizeof(block->data) - 2;
+ size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+
+ block->ctrl_sig = ~xor8_buf(block, rsvd0_off, ctrl_xor_len);
+ block->sig = ~xor8_buf(block, 0, sizeof(*block) - 1);
}
-static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum)
+static void calc_chain_sig(struct mlx5_cmd_msg *msg)
{
struct mlx5_cmd_mailbox *next = msg->next;
+ int size = msg->len;
+ int blen = size - min_t(int, sizeof(msg->first.data), size);
+ int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+ / MLX5_CMD_DATA_BLOCK_SIZE;
+ int i = 0;
- while (next) {
- calc_block_sig(next->buf, token, csum);
+ for (i = 0; i < n && next; i++) {
+ calc_block_sig(next->buf);
next = next->next;
}
}
static void set_signature(struct mlx5_cmd_work_ent *ent, int csum)
{
- ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay));
- calc_chain_sig(ent->in, ent->token, csum);
- calc_chain_sig(ent->out, ent->token, csum);
+ ent->lay->sig = ~xor8_buf(ent->lay, 0, sizeof(*ent->lay));
+ if (csum) {
+ calc_chain_sig(ent->in);
+ calc_chain_sig(ent->out);
+ }
}
static void poll_timeout(struct mlx5_cmd_work_ent *ent)
@@ -222,12 +231,17 @@
struct mlx5_cmd_mailbox *next = ent->out->next;
int err;
u8 sig;
+ int size = ent->out->len;
+ int blen = size - min_t(int, sizeof(ent->out->first.data), size);
+ int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+ / MLX5_CMD_DATA_BLOCK_SIZE;
+ int i = 0;
- sig = xor8_buf(ent->lay, sizeof(*ent->lay));
+ sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay));
if (sig != 0xff)
return -EINVAL;
- while (next) {
+ for (i = 0; i < n && next; i++) {
err = verify_block_sig(next->buf);
if (err)
return err;
@@ -656,7 +670,6 @@
spin_unlock_irqrestore(&cmd->alloc_lock, flags);
}
- ent->token = alloc_token(cmd);
cmd->ent_arr[ent->idx] = ent;
lay = get_inst(cmd, ent->idx);
ent->lay = lay;
@@ -766,7 +779,8 @@
static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
struct mlx5_cmd_msg *out, void *uout, int uout_size,
mlx5_cmd_cbk_t callback,
- void *context, int page_queue, u8 *status)
+ void *context, int page_queue, u8 *status,
+ u8 token)
{
struct mlx5_cmd *cmd = &dev->cmd;
struct mlx5_cmd_work_ent *ent;
@@ -783,6 +797,8 @@
if (IS_ERR(ent))
return PTR_ERR(ent);
+ ent->token = token;
+
if (!callback)
init_completion(&ent->done);
@@ -854,7 +870,8 @@
.write = dbg_write,
};
-static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
+static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size,
+ u8 token)
{
struct mlx5_cmd_prot_block *block;
struct mlx5_cmd_mailbox *next;
@@ -880,6 +897,7 @@
memcpy(block->data, from, copy);
from += copy;
size -= copy;
+ block->token = token;
next = next->next;
}
@@ -949,7 +967,8 @@
}
static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
- gfp_t flags, int size)
+ gfp_t flags, int size,
+ u8 token)
{
struct mlx5_cmd_mailbox *tmp, *head = NULL;
struct mlx5_cmd_prot_block *block;
@@ -978,6 +997,7 @@
tmp->next = head;
block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0);
block->block_num = cpu_to_be32(n - i - 1);
+ block->token = token;
head = tmp;
}
msg->next = head;
@@ -1352,7 +1372,7 @@
}
if (IS_ERR(msg))
- msg = mlx5_alloc_cmd_msg(dev, gfp, in_size);
+ msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
return msg;
}
@@ -1377,6 +1397,7 @@
int err;
u8 status = 0;
u32 drv_synd;
+ u8 token;
if (pci_channel_offline(dev->pdev) ||
dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -1395,20 +1416,22 @@
return err;
}
- err = mlx5_copy_to_msg(inb, in, in_size);
+ token = alloc_token(&dev->cmd);
+
+ err = mlx5_copy_to_msg(inb, in, in_size, token);
if (err) {
mlx5_core_warn(dev, "err %d\n", err);
goto out_in;
}
- outb = mlx5_alloc_cmd_msg(dev, gfp, out_size);
+ outb = mlx5_alloc_cmd_msg(dev, gfp, out_size, token);
if (IS_ERR(outb)) {
err = PTR_ERR(outb);
goto out_in;
}
err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context,
- pages_queue, &status);
+ pages_queue, &status, token);
if (err)
goto out_out;
@@ -1476,7 +1499,7 @@
INIT_LIST_HEAD(&cmd->cache.med.head);
for (i = 0; i < NUM_LONG_LISTS; i++) {
- msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE);
+ msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0);
if (IS_ERR(msg)) {
err = PTR_ERR(msg);
goto ex_err;
@@ -1486,7 +1509,7 @@
}
for (i = 0; i < NUM_MED_LISTS; i++) {
- msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE);
+ msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0);
if (IS_ERR(msg)) {
err = PTR_ERR(msg);
goto ex_err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 1b495ef..bf722aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -73,8 +73,12 @@
#define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
#define MLX5_MPWRQ_STRIDES_PER_PAGE (MLX5_MPWRQ_NUM_STRIDES >> \
MLX5_MPWRQ_WQE_PAGE_ORDER)
-#define MLX5_CHANNEL_MAX_NUM_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8) * \
- BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW))
+
+#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
+#define MLX5E_REQUIRED_MTTS(rqs, wqes)\
+ (rqs * wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX)
+
#define MLX5_UMR_ALIGN (2048)
#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128)
@@ -219,9 +223,8 @@
};
enum {
- MLX5E_RQ_STATE_POST_WQES_ENABLE,
+ MLX5E_RQ_STATE_FLUSH,
MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
- MLX5E_RQ_STATE_FLUSH_TIMEOUT,
MLX5E_RQ_STATE_AM,
};
@@ -304,6 +307,7 @@
unsigned long state;
int ix;
+ u32 mpwqe_mtt_offset;
struct mlx5e_rx_am am; /* Adaptive Moderation */
@@ -365,9 +369,8 @@
};
enum {
- MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
+ MLX5E_SQ_STATE_FLUSH,
MLX5E_SQ_STATE_BF_ENABLE,
- MLX5E_SQ_STATE_TX_TIMEOUT,
};
struct mlx5e_ico_wqe_info {
@@ -698,7 +701,6 @@
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
-void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
@@ -814,11 +816,6 @@
MLX5E_MAX_NUM_CHANNELS);
}
-static inline int mlx5e_get_mtt_octw(int npages)
-{
- return ALIGN(npages, 8) / 2;
-}
-
extern const struct ethtool_ops mlx5e_ethtool_ops;
#ifdef CONFIG_MLX5_CORE_EN_DCB
extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 673043c..9cce153 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -139,7 +139,7 @@
struct mlx5e_tir *tir;
void *in;
int inlen;
- int err;
+ int err = 0;
inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
in = mlx5_vzalloc(inlen);
@@ -151,10 +151,11 @@
list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
if (err)
- return err;
+ goto out;
}
+out:
kvfree(in);
- return 0;
+ return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index caa9a3c..762af16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -127,29 +127,40 @@
return mlx5_set_port_tc_bw_alloc(mdev, tc_tx_bw);
}
-static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets)
+static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
+ struct ieee_ets *ets)
{
int bw_sum = 0;
int i;
/* Validate Priority */
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
- if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY)
+ if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY) {
+ netdev_err(netdev,
+ "Failed to validate ETS: priority value greater than max(%d)\n",
+ MLX5E_MAX_PRIORITY);
return -EINVAL;
+ }
}
/* Validate Bandwidth Sum */
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
- if (!ets->tc_tx_bw[i])
+ if (!ets->tc_tx_bw[i]) {
+ netdev_err(netdev,
+ "Failed to validate ETS: BW 0 is illegal\n");
return -EINVAL;
+ }
bw_sum += ets->tc_tx_bw[i];
}
}
- if (bw_sum != 0 && bw_sum != 100)
+ if (bw_sum != 0 && bw_sum != 100) {
+ netdev_err(netdev,
+ "Failed to validate ETS: BW sum is illegal\n");
return -EINVAL;
+ }
return 0;
}
@@ -159,7 +170,7 @@
struct mlx5e_priv *priv = netdev_priv(netdev);
int err;
- err = mlx5e_dbcnl_validate_ets(ets);
+ err = mlx5e_dbcnl_validate_ets(netdev, ets);
if (err)
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 4a3757e..d0cf8fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -352,15 +352,61 @@
sq_stats_desc, j);
}
+static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
+ int num_wqe)
+{
+ int packets_per_wqe;
+ int stride_size;
+ int num_strides;
+ int wqe_size;
+
+ if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+ return num_wqe;
+
+ stride_size = 1 << priv->params.mpwqe_log_stride_sz;
+ num_strides = 1 << priv->params.mpwqe_log_num_strides;
+ wqe_size = stride_size * num_strides;
+
+ packets_per_wqe = wqe_size /
+ ALIGN(ETH_DATA_LEN, stride_size);
+ return (1 << (order_base_2(num_wqe * packets_per_wqe) - 1));
+}
+
+static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
+ int num_packets)
+{
+ int packets_per_wqe;
+ int stride_size;
+ int num_strides;
+ int wqe_size;
+ int num_wqes;
+
+ if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+ return num_packets;
+
+ stride_size = 1 << priv->params.mpwqe_log_stride_sz;
+ num_strides = 1 << priv->params.mpwqe_log_num_strides;
+ wqe_size = stride_size * num_strides;
+
+ num_packets = (1 << order_base_2(num_packets));
+
+ packets_per_wqe = wqe_size /
+ ALIGN(ETH_DATA_LEN, stride_size);
+ num_wqes = DIV_ROUND_UP(num_packets, packets_per_wqe);
+ return 1 << (order_base_2(num_wqes));
+}
+
static void mlx5e_get_ringparam(struct net_device *dev,
struct ethtool_ringparam *param)
{
struct mlx5e_priv *priv = netdev_priv(dev);
int rq_wq_type = priv->params.rq_wq_type;
- param->rx_max_pending = 1 << mlx5_max_log_rq_size(rq_wq_type);
+ param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << mlx5_max_log_rq_size(rq_wq_type));
param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
- param->rx_pending = 1 << priv->params.log_rq_size;
+ param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << priv->params.log_rq_size);
param->tx_pending = 1 << priv->params.log_sq_size;
}
@@ -370,9 +416,13 @@
struct mlx5e_priv *priv = netdev_priv(dev);
bool was_opened;
int rq_wq_type = priv->params.rq_wq_type;
+ u32 rx_pending_wqes;
+ u32 min_rq_size;
+ u32 max_rq_size;
u16 min_rx_wqes;
u8 log_rq_size;
u8 log_sq_size;
+ u32 num_mtts;
int err = 0;
if (param->rx_jumbo_pending) {
@@ -385,18 +435,36 @@
__func__);
return -EINVAL;
}
- if (param->rx_pending < (1 << mlx5_min_log_rq_size(rq_wq_type))) {
+
+ min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << mlx5_min_log_rq_size(rq_wq_type));
+ max_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << mlx5_max_log_rq_size(rq_wq_type));
+ rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type,
+ param->rx_pending);
+
+ if (param->rx_pending < min_rq_size) {
netdev_info(dev, "%s: rx_pending (%d) < min (%d)\n",
__func__, param->rx_pending,
- 1 << mlx5_min_log_rq_size(rq_wq_type));
+ min_rq_size);
return -EINVAL;
}
- if (param->rx_pending > (1 << mlx5_max_log_rq_size(rq_wq_type))) {
+ if (param->rx_pending > max_rq_size) {
netdev_info(dev, "%s: rx_pending (%d) > max (%d)\n",
__func__, param->rx_pending,
- 1 << mlx5_max_log_rq_size(rq_wq_type));
+ max_rq_size);
return -EINVAL;
}
+
+ num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels,
+ rx_pending_wqes);
+ if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+ !MLX5E_VALID_NUM_MTTS(num_mtts)) {
+ netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
+ __func__, param->rx_pending);
+ return -EINVAL;
+ }
+
if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) {
netdev_info(dev, "%s: tx_pending (%d) < min (%d)\n",
__func__, param->tx_pending,
@@ -410,9 +478,9 @@
return -EINVAL;
}
- log_rq_size = order_base_2(param->rx_pending);
+ log_rq_size = order_base_2(rx_pending_wqes);
log_sq_size = order_base_2(param->tx_pending);
- min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, param->rx_pending);
+ min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, rx_pending_wqes);
if (log_rq_size == priv->params.log_rq_size &&
log_sq_size == priv->params.log_sq_size &&
@@ -454,6 +522,7 @@
unsigned int count = ch->combined_count;
bool arfs_enabled;
bool was_opened;
+ u32 num_mtts;
int err = 0;
if (!count) {
@@ -472,6 +541,14 @@
return -EINVAL;
}
+ num_mtts = MLX5E_REQUIRED_MTTS(count, BIT(priv->params.log_rq_size));
+ if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+ !MLX5E_VALID_NUM_MTTS(num_mtts)) {
+ netdev_info(dev, "%s: rx count (%d) request can't be satisfied, try to reduce.\n",
+ __func__, count);
+ return -EINVAL;
+ }
+
if (priv->params.num_channels == count)
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 870bea3..2459c7f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,13 +39,6 @@
#include "eswitch.h"
#include "vxlan.h"
-enum {
- MLX5_EN_QP_FLUSH_TIMEOUT_MS = 5000,
- MLX5_EN_QP_FLUSH_MSLEEP_QUANT = 20,
- MLX5_EN_QP_FLUSH_MAX_ITER = MLX5_EN_QP_FLUSH_TIMEOUT_MS /
- MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
-};
-
struct mlx5e_rq_param {
u32 rqc[MLX5_ST_SZ_DW(rqc)];
struct mlx5_wq_param wq;
@@ -162,6 +155,7 @@
s->tx_queue_stopped += sq_stats->stopped;
s->tx_queue_wake += sq_stats->wake;
s->tx_queue_dropped += sq_stats->dropped;
+ s->tx_xmit_more += sq_stats->xmit_more;
s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
tx_offload_none += sq_stats->csum_none;
}
@@ -340,6 +334,9 @@
rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
+ rq->mpwqe_mtt_offset = c->ix *
+ MLX5E_REQUIRED_MTTS(1, BIT(priv->params.log_rq_size));
+
rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
rq->wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides;
@@ -428,7 +425,6 @@
MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn);
MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST);
- MLX5_SET(rqc, rqc, flush_in_error_en, 1);
MLX5_SET(rqc, rqc, vsd, priv->params.vlan_strip_disable);
MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift -
MLX5_ADAPTER_PAGE_SHIFT);
@@ -525,6 +521,27 @@
return -ETIMEDOUT;
}
+static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+{
+ struct mlx5_wq_ll *wq = &rq->wq;
+ struct mlx5e_rx_wqe *wqe;
+ __be16 wqe_ix_be;
+ u16 wqe_ix;
+
+ /* UMR WQE (if in progress) is always at wq->head */
+ if (test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
+ mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]);
+
+ while (!mlx5_wq_ll_is_empty(wq)) {
+ wqe_ix_be = *wq->tail_next;
+ wqe_ix = be16_to_cpu(wqe_ix_be);
+ wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
+ rq->dealloc_wqe(rq, wqe_ix);
+ mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
+ &wqe->next.next_wqe_index);
+ }
+}
+
static int mlx5e_open_rq(struct mlx5e_channel *c,
struct mlx5e_rq_param *param,
struct mlx5e_rq *rq)
@@ -548,8 +565,6 @@
if (param->am_enabled)
set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
- set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
-
sq->ico_wqe_info[pi].opcode = MLX5_OPCODE_NOP;
sq->ico_wqe_info[pi].num_wqebbs = 1;
mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */
@@ -566,23 +581,8 @@
static void mlx5e_close_rq(struct mlx5e_rq *rq)
{
- int tout = 0;
- int err;
-
- clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
+ set_bit(MLX5E_RQ_STATE_FLUSH, &rq->state);
napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
-
- err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
- while (!mlx5_wq_ll_is_empty(&rq->wq) && !err &&
- tout++ < MLX5_EN_QP_FLUSH_MAX_ITER)
- msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
-
- if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER)
- set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state);
-
- /* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
- napi_synchronize(&rq->channel->napi);
-
cancel_work_sync(&rq->am.work);
mlx5e_disable_rq(rq);
@@ -821,7 +821,6 @@
goto err_disable_sq;
if (sq->txq) {
- set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
netdev_tx_reset_queue(sq->txq);
netif_tx_start_queue(sq->txq);
}
@@ -845,38 +844,20 @@
static void mlx5e_close_sq(struct mlx5e_sq *sq)
{
- int tout = 0;
- int err;
-
- if (sq->txq) {
- clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
- /* prevent netif_tx_wake_queue */
- napi_synchronize(&sq->channel->napi);
- netif_tx_disable_queue(sq->txq);
-
- /* ensure hw is notified of all pending wqes */
- if (mlx5e_sq_has_room_for(sq, 1))
- mlx5e_send_nop(sq, true);
-
- err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
- MLX5_SQC_STATE_ERR, false, 0);
- if (err)
- set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
- }
-
- /* wait till sq is empty, unless a TX timeout occurred on this SQ */
- while (sq->cc != sq->pc &&
- !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
- msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
- if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
- set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
- }
-
- /* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
+ set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state);
+ /* prevent netif_tx_wake_queue */
napi_synchronize(&sq->channel->napi);
- mlx5e_free_tx_descs(sq);
+ if (sq->txq) {
+ netif_tx_disable_queue(sq->txq);
+
+ /* last doorbell out, godspeed .. */
+ if (mlx5e_sq_has_room_for(sq, 1))
+ mlx5e_send_nop(sq, true);
+ }
+
mlx5e_disable_sq(sq);
+ mlx5e_free_tx_descs(sq);
mlx5e_destroy_sq(sq);
}
@@ -1826,10 +1807,6 @@
netif_set_real_num_tx_queues(netdev, num_txqs);
netif_set_real_num_rx_queues(netdev, priv->params.num_channels);
- err = mlx5e_set_dev_port_mtu(netdev);
- if (err)
- goto err_clear_state_opened_flag;
-
err = mlx5e_open_channels(priv);
if (err) {
netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n",
@@ -2573,6 +2550,7 @@
u16 max_mtu;
u16 min_mtu;
int err = 0;
+ bool reset;
mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
@@ -2588,13 +2566,18 @@
mutex_lock(&priv->state_lock);
+ reset = !priv->params.lro_en &&
+ (priv->params.rq_wq_type !=
+ MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+
was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
+ if (was_opened && reset)
mlx5e_close_locked(netdev);
netdev->mtu = new_mtu;
+ mlx5e_set_dev_port_mtu(netdev);
- if (was_opened)
+ if (was_opened && reset)
err = mlx5e_open_locked(netdev);
mutex_unlock(&priv->state_lock);
@@ -2794,7 +2777,7 @@
if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
continue;
sched_work = true;
- set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+ set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state);
netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
}
@@ -3231,8 +3214,8 @@
struct mlx5_create_mkey_mbox_in *in;
struct mlx5_mkey_seg *mkc;
int inlen = sizeof(*in);
- u64 npages =
- priv->profile->max_nch(mdev) * MLX5_CHANNEL_MAX_NUM_MTTS;
+ u64 npages = MLX5E_REQUIRED_MTTS(priv->profile->max_nch(mdev),
+ BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW));
int err;
in = mlx5_vzalloc(inlen);
@@ -3246,10 +3229,12 @@
MLX5_PERM_LOCAL_WRITE |
MLX5_ACCESS_MODE_MTT;
+ npages = min_t(u32, ALIGN(U16_MAX, 4) * 2, npages);
+
mkc->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
mkc->flags_pd = cpu_to_be32(mdev->mlx5e_res.pdn);
mkc->len = cpu_to_be64(npages << PAGE_SHIFT);
- mkc->xlt_oct_size = cpu_to_be32(mlx5e_get_mtt_octw(npages));
+ mkc->xlt_oct_size = cpu_to_be32(MLX5_MTT_OCTW(npages));
mkc->log2_page_size = PAGE_SHIFT;
err = mlx5_core_create_mkey(mdev, &priv->umr_mkey, in, inlen, NULL,
@@ -3385,6 +3370,7 @@
queue_work(priv->wq, &priv->set_rx_mode_work);
if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
+ mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
rep.load = mlx5e_nic_rep_load;
rep.unload = mlx5e_nic_rep_unload;
rep.vport = 0;
@@ -3463,6 +3449,8 @@
mlx5e_init_l2_addr(priv);
+ mlx5e_set_dev_port_mtu(netdev);
+
err = register_netdev(netdev);
if (err) {
mlx5_core_err(mdev, "register_netdev failed, %d\n", err);
@@ -3501,16 +3489,20 @@
struct mlx5_eswitch *esw = mdev->priv.eswitch;
int total_vfs = MLX5_TOTAL_VPORTS(mdev);
int vport;
+ u8 mac[ETH_ALEN];
if (!MLX5_CAP_GEN(mdev, vport_group_manager))
return;
+ mlx5_query_nic_vport_mac_address(mdev, 0, mac);
+
for (vport = 1; vport < total_vfs; vport++) {
struct mlx5_eswitch_rep rep;
rep.load = mlx5e_vport_rep_load;
rep.unload = mlx5e_vport_rep_unload;
rep.vport = vport;
+ ether_addr_copy(rep.hw_id, mac);
mlx5_eswitch_register_vport_rep(esw, &rep);
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 1c7d8b8..134de4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -135,17 +135,16 @@
int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
{
struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5_eswitch_rep *rep = priv->ppriv;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
- u8 mac[ETH_ALEN];
if (esw->mode == SRIOV_NONE)
return -EOPNOTSUPP;
switch (attr->id) {
case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
- mlx5_query_nic_vport_mac_address(priv->mdev, 0, mac);
attr->u.ppid.id_len = ETH_ALEN;
- memcpy(&attr->u.ppid.id, &mac, ETH_ALEN);
+ ether_addr_copy(attr->u.ppid.id, rep->hw_id);
break;
default:
return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 9f2a16a..b6f8ebb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -324,9 +324,9 @@
}
}
-static u16 mlx5e_get_wqe_mtt_offset(u16 rq_ix, u16 wqe_ix)
+static u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix)
{
- return rq_ix * MLX5_CHANNEL_MAX_NUM_MTTS +
+ return rq->mpwqe_mtt_offset +
wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8);
}
@@ -340,7 +340,7 @@
struct mlx5_wqe_data_seg *dseg = &wqe->data;
struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
u8 ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS);
- u16 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix);
+ u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix);
memset(wqe, 0, sizeof(*wqe));
cseg->opmod_idx_opcode =
@@ -353,9 +353,9 @@
ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN;
ucseg->klm_octowords =
- cpu_to_be16(mlx5e_get_mtt_octw(MLX5_MPWRQ_PAGES_PER_WQE));
+ cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE));
ucseg->bsf_octowords =
- cpu_to_be16(mlx5e_get_mtt_octw(umr_wqe_mtt_offset));
+ cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset));
ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
dseg->lkey = sq->mkey_be;
@@ -423,7 +423,7 @@
{
struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
int mtt_sz = mlx5e_get_wqe_mtt_sz();
- u32 dma_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix) << PAGE_SHIFT;
+ u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT;
int i;
wi->umr.dma_info = kmalloc(sizeof(*wi->umr.dma_info) *
@@ -506,6 +506,12 @@
struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state);
+
+ if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) {
+ mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]);
+ return;
+ }
+
mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
rq->stats.mpwqe_frag++;
@@ -595,26 +601,9 @@
wi->free_wqe(rq, wi);
}
-void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
-{
- struct mlx5_wq_ll *wq = &rq->wq;
- struct mlx5e_rx_wqe *wqe;
- __be16 wqe_ix_be;
- u16 wqe_ix;
-
- while (!mlx5_wq_ll_is_empty(wq)) {
- wqe_ix_be = *wq->tail_next;
- wqe_ix = be16_to_cpu(wqe_ix_be);
- wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
- rq->dealloc_wqe(rq, wqe_ix);
- mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
- &wqe->next.next_wqe_index);
- }
-}
-
#define RQ_CANNOT_POST(rq) \
- (!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \
- test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
+ (test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state) || \
+ test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
{
@@ -916,7 +905,7 @@
struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
int work_done = 0;
- if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state)))
+ if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state)))
return 0;
if (cq->decmprs_left)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 7b9d8a9..499487c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -70,6 +70,7 @@
u64 tx_queue_stopped;
u64 tx_queue_wake;
u64 tx_queue_dropped;
+ u64 tx_xmit_more;
u64 rx_wqe_err;
u64 rx_mpwqe_filler;
u64 rx_mpwqe_frag;
@@ -101,6 +102,7 @@
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_frag) },
@@ -298,6 +300,7 @@
/* commonly accessed in data path */
u64 packets;
u64 bytes;
+ u64 xmit_more;
u64 tso_packets;
u64 tso_bytes;
u64 tso_inner_packets;
@@ -324,6 +327,7 @@
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
};
#define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dc8b1cb..22cfc4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -170,7 +170,7 @@
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
struct flow_dissector_key_control *key =
skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
+ FLOW_DISSECTOR_KEY_CONTROL,
f->key);
addr_type = key->addr_type;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index e073bf59..988eca9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -375,6 +375,7 @@
sq->stats.packets++;
sq->stats.bytes += num_bytes;
+ sq->stats.xmit_more += skb->xmit_more;
return NETDEV_TX_OK;
dma_unmap_wqe_err:
@@ -394,35 +395,6 @@
return mlx5e_sq_xmit(sq, skb);
}
-void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
-{
- struct mlx5e_tx_wqe_info *wi;
- struct sk_buff *skb;
- u16 ci;
- int i;
-
- while (sq->cc != sq->pc) {
- ci = sq->cc & sq->wq.sz_m1;
- skb = sq->skb[ci];
- wi = &sq->wqe_info[ci];
-
- if (!skb) { /* nop */
- sq->cc++;
- continue;
- }
-
- for (i = 0; i < wi->num_dma; i++) {
- struct mlx5e_sq_dma *dma =
- mlx5e_dma_get(sq, sq->dma_fifo_cc++);
-
- mlx5e_tx_dma_unmap(sq->pdev, dma);
- }
-
- dev_kfree_skb_any(skb);
- sq->cc += wi->num_wqebbs;
- }
-}
-
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
{
struct mlx5e_sq *sq;
@@ -434,7 +406,7 @@
sq = container_of(cq, struct mlx5e_sq, cq);
- if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
+ if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state)))
return false;
npkts = 0;
@@ -512,11 +484,39 @@
netdev_tx_completed_queue(sq->txq, npkts, nbytes);
if (netif_tx_queue_stopped(sq->txq) &&
- mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM) &&
- likely(test_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state))) {
- netif_tx_wake_queue(sq->txq);
- sq->stats.wake++;
+ mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) {
+ netif_tx_wake_queue(sq->txq);
+ sq->stats.wake++;
}
return (i == MLX5E_TX_CQ_POLL_BUDGET);
}
+
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
+{
+ struct mlx5e_tx_wqe_info *wi;
+ struct sk_buff *skb;
+ u16 ci;
+ int i;
+
+ while (sq->cc != sq->pc) {
+ ci = sq->cc & sq->wq.sz_m1;
+ skb = sq->skb[ci];
+ wi = &sq->wqe_info[ci];
+
+ if (!skb) { /* nop */
+ sq->cc++;
+ continue;
+ }
+
+ for (i = 0; i < wi->num_dma; i++) {
+ struct mlx5e_sq_dma *dma =
+ mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+
+ mlx5e_tx_dma_unmap(sq->pdev, dma);
+ }
+
+ dev_kfree_skb_any(skb);
+ sq->cc += wi->num_wqebbs;
+ }
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 64ae2e8..9bf33bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -51,16 +51,18 @@
static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
{
+ struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq);
struct mlx5_wq_cyc *wq;
struct mlx5_cqe64 *cqe;
- struct mlx5e_sq *sq;
u16 sqcc;
+ if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state)))
+ return;
+
cqe = mlx5e_get_cqe(cq);
if (likely(!cqe))
return;
- sq = container_of(cq, struct mlx5e_sq, cq);
wq = &sq->wq;
/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index f6d6677..8b78f15 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1451,7 +1451,8 @@
esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
- if (vport_num) { /* Only VFs need ACLs for VST and spoofchk filtering */
+ /* Only VFs need ACLs for VST and spoofchk filtering */
+ if (vport_num && esw->mode == SRIOV_LEGACY) {
esw_vport_ingress_config(esw, vport);
esw_vport_egress_config(esw, vport);
}
@@ -1502,7 +1503,7 @@
*/
esw_vport_change_handle_locked(vport);
vport->enabled_events = 0;
- if (vport_num) {
+ if (vport_num && esw->mode == SRIOV_LEGACY) {
esw_vport_disable_egress_acl(esw, vport);
esw_vport_disable_ingress_acl(esw, vport);
}
@@ -1767,7 +1768,7 @@
vport, err);
mutex_lock(&esw->state_lock);
- if (evport->enabled)
+ if (evport->enabled && esw->mode == SRIOV_LEGACY)
err = esw_vport_ingress_config(esw, evport);
mutex_unlock(&esw->state_lock);
return err;
@@ -1839,7 +1840,7 @@
mutex_lock(&esw->state_lock);
evport->vlan = vlan;
evport->qos = qos;
- if (evport->enabled) {
+ if (evport->enabled && esw->mode == SRIOV_LEGACY) {
err = esw_vport_ingress_config(esw, evport);
if (err)
goto out;
@@ -1868,10 +1869,11 @@
mutex_lock(&esw->state_lock);
pschk = evport->spoofchk;
evport->spoofchk = spoofchk;
- if (evport->enabled)
+ if (evport->enabled && esw->mode == SRIOV_LEGACY) {
err = esw_vport_ingress_config(esw, evport);
- if (err)
- evport->spoofchk = pschk;
+ if (err)
+ evport->spoofchk = pschk;
+ }
mutex_unlock(&esw->state_lock);
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index c0b0560..a961409 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -174,6 +174,7 @@
void *priv_data;
struct list_head vport_sqs_list;
bool valid;
+ u8 hw_id[ETH_ALEN];
};
struct mlx5_esw_offload {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a357e8e..3dc83a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -113,7 +113,7 @@
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport_num = vport;
- flow_rule = mlx5_add_flow_rule(esw->fdb_table.fdb, spec,
+ flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec,
MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
0, &dest);
if (IS_ERR(flow_rule))
@@ -535,7 +535,7 @@
esw_destroy_offloads_fdb_table(esw);
}
-static int mlx5_esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
+static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
{
switch (mode) {
case DEVLINK_ESWITCH_MODE_LEGACY:
@@ -551,6 +551,22 @@
return 0;
}
+static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
+{
+ switch (mlx5_mode) {
+ case SRIOV_LEGACY:
+ *mode = DEVLINK_ESWITCH_MODE_LEGACY;
+ break;
+ case SRIOV_OFFLOADS:
+ *mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
{
struct mlx5_core_dev *dev;
@@ -566,7 +582,7 @@
if (cur_mlx5_mode == SRIOV_NONE)
return -EOPNOTSUPP;
- if (mlx5_esw_mode_from_devlink(mode, &mlx5_mode))
+ if (esw_mode_from_devlink(mode, &mlx5_mode))
return -EINVAL;
if (cur_mlx5_mode == mlx5_mode)
@@ -592,9 +608,7 @@
if (dev->priv.eswitch->mode == SRIOV_NONE)
return -EOPNOTSUPP;
- *mode = dev->priv.eswitch->mode;
-
- return 0;
+ return esw_mode_to_devlink(dev->priv.eswitch->mode, mode);
}
void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 75bb8c8..3d6c1f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -80,7 +80,7 @@
LEFTOVERS_NUM_PRIOS)
#define ETHTOOL_PRIO_NUM_LEVELS 1
-#define ETHTOOL_NUM_PRIOS 10
+#define ETHTOOL_NUM_PRIOS 11
#define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
/* Vlan, mac, ttc, aRFS */
#define KERNEL_NIC_PRIO_NUM_LEVELS 4
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index c2877e9..3a9195b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -126,12 +126,21 @@
for (node = &first->node; node; node = rb_next(node)) {
struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node);
struct mlx5_fc_cache *c = &counter->cache;
+ u64 packets;
+ u64 bytes;
if (counter->id > last_id)
break;
mlx5_cmd_fc_bulk_get(dev, b,
- counter->id, &c->packets, &c->bytes);
+ counter->id, &packets, &bytes);
+
+ if (c->packets == packets)
+ continue;
+
+ c->packets = packets;
+ c->bytes = bytes;
+ c->lastuse = jiffies;
}
out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4f491d4..2385bae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1420,36 +1420,12 @@
dev_info(&pdev->dev, "%s was called\n", __func__);
mlx5_enter_error_state(dev);
mlx5_unload_one(dev, priv);
+ pci_save_state(pdev);
mlx5_pci_disable_device(dev);
return state == pci_channel_io_perm_failure ?
PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
}
-static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
-{
- struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
- int err = 0;
-
- dev_info(&pdev->dev, "%s was called\n", __func__);
-
- err = mlx5_pci_enable_device(dev);
- if (err) {
- dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
- , __func__, err);
- return PCI_ERS_RESULT_DISCONNECT;
- }
- pci_set_master(pdev);
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
-
- return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
-}
-
-void mlx5_disable_device(struct mlx5_core_dev *dev)
-{
- mlx5_pci_err_detected(dev->pdev, 0);
-}
-
/* wait for the device to show vital signs by waiting
* for the health counter to start counting.
*/
@@ -1477,6 +1453,36 @@
return -ETIMEDOUT;
}
+static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
+{
+ struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+ int err;
+
+ dev_info(&pdev->dev, "%s was called\n", __func__);
+
+ err = mlx5_pci_enable_device(dev);
+ if (err) {
+ dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
+ , __func__, err);
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ pci_set_master(pdev);
+ pci_restore_state(pdev);
+
+ if (wait_vital(pdev)) {
+ dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ return PCI_ERS_RESULT_RECOVERED;
+}
+
+void mlx5_disable_device(struct mlx5_core_dev *dev)
+{
+ mlx5_pci_err_detected(dev->pdev, 0);
+}
+
static void mlx5_pci_resume(struct pci_dev *pdev)
{
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
@@ -1485,13 +1491,6 @@
dev_info(&pdev->dev, "%s was called\n", __func__);
- pci_save_state(pdev);
- err = wait_vital(pdev);
- if (err) {
- dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
- return;
- }
-
err = mlx5_load_one(dev, priv);
if (err)
dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n"
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index f33b997..af371a8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -56,6 +56,7 @@
#define MLXSW_PORT_PHY_BITS_MASK (MLXSW_PORT_MAX_PHY_PORTS - 1)
#define MLXSW_PORT_CPU_PORT 0x0
+#define MLXSW_PORT_ROUTER_PORT (MLXSW_PORT_MAX_PHY_PORTS + 2)
#define MLXSW_PORT_DONT_CARE (MLXSW_PORT_MAX_PORTS)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 1f81689..7291f2c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3324,6 +3324,39 @@
return mlxsw_sp_fid_find(mlxsw_sp, fid);
}
+static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
+{
+ return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
+ MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
+}
+
+static u16 mlxsw_sp_flood_table_index_get(u16 fid)
+{
+ return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
+}
+
+static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
+ bool set)
+{
+ enum mlxsw_flood_table_type table_type;
+ char *sftr_pl;
+ u16 index;
+ int err;
+
+ sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
+ if (!sftr_pl)
+ return -ENOMEM;
+
+ table_type = mlxsw_sp_flood_table_type_get(fid);
+ index = mlxsw_sp_flood_table_index_get(fid);
+ mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, index, table_type,
+ 1, MLXSW_PORT_ROUTER_PORT, set);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
+
+ kfree(sftr_pl);
+ return err;
+}
+
static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
{
if (mlxsw_sp_fid_is_vfid(fid))
@@ -3360,10 +3393,14 @@
if (rif == MLXSW_SP_RIF_MAX)
return -ERANGE;
- err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
+ err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
if (err)
return err;
+ err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
+ if (err)
+ goto err_rif_bridge_op;
+
err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
if (err)
goto err_rif_fdb_op;
@@ -3385,6 +3422,8 @@
mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
err_rif_fdb_op:
mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
+err_rif_bridge_op:
+ mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
return err;
}
@@ -3404,6 +3443,8 @@
mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
+ mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+
netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 237418a..953b214 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -717,22 +717,18 @@
u8 local_port = mlxsw_sp_port->local_port;
u8 pg_buff = tc_index;
enum mlxsw_reg_sbxx_dir dir = pool_type;
- u8 pool = pool_index;
+ u8 pool = pool_get(pool_index);
u32 max_buff;
int err;
+ if (dir != dir_get(pool_index))
+ return -EINVAL;
+
err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir,
threshold, &max_buff);
if (err)
return err;
- if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS) {
- if (pool < MLXSW_SP_SB_POOL_COUNT)
- return -EINVAL;
- pool -= MLXSW_SP_SB_POOL_COUNT;
- } else if (pool >= MLXSW_SP_SB_POOL_COUNT) {
- return -EINVAL;
- }
return mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, pg_buff, dir,
0, max_buff, pool);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 90bb93b..917ddd1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -657,7 +657,7 @@
return 0;
}
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+ r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
if (WARN_ON(!r))
return -EINVAL;
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 4d4ecba..8e13ec8 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -475,14 +475,6 @@
mac[5] = tmp >> 8;
}
-static void __lpc_eth_clock_enable(struct netdata_local *pldat, bool enable)
-{
- if (enable)
- clk_prepare_enable(pldat->clk);
- else
- clk_disable_unprepare(pldat->clk);
-}
-
static void __lpc_params_setup(struct netdata_local *pldat)
{
u32 tmp;
@@ -1056,7 +1048,7 @@
writel(0, LPC_ENET_MAC2(pldat->net_base));
spin_unlock_irqrestore(&pldat->lock, flags);
- __lpc_eth_clock_enable(pldat, false);
+ clk_disable_unprepare(pldat->clk);
return 0;
}
@@ -1197,11 +1189,14 @@
static int lpc_eth_open(struct net_device *ndev)
{
struct netdata_local *pldat = netdev_priv(ndev);
+ int ret;
if (netif_msg_ifup(pldat))
dev_dbg(&pldat->pdev->dev, "enabling %s\n", ndev->name);
- __lpc_eth_clock_enable(pldat, true);
+ ret = clk_prepare_enable(pldat->clk);
+ if (ret)
+ return ret;
/* Suspended PHY makes LPC ethernet core block, so resume now */
phy_resume(ndev->phydev);
@@ -1320,7 +1315,9 @@
}
/* Enable network clock */
- __lpc_eth_clock_enable(pldat, true);
+ ret = clk_prepare_enable(pldat->clk);
+ if (ret)
+ goto err_out_clk_put;
/* Map IO space */
pldat->net_base = ioremap(res->start, resource_size(res));
@@ -1454,6 +1451,7 @@
iounmap(pldat->net_base);
err_out_disable_clocks:
clk_disable_unprepare(pldat->clk);
+err_out_clk_put:
clk_put(pldat->clk);
err_out_free_dev:
free_netdev(ndev);
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 35e5377..45ab746 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -561,9 +561,18 @@
static inline u8 qed_concrete_to_sw_fid(struct qed_dev *cdev,
u32 concrete_fid)
{
+ u8 vfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_VFID);
u8 pfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_PFID);
+ u8 vf_valid = GET_FIELD(concrete_fid,
+ PXP_CONCRETE_FID_VFVALID);
+ u8 sw_fid;
- return pfid;
+ if (vf_valid)
+ sw_fid = vfid + MAX_NUM_PFS;
+ else
+ sw_fid = pfid;
+
+ return sw_fid;
}
#define PURE_LB_TC 8
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index e4bd02e..a6eb6af 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -722,11 +722,14 @@
txq->tx_db.data.bd_prod =
cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl));
- if (!skb->xmit_more || netif_tx_queue_stopped(netdev_txq))
+ if (!skb->xmit_more || netif_xmit_stopped(netdev_txq))
qede_update_tx_producer(txq);
if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl)
< (MAX_SKB_FRAGS + 1))) {
+ if (skb->xmit_more)
+ qede_update_tx_producer(txq);
+
netif_tx_stop_queue(netdev_txq);
DP_VERBOSE(edev, NETIF_MSG_TX_QUEUED,
"Stop queue was called\n");
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index deae10d..5297bf7 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -467,8 +467,8 @@
unsigned int rx_tail = cp->rx_tail;
int rx;
-rx_status_loop:
rx = 0;
+rx_status_loop:
cpw16(IntrStatus, cp_rx_intr_mask);
while (rx < budget) {
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index f658fee..e00a669 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1517,13 +1517,14 @@
}
#if BITS_PER_LONG == 64
+ BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 2);
mask[0] = raw_mask[0];
mask[1] = raw_mask[1];
#else
+ BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 3);
mask[0] = raw_mask[0] & 0xffffffff;
mask[1] = raw_mask[0] >> 32;
mask[2] = raw_mask[1] & 0xffffffff;
- mask[3] = raw_mask[1] >> 32;
#endif
}
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 726b80f..503a3b6 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2275,6 +2275,13 @@
if (pd) {
memcpy(&lp->cfg, pd, sizeof(lp->cfg));
lp->io_shift = SMC91X_IO_SHIFT(lp->cfg.flags);
+
+ if (!SMC_8BIT(lp) && !SMC_16BIT(lp)) {
+ dev_err(&pdev->dev,
+ "at least one of 8-bit or 16-bit access support is required.\n");
+ ret = -ENXIO;
+ goto out_free_netdev;
+ }
}
#if IS_BUILTIN(CONFIG_OF)
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index 1a55c79..e17671c 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -37,6 +37,27 @@
#include <linux/smc91x.h>
/*
+ * Any 16-bit access is performed with two 8-bit accesses if the hardware
+ * can't do it directly. Most registers are 16-bit so those are mandatory.
+ */
+#define SMC_outw_b(x, a, r) \
+ do { \
+ unsigned int __val16 = (x); \
+ unsigned int __reg = (r); \
+ SMC_outb(__val16, a, __reg); \
+ SMC_outb(__val16 >> 8, a, __reg + (1 << SMC_IO_SHIFT)); \
+ } while (0)
+
+#define SMC_inw_b(a, r) \
+ ({ \
+ unsigned int __val16; \
+ unsigned int __reg = r; \
+ __val16 = SMC_inb(a, __reg); \
+ __val16 |= SMC_inb(a, __reg + (1 << SMC_IO_SHIFT)) << 8; \
+ __val16; \
+ })
+
+/*
* Define your architecture specific bus configuration parameters here.
*/
@@ -55,10 +76,30 @@
#define SMC_IO_SHIFT (lp->io_shift)
#define SMC_inb(a, r) readb((a) + (r))
-#define SMC_inw(a, r) readw((a) + (r))
+#define SMC_inw(a, r) \
+ ({ \
+ unsigned int __smc_r = r; \
+ SMC_16BIT(lp) ? readw((a) + __smc_r) : \
+ SMC_8BIT(lp) ? SMC_inw_b(a, __smc_r) : \
+ ({ BUG(); 0; }); \
+ })
+
#define SMC_inl(a, r) readl((a) + (r))
#define SMC_outb(v, a, r) writeb(v, (a) + (r))
+#define SMC_outw(v, a, r) \
+ do { \
+ unsigned int __v = v, __smc_r = r; \
+ if (SMC_16BIT(lp)) \
+ __SMC_outw(__v, a, __smc_r); \
+ else if (SMC_8BIT(lp)) \
+ SMC_outw_b(__v, a, __smc_r); \
+ else \
+ BUG(); \
+ } while (0)
+
#define SMC_outl(v, a, r) writel(v, (a) + (r))
+#define SMC_insb(a, r, p, l) readsb((a) + (r), p, l)
+#define SMC_outsb(a, r, p, l) writesb((a) + (r), p, l)
#define SMC_insw(a, r, p, l) readsw((a) + (r), p, l)
#define SMC_outsw(a, r, p, l) writesw((a) + (r), p, l)
#define SMC_insl(a, r, p, l) readsl((a) + (r), p, l)
@@ -66,7 +107,7 @@
#define SMC_IRQ_FLAGS (-1) /* from resource */
/* We actually can't write halfwords properly if not word aligned */
-static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg)
+static inline void __SMC_outw(u16 val, void __iomem *ioaddr, int reg)
{
if ((machine_is_mainstone() || machine_is_stargate2() ||
machine_is_pxa_idp()) && reg & 2) {
@@ -416,24 +457,8 @@
#if ! SMC_CAN_USE_16BIT
-/*
- * Any 16-bit access is performed with two 8-bit accesses if the hardware
- * can't do it directly. Most registers are 16-bit so those are mandatory.
- */
-#define SMC_outw(x, ioaddr, reg) \
- do { \
- unsigned int __val16 = (x); \
- SMC_outb( __val16, ioaddr, reg ); \
- SMC_outb( __val16 >> 8, ioaddr, reg + (1 << SMC_IO_SHIFT));\
- } while (0)
-#define SMC_inw(ioaddr, reg) \
- ({ \
- unsigned int __val16; \
- __val16 = SMC_inb( ioaddr, reg ); \
- __val16 |= SMC_inb( ioaddr, reg + (1 << SMC_IO_SHIFT)) << 8; \
- __val16; \
- })
-
+#define SMC_outw(x, ioaddr, reg) SMC_outw_b(x, ioaddr, reg)
+#define SMC_inw(ioaddr, reg) SMC_inw_b(ioaddr, reg)
#define SMC_insw(a, r, p, l) BUG()
#define SMC_outsw(a, r, p, l) BUG()
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 9f159a7..5a3941b 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -1622,13 +1622,7 @@
DWCEQOS_MMC_CTRL_RSTONRD);
dwceqos_enable_mmc_interrupt(lp);
- /* Enable Interrupts */
- dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE,
- DWCEQOS_DMA_CH0_IE_NIE |
- DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE |
- DWCEQOS_DMA_CH0_IE_AIE |
- DWCEQOS_DMA_CH0_IE_FBEE);
-
+ dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, 0);
dwceqos_write(lp, REG_DWCEQOS_MAC_IE, 0);
dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, DWCEQOS_MAC_CFG_IPC |
@@ -1905,6 +1899,15 @@
netif_start_queue(ndev);
tasklet_enable(&lp->tx_bdreclaim_tasklet);
+ /* Enable Interrupts -- do this only after we enable NAPI and the
+ * tasklet.
+ */
+ dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE,
+ DWCEQOS_DMA_CH0_IE_NIE |
+ DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE |
+ DWCEQOS_DMA_CH0_IE_AIE |
+ DWCEQOS_DMA_CH0_IE_FBEE);
+
return 0;
}
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 7452b5f..7108c68 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1987,7 +1987,7 @@
if ((readl(nic->regs + FPGA_VER) & 0xFFF) >= 378) {
err = pci_enable_msi(pdev);
if (err)
- pr_err("Can't eneble msi. error is %d\n", err);
+ pr_err("Can't enable msi. error is %d\n", err);
else
nic->irq_type = IRQ_MSI;
} else
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 3cee84a..93dc10b 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -1131,11 +1131,13 @@
lp->rx_ping_pong = get_bool(ofdev, "xlnx,rx-ping-pong");
mac_address = of_get_mac_address(ofdev->dev.of_node);
- if (mac_address)
+ if (mac_address) {
/* Set the MAC address. */
memcpy(ndev->dev_addr, mac_address, ETH_ALEN);
- else
- dev_warn(dev, "No MAC address found\n");
+ } else {
+ dev_warn(dev, "No MAC address found, using random\n");
+ eth_hw_addr_random(ndev);
+ }
/* Clear the Tx CSR's in case this is a restart */
__raw_writel(0, lp->base_addr + XEL_TSR_OFFSET);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 053e879..885ac9c 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -964,7 +964,7 @@
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
- .resume = genphy_resume,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8873MLL,
.phy_id_mask = MICREL_PHY_ID_MASK,
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index c5dc2c36..c6f6683 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -722,8 +722,10 @@
int phy_start_interrupts(struct phy_device *phydev)
{
atomic_set(&phydev->irq_disable, 0);
- if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt",
- phydev) < 0) {
+ if (request_irq(phydev->irq, phy_interrupt,
+ IRQF_SHARED,
+ "phy_interrupt",
+ phydev) < 0) {
pr_warn("%s: Can't get IRQ %d (PHY)\n",
phydev->mdio.bus->name, phydev->irq);
phydev->irq = PHY_POLL;
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index cdb19b3..b228bea 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -14,9 +14,23 @@
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/filter.h>
#include <linux/if_team.h>
+static rx_handler_result_t lb_receive(struct team *team, struct team_port *port,
+ struct sk_buff *skb)
+{
+ if (unlikely(skb->protocol == htons(ETH_P_SLOW))) {
+ /* LACPDU packets should go to exact delivery */
+ const unsigned char *dest = eth_hdr(skb)->h_dest;
+
+ if (is_link_local_ether_addr(dest) && dest[5] == 0x02)
+ return RX_HANDLER_EXACT;
+ }
+ return RX_HANDLER_ANOTHER;
+}
+
struct lb_priv;
typedef struct team_port *lb_select_tx_port_func_t(struct team *,
@@ -652,6 +666,7 @@
.port_enter = lb_port_enter,
.port_leave = lb_port_leave,
.port_disabled = lb_port_disabled,
+ .receive = lb_receive,
.transmit = lb_transmit,
};
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9c8b5bc..6f9df37 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -894,11 +894,7 @@
if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
goto drop;
- if (skb->sk && sk_fullsock(skb->sk)) {
- sock_tx_timestamp(skb->sk, skb->sk->sk_tsflags,
- &skb_shinfo(skb)->tx_flags);
- sw_tx_timestamp(skb);
- }
+ skb_tx_timestamp(skb);
/* Orphan the skb - required as we might hang on to it
* for indefinite time.
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index 770212b..528b9c9 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -1009,6 +1009,7 @@
struct net_device *netdev;
const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
int result = 0;
+ int rv = -EIO;
dev_dbg(dev,
"Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n",
@@ -1029,6 +1030,7 @@
kaweth = netdev_priv(netdev);
kaweth->dev = udev;
kaweth->net = netdev;
+ kaweth->intf = intf;
spin_lock_init(&kaweth->device_lock);
init_waitqueue_head(&kaweth->term_wait);
@@ -1048,6 +1050,10 @@
/* Download the firmware */
dev_info(dev, "Downloading firmware...\n");
kaweth->firmware_buf = (__u8 *)__get_free_page(GFP_KERNEL);
+ if (!kaweth->firmware_buf) {
+ rv = -ENOMEM;
+ goto err_free_netdev;
+ }
if ((result = kaweth_download_firmware(kaweth,
"kaweth/new_code.bin",
100,
@@ -1139,8 +1145,6 @@
dev_dbg(dev, "Initializing net device.\n");
- kaweth->intf = intf;
-
kaweth->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
if (!kaweth->tx_urb)
goto err_free_netdev;
@@ -1204,7 +1208,7 @@
err_free_netdev:
free_netdev(netdev);
- return -EIO;
+ return rv;
}
/****************************************************************
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index c68fe49..4244b9d 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -914,7 +914,9 @@
{
struct Vmxnet3_TxDataDesc *tdd;
- tdd = tq->data_ring.base + tq->tx_ring.next2fill;
+ tdd = (struct Vmxnet3_TxDataDesc *)((u8 *)tq->data_ring.base +
+ tq->tx_ring.next2fill *
+ tq->txdata_desc_size);
memcpy(tdd->data, skb->data, ctx->copy_size);
netdev_dbg(adapter->netdev,
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 74fc030..7dc37a0 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.9.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.a.0-k"
/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040900
+#define VMXNET3_DRIVER_VERSION_NUM 0x01040a00
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7ff2e82..2feacc7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -81,10 +81,12 @@
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state)
{
- enum nvme_ctrl_state old_state = ctrl->state;
+ enum nvme_ctrl_state old_state;
bool changed = false;
spin_lock_irq(&ctrl->lock);
+
+ old_state = ctrl->state;
switch (new_state) {
case NVME_CTRL_LIVE:
switch (old_state) {
@@ -140,11 +142,12 @@
default:
break;
}
- spin_unlock_irq(&ctrl->lock);
if (changed)
ctrl->state = new_state;
+ spin_unlock_irq(&ctrl->lock);
+
return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
@@ -608,7 +611,7 @@
ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
NVME_QID_ANY, 0, 0);
- if (ret >= 0)
+ if (ret >= 0 && result)
*result = le32_to_cpu(cqe.result);
return ret;
}
@@ -628,7 +631,7 @@
ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
NVME_QID_ANY, 0, 0);
- if (ret >= 0)
+ if (ret >= 0 && result)
*result = le32_to_cpu(cqe.result);
return ret;
}
diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c
index 5f4a2e0..add6623 100644
--- a/drivers/pci/host-bridge.c
+++ b/drivers/pci/host-bridge.c
@@ -44,6 +44,7 @@
bridge->release_fn = release_fn;
bridge->release_data = release_data;
}
+EXPORT_SYMBOL_GPL(pci_set_host_bridge_release);
void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region,
struct resource *res)
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index eafa613..98f1222 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1069,7 +1069,7 @@
nvec = maxvec;
for (;;) {
- if (!(flags & PCI_IRQ_NOAFFINITY)) {
+ if (flags & PCI_IRQ_AFFINITY) {
dev->irq_affinity = irq_create_affinity_mask(&nvec);
if (nvec < minvec)
return -ENOSPC;
@@ -1105,7 +1105,7 @@
**/
int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
{
- return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY);
+ return __pci_enable_msi_range(dev, minvec, maxvec, 0);
}
EXPORT_SYMBOL(pci_enable_msi_range);
@@ -1120,7 +1120,7 @@
return -ERANGE;
for (;;) {
- if (!(flags & PCI_IRQ_NOAFFINITY)) {
+ if (flags & PCI_IRQ_AFFINITY) {
dev->irq_affinity = irq_create_affinity_mask(&nvec);
if (nvec < minvec)
return -ENOSPC;
@@ -1160,8 +1160,7 @@
int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
int minvec, int maxvec)
{
- return __pci_enable_msix_range(dev, entries, minvec, maxvec,
- PCI_IRQ_NOAFFINITY);
+ return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0);
}
EXPORT_SYMBOL(pci_enable_msix_range);
@@ -1187,22 +1186,25 @@
{
int vecs = -ENOSPC;
- if (!(flags & PCI_IRQ_NOMSIX)) {
+ if (flags & PCI_IRQ_MSIX) {
vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs,
flags);
if (vecs > 0)
return vecs;
}
- if (!(flags & PCI_IRQ_NOMSI)) {
+ if (flags & PCI_IRQ_MSI) {
vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags);
if (vecs > 0)
return vecs;
}
/* use legacy irq if allowed */
- if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1)
+ if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) {
+ pci_intx(dev, 1);
return 1;
+ }
+
return vecs;
}
EXPORT_SYMBOL(pci_alloc_irq_vectors);
diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c
index f99b183..374a802 100644
--- a/drivers/platform/olpc/olpc-ec.c
+++ b/drivers/platform/olpc/olpc-ec.c
@@ -1,6 +1,8 @@
/*
* Generic driver for the OLPC Embedded Controller.
*
+ * Author: Andres Salomon <dilinger@queued.net>
+ *
* Copyright (C) 2011-2012 One Laptop per Child Foundation.
*
* Licensed under the GPL v2 or later.
@@ -12,7 +14,7 @@
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
-#include <linux/module.h>
+#include <linux/init.h>
#include <linux/list.h>
#include <linux/olpc-ec.h>
#include <asm/olpc.h>
@@ -326,8 +328,4 @@
{
return platform_driver_register(&olpc_ec_plat_driver);
}
-
arch_initcall(olpc_ec_init_module);
-
-MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c
index 63b371d..91ae585 100644
--- a/drivers/platform/x86/intel_pmic_gpio.c
+++ b/drivers/platform/x86/intel_pmic_gpio.c
@@ -1,6 +1,8 @@
/* Moorestown PMIC GPIO (access through IPC) driver
* Copyright (c) 2008 - 2009, Intel Corporation.
*
+ * Author: Alek Du <alek.du@intel.com>
+ *
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
@@ -21,7 +23,6 @@
#define pr_fmt(fmt) "%s: " fmt, __func__
-#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
@@ -322,9 +323,4 @@
{
return platform_driver_register(&platform_pmic_gpio_driver);
}
-
subsys_initcall(platform_pmic_gpio_init);
-
-MODULE_AUTHOR("Alek Du <alek.du@intel.com>");
-MODULE_DESCRIPTION("Intel Moorestown PMIC GPIO driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 3788ed7..a32b417 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -740,12 +740,22 @@
}
/* Bind cpufreq callbacks to thermal cooling device ops */
+
static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
.get_max_state = cpufreq_get_max_state,
.get_cur_state = cpufreq_get_cur_state,
.set_cur_state = cpufreq_set_cur_state,
};
+static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = {
+ .get_max_state = cpufreq_get_max_state,
+ .get_cur_state = cpufreq_get_cur_state,
+ .set_cur_state = cpufreq_set_cur_state,
+ .get_requested_power = cpufreq_get_requested_power,
+ .state2power = cpufreq_state2power,
+ .power2state = cpufreq_power2state,
+};
+
/* Notifier for cpufreq policy change */
static struct notifier_block thermal_cpufreq_notifier_block = {
.notifier_call = cpufreq_thermal_notifier,
@@ -795,6 +805,7 @@
struct cpumask temp_mask;
unsigned int freq, i, num_cpus;
int ret;
+ struct thermal_cooling_device_ops *cooling_ops;
cpumask_and(&temp_mask, clip_cpus, cpu_online_mask);
policy = cpufreq_cpu_get(cpumask_first(&temp_mask));
@@ -850,10 +861,6 @@
cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
if (capacitance) {
- cpufreq_cooling_ops.get_requested_power =
- cpufreq_get_requested_power;
- cpufreq_cooling_ops.state2power = cpufreq_state2power;
- cpufreq_cooling_ops.power2state = cpufreq_power2state;
cpufreq_dev->plat_get_static_power = plat_static_func;
ret = build_dyn_power_table(cpufreq_dev, capacitance);
@@ -861,6 +868,10 @@
cool_dev = ERR_PTR(ret);
goto free_table;
}
+
+ cooling_ops = &cpufreq_power_cooling_ops;
+ } else {
+ cooling_ops = &cpufreq_cooling_ops;
}
ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
@@ -885,7 +896,7 @@
cpufreq_dev->id);
cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
- &cpufreq_cooling_ops);
+ cooling_ops);
if (IS_ERR(cool_dev))
goto remove_idr;
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index c5547bd..e473548 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -471,8 +471,6 @@
static int imx_thermal_probe(struct platform_device *pdev)
{
- const struct of_device_id *of_id =
- of_match_device(of_imx_thermal_match, &pdev->dev);
struct imx_thermal_data *data;
struct regmap *map;
int measure_freq;
@@ -490,7 +488,7 @@
}
data->tempmon = map;
- data->socdata = of_id->data;
+ data->socdata = of_device_get_match_data(&pdev->dev);
/* make sure the IRQ flag is clear before enabling irq on i.MX6SX */
if (data->socdata->version == TEMPMON_IMX6SX) {
diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c
index a578cd2..1891f34 100644
--- a/drivers/thermal/int340x_thermal/int3406_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3406_thermal.c
@@ -225,7 +225,6 @@
.remove = int3406_thermal_remove,
.driver = {
.name = "int3406 thermal",
- .owner = THIS_MODULE,
.acpi_match_table = int3406_thermal_match,
},
};
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 9d6320e..6e29d05 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -88,7 +88,7 @@
struct scatterlist *tvc_prot_sgl;
struct page **tvc_upages;
/* Pointer to response header iovec */
- struct iovec *tvc_resp_iov;
+ struct iovec tvc_resp_iov;
/* Pointer to vhost_scsi for our device */
struct vhost_scsi *tvc_vhost;
/* Pointer to vhost_virtqueue for the cmd */
@@ -547,7 +547,7 @@
memcpy(v_rsp.sense, cmd->tvc_sense_buf,
se_cmd->scsi_sense_length);
- iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov,
+ iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov,
cmd->tvc_in_iovs, sizeof(v_rsp));
ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
if (likely(ret == sizeof(v_rsp))) {
@@ -1044,7 +1044,7 @@
}
cmd->tvc_vhost = vs;
cmd->tvc_vq = vq;
- cmd->tvc_resp_iov = &vq->iov[out];
+ cmd->tvc_resp_iov = vq->iov[out];
cmd->tvc_in_iovs = in;
pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 7487971..c1010f01 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -316,7 +316,7 @@
rc = -ENOMEM;
goto out;
}
- } else {
+ } else if (msg_type == XS_TRANSACTION_END) {
list_for_each_entry(trans, &u->transactions, list)
if (trans->handle.id == u->u.msg.tx_id)
break;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c3cdde8..08ae993 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -249,7 +249,8 @@
* thaw_bdev drops it.
*/
sb = get_super(bdev);
- drop_super(sb);
+ if (sb)
+ drop_super(sb);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return sb;
}
@@ -646,7 +647,7 @@
{
struct dentry *dent;
dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
- if (dent)
+ if (!IS_ERR(dent))
dent->d_sb->s_iflags |= SB_I_CGROUPWB;
return dent;
}
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 2b88439..455a6b2 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -589,6 +589,7 @@
list_del(&ref2->list);
kmem_cache_free(btrfs_prelim_ref_cache, ref2);
+ cond_resched();
}
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2fe8f89..eff3993 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1028,6 +1028,7 @@
struct btrfs_workqueue *qgroup_rescan_workers;
struct completion qgroup_rescan_completion;
struct btrfs_work qgroup_rescan_work;
+ bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */
/* filesystem state */
unsigned long fs_state;
@@ -1079,6 +1080,8 @@
struct list_head pinned_chunks;
int creating_free_space_tree;
+ /* Used to record internally whether fs has been frozen */
+ int fs_frozen;
};
struct btrfs_subvolume_writers {
@@ -2578,7 +2581,7 @@
struct btrfs_root *root,
u64 root_objectid, u64 owner, u64 offset,
struct btrfs_key *ins);
-int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
+int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
u64 min_alloc_size, u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index d9ddcfc..ac02e04 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -541,7 +541,6 @@
struct btrfs_delayed_ref_head *existing;
struct btrfs_delayed_ref_head *head_ref = NULL;
struct btrfs_delayed_ref_root *delayed_refs;
- struct btrfs_qgroup_extent_record *qexisting;
int count_mod = 1;
int must_insert_reserved = 0;
@@ -606,10 +605,8 @@
qrecord->num_bytes = num_bytes;
qrecord->old_roots = NULL;
- qexisting = btrfs_qgroup_insert_dirty_extent(fs_info,
- delayed_refs,
- qrecord);
- if (qexisting)
+ if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info,
+ delayed_refs, qrecord))
kfree(qrecord);
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 59febfb..54bc8c7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -559,8 +559,29 @@
u32 nritems = btrfs_header_nritems(leaf);
int slot;
- if (nritems == 0)
+ if (nritems == 0) {
+ struct btrfs_root *check_root;
+
+ key.objectid = btrfs_header_owner(leaf);
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ check_root = btrfs_get_fs_root(root->fs_info, &key, false);
+ /*
+ * The only reason we also check NULL here is that during
+ * open_ctree() some roots has not yet been set up.
+ */
+ if (!IS_ERR_OR_NULL(check_root)) {
+ /* if leaf is the root, then it's fine */
+ if (leaf->start !=
+ btrfs_root_bytenr(&check_root->root_item)) {
+ CORRUPT("non-root leaf's nritems is 0",
+ leaf, root, 0);
+ return -EIO;
+ }
+ }
return 0;
+ }
/* Check the 0 item */
if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
@@ -612,6 +633,19 @@
return 0;
}
+static int check_node(struct btrfs_root *root, struct extent_buffer *node)
+{
+ unsigned long nr = btrfs_header_nritems(node);
+
+ if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) {
+ btrfs_crit(root->fs_info,
+ "corrupt node: block %llu root %llu nritems %lu",
+ node->start, root->objectid, nr);
+ return -EIO;
+ }
+ return 0;
+}
+
static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
@@ -682,6 +716,9 @@
ret = -EIO;
}
+ if (found_level > 0 && check_node(root, eb))
+ ret = -EIO;
+
if (!ret)
set_extent_buffer_uptodate(eb);
err:
@@ -1618,8 +1655,8 @@
return ret;
}
-static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
- u64 root_id)
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id)
{
struct btrfs_root *root;
@@ -2298,6 +2335,7 @@
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
fs_info->qgroup_ulist = NULL;
+ fs_info->qgroup_rescan_running = false;
mutex_init(&fs_info->qgroup_rescan_lock);
}
@@ -2624,6 +2662,7 @@
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
+ fs_info->fs_frozen = 0;
fs_info->sb = sb;
fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
fs_info->metadata_ratio = 0;
@@ -3739,8 +3778,15 @@
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
btrfs_free_log(NULL, root);
+ if (root->reloc_root) {
+ free_extent_buffer(root->reloc_root->node);
+ free_extent_buffer(root->reloc_root->commit_root);
+ btrfs_put_fs_root(root->reloc_root);
+ root->reloc_root = NULL;
+ }
+ }
if (root->free_ino_pinned)
__btrfs_remove_free_space_cache(root->free_ino_pinned);
@@ -3851,7 +3897,7 @@
smp_mb();
/* wait for the qgroup rescan worker to stop */
- btrfs_qgroup_wait_for_completion(fs_info);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index b3207a0e..f19a982 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -68,6 +68,8 @@
struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
struct btrfs_key *location);
int btrfs_init_fs_root(struct btrfs_root *root);
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id);
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 61b494e..0450dc4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -60,21 +60,6 @@
CHUNK_ALLOC_FORCE = 2,
};
-/*
- * Control how reservations are dealt with.
- *
- * RESERVE_FREE - freeing a reservation.
- * RESERVE_ALLOC - allocating space and we need to update bytes_may_use for
- * ENOSPC accounting
- * RESERVE_ALLOC_NO_ACCOUNT - allocating space and we should not update
- * bytes_may_use as the ENOSPC accounting is done elsewhere
- */
-enum {
- RESERVE_FREE = 0,
- RESERVE_ALLOC = 1,
- RESERVE_ALLOC_NO_ACCOUNT = 2,
-};
-
static int update_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr,
u64 num_bytes, int alloc);
@@ -104,9 +89,10 @@
struct btrfs_key *key);
static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
int dump_block_groups);
-static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve,
- int delalloc);
+static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 ram_bytes, u64 num_bytes, int delalloc);
+static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 num_bytes, int delalloc);
static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
u64 num_bytes);
int btrfs_pin_extent(struct btrfs_root *root,
@@ -3501,7 +3487,6 @@
dcs = BTRFS_DC_SETUP;
else if (ret == -ENOSPC)
set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags);
- btrfs_free_reserved_data_space(inode, 0, num_pages);
out_put:
iput(inode);
@@ -4472,6 +4457,15 @@
}
}
+/*
+ * If force is CHUNK_ALLOC_FORCE:
+ * - return 1 if it successfully allocates a chunk,
+ * - return errors including -ENOSPC otherwise.
+ * If force is NOT CHUNK_ALLOC_FORCE:
+ * - return 0 if it doesn't need to allocate a new chunk,
+ * - return 1 if it successfully allocates a chunk,
+ * - return errors including -ENOSPC otherwise.
+ */
static int do_chunk_alloc(struct btrfs_trans_handle *trans,
struct btrfs_root *extent_root, u64 flags, int force)
{
@@ -4882,7 +4876,7 @@
btrfs_get_alloc_profile(root, 0),
CHUNK_ALLOC_NO_FORCE);
btrfs_end_transaction(trans, root);
- if (ret == -ENOSPC)
+ if (ret > 0 || ret == -ENOSPC)
ret = 0;
break;
case COMMIT_TRANS:
@@ -6497,19 +6491,15 @@
}
/**
- * btrfs_update_reserved_bytes - update the block_group and space info counters
+ * btrfs_add_reserved_bytes - update the block_group and space info counters
* @cache: The cache we are manipulating
+ * @ram_bytes: The number of bytes of file content, and will be same to
+ * @num_bytes except for the compress path.
* @num_bytes: The number of bytes in question
- * @reserve: One of the reservation enums
* @delalloc: The blocks are allocated for the delalloc write
*
- * This is called by the allocator when it reserves space, or by somebody who is
- * freeing space that was never actually used on disk. For example if you
- * reserve some space for a new leaf in transaction A and before transaction A
- * commits you free that leaf, you call this with reserve set to 0 in order to
- * clear the reservation.
- *
- * Metadata reservations should be called with RESERVE_ALLOC so we do the proper
+ * This is called by the allocator when it reserves space. Metadata
+ * reservations should be called with RESERVE_ALLOC so we do the proper
* ENOSPC accounting. For data we handle the reservation through clearing the
* delalloc bits in the io_tree. We have to do this since we could end up
* allocating less disk space for the amount of data we have reserved in the
@@ -6519,44 +6509,63 @@
* make the reservation and return -EAGAIN, otherwise this function always
* succeeds.
*/
-static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve, int delalloc)
+static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 ram_bytes, u64 num_bytes, int delalloc)
{
struct btrfs_space_info *space_info = cache->space_info;
int ret = 0;
spin_lock(&space_info->lock);
spin_lock(&cache->lock);
- if (reserve != RESERVE_FREE) {
- if (cache->ro) {
- ret = -EAGAIN;
- } else {
- cache->reserved += num_bytes;
- space_info->bytes_reserved += num_bytes;
- if (reserve == RESERVE_ALLOC) {
- trace_btrfs_space_reservation(cache->fs_info,
- "space_info", space_info->flags,
- num_bytes, 0);
- space_info->bytes_may_use -= num_bytes;
- }
-
- if (delalloc)
- cache->delalloc_bytes += num_bytes;
- }
+ if (cache->ro) {
+ ret = -EAGAIN;
} else {
- if (cache->ro)
- space_info->bytes_readonly += num_bytes;
- cache->reserved -= num_bytes;
- space_info->bytes_reserved -= num_bytes;
+ cache->reserved += num_bytes;
+ space_info->bytes_reserved += num_bytes;
+ trace_btrfs_space_reservation(cache->fs_info,
+ "space_info", space_info->flags,
+ ram_bytes, 0);
+ space_info->bytes_may_use -= ram_bytes;
if (delalloc)
- cache->delalloc_bytes -= num_bytes;
+ cache->delalloc_bytes += num_bytes;
}
spin_unlock(&cache->lock);
spin_unlock(&space_info->lock);
return ret;
}
+/**
+ * btrfs_free_reserved_bytes - update the block_group and space info counters
+ * @cache: The cache we are manipulating
+ * @num_bytes: The number of bytes in question
+ * @delalloc: The blocks are allocated for the delalloc write
+ *
+ * This is called by somebody who is freeing space that was never actually used
+ * on disk. For example if you reserve some space for a new leaf in transaction
+ * A and before transaction A commits you free that leaf, you call this with
+ * reserve set to 0 in order to clear the reservation.
+ */
+
+static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 num_bytes, int delalloc)
+{
+ struct btrfs_space_info *space_info = cache->space_info;
+ int ret = 0;
+
+ spin_lock(&space_info->lock);
+ spin_lock(&cache->lock);
+ if (cache->ro)
+ space_info->bytes_readonly += num_bytes;
+ cache->reserved -= num_bytes;
+ space_info->bytes_reserved -= num_bytes;
+
+ if (delalloc)
+ cache->delalloc_bytes -= num_bytes;
+ spin_unlock(&cache->lock);
+ spin_unlock(&space_info->lock);
+ return ret;
+}
void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
@@ -7191,7 +7200,7 @@
WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
btrfs_add_free_space(cache, buf->start, buf->len);
- btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
+ btrfs_free_reserved_bytes(cache, buf->len, 0);
btrfs_put_block_group(cache);
trace_btrfs_reserved_extent_free(root, buf->start, buf->len);
pin = 0;
@@ -7416,9 +7425,9 @@
* the free space extent currently.
*/
static noinline int find_free_extent(struct btrfs_root *orig_root,
- u64 num_bytes, u64 empty_size,
- u64 hint_byte, struct btrfs_key *ins,
- u64 flags, int delalloc)
+ u64 ram_bytes, u64 num_bytes, u64 empty_size,
+ u64 hint_byte, struct btrfs_key *ins,
+ u64 flags, int delalloc)
{
int ret = 0;
struct btrfs_root *root = orig_root->fs_info->extent_root;
@@ -7430,8 +7439,6 @@
struct btrfs_space_info *space_info;
int loop = 0;
int index = __get_raid_index(flags);
- int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ?
- RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
bool failed_cluster_refill = false;
bool failed_alloc = false;
bool use_cluster = true;
@@ -7763,8 +7770,8 @@
search_start - offset);
BUG_ON(offset > search_start);
- ret = btrfs_update_reserved_bytes(block_group, num_bytes,
- alloc_type, delalloc);
+ ret = btrfs_add_reserved_bytes(block_group, ram_bytes,
+ num_bytes, delalloc);
if (ret == -EAGAIN) {
btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
@@ -7936,7 +7943,7 @@
up_read(&info->groups_sem);
}
-int btrfs_reserve_extent(struct btrfs_root *root,
+int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
u64 num_bytes, u64 min_alloc_size,
u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc)
@@ -7948,8 +7955,8 @@
flags = btrfs_get_alloc_profile(root, is_data);
again:
WARN_ON(num_bytes < root->sectorsize);
- ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
- flags, delalloc);
+ ret = find_free_extent(root, ram_bytes, num_bytes, empty_size,
+ hint_byte, ins, flags, delalloc);
if (!ret && !is_data) {
btrfs_dec_block_group_reservations(root->fs_info,
ins->objectid);
@@ -7958,6 +7965,7 @@
num_bytes = min(num_bytes >> 1, ins->offset);
num_bytes = round_down(num_bytes, root->sectorsize);
num_bytes = max(num_bytes, min_alloc_size);
+ ram_bytes = num_bytes;
if (num_bytes == min_alloc_size)
final_tried = true;
goto again;
@@ -7995,7 +8003,7 @@
if (btrfs_test_opt(root->fs_info, DISCARD))
ret = btrfs_discard_extent(root, start, len, NULL);
btrfs_add_free_space(cache, start, len);
- btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
+ btrfs_free_reserved_bytes(cache, len, delalloc);
trace_btrfs_reserved_extent_free(root, start, len);
}
@@ -8223,8 +8231,8 @@
if (!block_group)
return -EINVAL;
- ret = btrfs_update_reserved_bytes(block_group, ins->offset,
- RESERVE_ALLOC_NO_ACCOUNT, 0);
+ ret = btrfs_add_reserved_bytes(block_group, ins->offset,
+ ins->offset, 0);
BUG_ON(ret); /* logic error */
ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
0, owner, offset, ins, 1);
@@ -8368,7 +8376,7 @@
if (IS_ERR(block_rsv))
return ERR_CAST(block_rsv);
- ret = btrfs_reserve_extent(root, blocksize, blocksize,
+ ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize,
empty_size, hint, &ins, 0, 0);
if (ret)
goto out_unuse;
@@ -8521,35 +8529,6 @@
wc->reada_slot = slot;
}
-/*
- * These may not be seen by the usual inc/dec ref code so we have to
- * add them here.
- */
-static int record_one_subtree_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, u64 bytenr,
- u64 num_bytes)
-{
- struct btrfs_qgroup_extent_record *qrecord;
- struct btrfs_delayed_ref_root *delayed_refs;
-
- qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS);
- if (!qrecord)
- return -ENOMEM;
-
- qrecord->bytenr = bytenr;
- qrecord->num_bytes = num_bytes;
- qrecord->old_roots = NULL;
-
- delayed_refs = &trans->transaction->delayed_refs;
- spin_lock(&delayed_refs->lock);
- if (btrfs_qgroup_insert_dirty_extent(trans->fs_info,
- delayed_refs, qrecord))
- kfree(qrecord);
- spin_unlock(&delayed_refs->lock);
-
- return 0;
-}
-
static int account_leaf_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *eb)
@@ -8583,7 +8562,8 @@
num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
- ret = record_one_subtree_extent(trans, root, bytenr, num_bytes);
+ ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+ bytenr, num_bytes, GFP_NOFS);
if (ret)
return ret;
}
@@ -8732,8 +8712,9 @@
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
- ret = record_one_subtree_extent(trans, root, child_bytenr,
- root->nodesize);
+ ret = btrfs_qgroup_insert_dirty_extent(trans,
+ root->fs_info, child_bytenr,
+ root->nodesize, GFP_NOFS);
if (ret)
goto out;
}
@@ -9906,6 +9887,7 @@
} else {
ret = 0;
}
+ free_extent_map(em);
goto out;
}
path->slots[0]++;
@@ -9942,6 +9924,7 @@
block_group->iref = 0;
block_group->inode = NULL;
spin_unlock(&block_group->lock);
+ ASSERT(block_group->io_ctl.inode == NULL);
iput(inode);
last = block_group->key.objectid + block_group->key.offset;
btrfs_put_block_group(block_group);
@@ -9999,6 +9982,10 @@
free_excluded_extents(info->extent_root, block_group);
btrfs_remove_free_space_cache(block_group);
+ ASSERT(list_empty(&block_group->dirty_list));
+ ASSERT(list_empty(&block_group->io_list));
+ ASSERT(list_empty(&block_group->bg_list));
+ ASSERT(atomic_read(&block_group->count) == 1);
btrfs_put_block_group(block_group);
spin_lock(&info->block_group_cache_lock);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index bc2729a..28cd88f 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -20,6 +20,7 @@
#define EXTENT_DAMAGED (1U << 14)
#define EXTENT_NORESERVE (1U << 15)
#define EXTENT_QGROUP_RESERVED (1U << 16)
+#define EXTENT_CLEAR_DATA_RESV (1U << 17)
#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 5842423..fea31a4 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2070,7 +2070,7 @@
}
trans->sync = true;
- btrfs_init_log_ctx(&ctx);
+ btrfs_init_log_ctx(&ctx, inode);
ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx);
if (ret < 0) {
@@ -2675,6 +2675,7 @@
alloc_start = round_down(offset, blocksize);
alloc_end = round_up(offset + len, blocksize);
+ cur_offset = alloc_start;
/* Make sure we aren't being give some crap mode */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -2767,7 +2768,6 @@
/* First, check if we exceed the qgroup limit */
INIT_LIST_HEAD(&reserve_list);
- cur_offset = alloc_start;
while (1) {
em = btrfs_get_extent(inode, NULL, 0, cur_offset,
alloc_end - cur_offset, 0);
@@ -2794,6 +2794,14 @@
last_byte - cur_offset);
if (ret < 0)
break;
+ } else {
+ /*
+ * Do not need to reserve unwritten extent for this
+ * range, free reserved data space first, otherwise
+ * it'll result in false ENOSPC error.
+ */
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ last_byte - cur_offset);
}
free_extent_map(em);
cur_offset = last_byte;
@@ -2811,6 +2819,9 @@
range->start,
range->len, 1 << inode->i_blkbits,
offset + len, &alloc_hint);
+ else
+ btrfs_free_reserved_data_space(inode, range->start,
+ range->len);
list_del(&range->list);
kfree(range);
}
@@ -2845,18 +2856,11 @@
unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
&cached_state, GFP_KERNEL);
out:
- /*
- * As we waited the extent range, the data_rsv_map must be empty
- * in the range, as written data range will be released from it.
- * And for prealloacted extent, it will also be released when
- * its metadata is written.
- * So this is completely used as cleanup.
- */
- btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start);
inode_unlock(inode);
/* Let go of our reservation. */
- btrfs_free_reserved_data_space(inode, alloc_start,
- alloc_end - alloc_start);
+ if (ret != 0)
+ btrfs_free_reserved_data_space(inode, alloc_start,
+ alloc_end - cur_offset);
return ret;
}
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index aa6faba..359ee86 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -495,10 +495,9 @@
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
prealloc, prealloc, &alloc_hint);
if (ret) {
- btrfs_delalloc_release_space(inode, 0, prealloc);
+ btrfs_delalloc_release_metadata(inode, prealloc);
goto out_put;
}
- btrfs_free_reserved_data_space(inode, 0, prealloc);
ret = btrfs_write_out_ino_cache(root, trans, path, inode);
out_put:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 08dfc57..e6811c4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -566,6 +566,8 @@
PAGE_SET_WRITEBACK |
page_error_op |
PAGE_END_WRITEBACK);
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
goto free_pages_out;
}
}
@@ -742,7 +744,7 @@
lock_extent(io_tree, async_extent->start,
async_extent->start + async_extent->ram_size - 1);
- ret = btrfs_reserve_extent(root,
+ ret = btrfs_reserve_extent(root, async_extent->ram_size,
async_extent->compressed_size,
async_extent->compressed_size,
0, alloc_hint, &ins, 1, 1);
@@ -969,7 +971,8 @@
EXTENT_DEFRAG, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK);
-
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
*nr_written = *nr_written +
(end - start + PAGE_SIZE) / PAGE_SIZE;
*page_started = 1;
@@ -989,7 +992,7 @@
unsigned long op;
cur_alloc_size = disk_num_bytes;
- ret = btrfs_reserve_extent(root, cur_alloc_size,
+ ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
@@ -1489,8 +1492,10 @@
extent_clear_unlock_delalloc(inode, cur_offset,
cur_offset + num_bytes - 1,
locked_page, EXTENT_LOCKED |
- EXTENT_DELALLOC, PAGE_UNLOCK |
- PAGE_SET_PRIVATE2);
+ EXTENT_DELALLOC |
+ EXTENT_CLEAR_DATA_RESV,
+ PAGE_UNLOCK | PAGE_SET_PRIVATE2);
+
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
@@ -1807,7 +1812,9 @@
return;
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
- && do_list && !(state->state & EXTENT_NORESERVE))
+ && do_list && !(state->state & EXTENT_NORESERVE)
+ && (*bits & (EXTENT_DO_ACCOUNTING |
+ EXTENT_CLEAR_DATA_RESV)))
btrfs_free_reserved_data_space_noquota(inode,
state->start, len);
@@ -7251,7 +7258,7 @@
int ret;
alloc_hint = get_extent_allocation_hint(inode, start, len);
- ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
+ ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0,
alloc_hint, &ins, 1, 1);
if (ret)
return ERR_PTR(ret);
@@ -7751,6 +7758,13 @@
ret = PTR_ERR(em2);
goto unlock_err;
}
+ /*
+ * For inode marked NODATACOW or extent marked PREALLOC,
+ * use the existing or preallocated extent, so does not
+ * need to adjust btrfs_space_info's bytes_may_use.
+ */
+ btrfs_free_reserved_data_space_noquota(inode,
+ start, len);
goto unlock;
}
}
@@ -7785,7 +7799,6 @@
i_size_write(inode, start + len);
adjust_dio_outstanding_extents(inode, dio_data, len);
- btrfs_free_reserved_data_space(inode, start, len);
WARN_ON(dio_data->reserve < len);
dio_data->reserve -= len;
dio_data->unsubmitted_oe_range_end = start + len;
@@ -10306,6 +10319,7 @@
u64 last_alloc = (u64)-1;
int ret = 0;
bool own_trans = true;
+ u64 end = start + num_bytes - 1;
if (trans)
own_trans = false;
@@ -10327,8 +10341,8 @@
* sized chunks.
*/
cur_bytes = min(cur_bytes, last_alloc);
- ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
- *alloc_hint, &ins, 1, 0);
+ ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes,
+ min_size, 0, *alloc_hint, &ins, 1, 0);
if (ret) {
if (own_trans)
btrfs_end_transaction(trans, root);
@@ -10414,6 +10428,9 @@
if (own_trans)
btrfs_end_transaction(trans, root);
}
+ if (cur_offset < end)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ end - cur_offset + 1);
return ret;
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 14ed1e9..b2a2da5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5084,7 +5084,7 @@
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- return btrfs_qgroup_wait_for_completion(root->fs_info);
+ return btrfs_qgroup_wait_for_completion(root->fs_info, true);
}
static long _btrfs_ioctl_set_received_subvol(struct file *file,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 93ee1c1..8db2e29 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -995,7 +995,7 @@
goto out;
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
- btrfs_qgroup_wait_for_completion(fs_info);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
@@ -1453,10 +1453,9 @@
return ret;
}
-struct btrfs_qgroup_extent_record *
-btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- struct btrfs_qgroup_extent_record *record)
+int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_qgroup_extent_record *record)
{
struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node;
struct rb_node *parent_node = NULL;
@@ -1475,12 +1474,42 @@
else if (bytenr > entry->bytenr)
p = &(*p)->rb_right;
else
- return entry;
+ return 1;
}
rb_link_node(&record->node, parent_node, p);
rb_insert_color(&record->node, &delayed_refs->dirty_extent_root);
- return NULL;
+ return 0;
+}
+
+int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
+ gfp_t gfp_flag)
+{
+ struct btrfs_qgroup_extent_record *record;
+ struct btrfs_delayed_ref_root *delayed_refs;
+ int ret;
+
+ if (!fs_info->quota_enabled || bytenr == 0 || num_bytes == 0)
+ return 0;
+ if (WARN_ON(trans == NULL))
+ return -EINVAL;
+ record = kmalloc(sizeof(*record), gfp_flag);
+ if (!record)
+ return -ENOMEM;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+ record->bytenr = bytenr;
+ record->num_bytes = num_bytes;
+ record->old_roots = NULL;
+
+ spin_lock(&delayed_refs->lock);
+ ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs,
+ record);
+ spin_unlock(&delayed_refs->lock);
+ if (ret > 0)
+ kfree(record);
+ return 0;
}
#define UPDATE_NEW 0
@@ -2303,6 +2332,10 @@
int err = -ENOMEM;
int ret = 0;
+ mutex_lock(&fs_info->qgroup_rescan_lock);
+ fs_info->qgroup_rescan_running = true;
+ mutex_unlock(&fs_info->qgroup_rescan_lock);
+
path = btrfs_alloc_path();
if (!path)
goto out;
@@ -2369,6 +2402,9 @@
}
done:
+ mutex_lock(&fs_info->qgroup_rescan_lock);
+ fs_info->qgroup_rescan_running = false;
+ mutex_unlock(&fs_info->qgroup_rescan_lock);
complete_all(&fs_info->qgroup_rescan_completion);
}
@@ -2487,20 +2523,26 @@
return 0;
}
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info)
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+ bool interruptible)
{
int running;
int ret = 0;
mutex_lock(&fs_info->qgroup_rescan_lock);
spin_lock(&fs_info->qgroup_lock);
- running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+ running = fs_info->qgroup_rescan_running;
spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
- if (running)
+ if (!running)
+ return 0;
+
+ if (interruptible)
ret = wait_for_completion_interruptible(
&fs_info->qgroup_rescan_completion);
+ else
+ wait_for_completion(&fs_info->qgroup_rescan_completion);
return ret;
}
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 710887c0..1bc64c8 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -46,7 +46,8 @@
struct btrfs_fs_info *fs_info);
int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+ bool interruptible);
int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 src, u64 dst);
int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
@@ -63,10 +64,35 @@
struct btrfs_delayed_extent_op;
int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
-struct btrfs_qgroup_extent_record *
-btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- struct btrfs_qgroup_extent_record *record);
+/*
+ * Insert one dirty extent record into @delayed_refs, informing qgroup to
+ * account that extent at commit trans time.
+ *
+ * No lock version, caller must acquire delayed ref lock and allocate memory.
+ *
+ * Return 0 for success insert
+ * Return >0 for existing record, caller can free @record safely.
+ * Error is not possible
+ */
+int btrfs_qgroup_insert_dirty_extent_nolock(
+ struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_qgroup_extent_record *record);
+
+/*
+ * Insert one dirty extent record into @delayed_refs, informing qgroup to
+ * account that extent at commit trans time.
+ *
+ * Better encapsulated version.
+ *
+ * Return 0 if the operation is done.
+ * Return <0 for error, like memory allocation failure or invalid parameter
+ * (NULL trans)
+ */
+int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
+ gfp_t gfp_flag);
+
int
btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index b26a5ae..8a2c2a0 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -31,6 +31,7 @@
#include "async-thread.h"
#include "free-space-cache.h"
#include "inode-map.h"
+#include "qgroup.h"
/*
* backref_node, mapping_node and tree_block start with this
@@ -3037,15 +3038,19 @@
u64 num_bytes;
int nr = 0;
int ret = 0;
+ u64 prealloc_start = cluster->start - offset;
+ u64 prealloc_end = cluster->end - offset;
+ u64 cur_offset;
BUG_ON(cluster->start != cluster->boundary[0]);
inode_lock(inode);
- ret = btrfs_check_data_free_space(inode, cluster->start,
- cluster->end + 1 - cluster->start);
+ ret = btrfs_check_data_free_space(inode, prealloc_start,
+ prealloc_end + 1 - prealloc_start);
if (ret)
goto out;
+ cur_offset = prealloc_start;
while (nr < cluster->nr) {
start = cluster->boundary[nr] - offset;
if (nr + 1 < cluster->nr)
@@ -3055,16 +3060,21 @@
lock_extent(&BTRFS_I(inode)->io_tree, start, end);
num_bytes = end + 1 - start;
+ if (cur_offset < start)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ start - cur_offset);
ret = btrfs_prealloc_file_range(inode, 0, start,
num_bytes, num_bytes,
end + 1, &alloc_hint);
+ cur_offset = end + 1;
unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
if (ret)
break;
nr++;
}
- btrfs_free_reserved_data_space(inode, cluster->start,
- cluster->end + 1 - cluster->start);
+ if (cur_offset < prealloc_end)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ prealloc_end + 1 - cur_offset);
out:
inode_unlock(inode);
return ret;
@@ -3916,6 +3926,90 @@
return 0;
}
+/*
+ * Qgroup fixer for data chunk relocation.
+ * The data relocation is done in the following steps
+ * 1) Copy data extents into data reloc tree
+ * 2) Create tree reloc tree(special snapshot) for related subvolumes
+ * 3) Modify file extents in tree reloc tree
+ * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks
+ *
+ * The problem is, data and tree reloc tree are not accounted to qgroup,
+ * and 4) will only info qgroup to track tree blocks change, not file extents
+ * in the tree blocks.
+ *
+ * The good news is, related data extents are all in data reloc tree, so we
+ * only need to info qgroup to track all file extents in data reloc tree
+ * before commit trans.
+ */
+static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans,
+ struct reloc_control *rc)
+{
+ struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
+ struct inode *inode = rc->data_inode;
+ struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ int ret = 0;
+
+ if (!fs_info->quota_enabled)
+ return 0;
+
+ /*
+ * Only for stage where we update data pointers the qgroup fix is
+ * valid.
+ * For MOVING_DATA stage, we will miss the timing of swapping tree
+ * blocks, and won't fix it.
+ */
+ if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found))
+ return 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ key.objectid = btrfs_ino(inode);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1);
+ while (1) {
+ struct btrfs_file_extent_item *fi;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ if (key.objectid > btrfs_ino(inode))
+ break;
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ goto next;
+ fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(path->nodes[0], fi) !=
+ BTRFS_FILE_EXTENT_REG)
+ goto next;
+ ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info,
+ btrfs_file_extent_disk_bytenr(path->nodes[0], fi),
+ btrfs_file_extent_disk_num_bytes(path->nodes[0], fi),
+ GFP_NOFS);
+ if (ret < 0)
+ break;
+next:
+ ret = btrfs_next_item(data_reloc_root, path);
+ if (ret < 0)
+ break;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ }
+ unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1);
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
{
struct rb_root blocks = RB_ROOT;
@@ -4102,10 +4196,16 @@
/* get rid of pinned extents */
trans = btrfs_join_transaction(rc->extent_root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- else
- btrfs_commit_transaction(trans, rc->extent_root);
+ goto out_free;
+ }
+ err = qgroup_fix_relocated_data_extents(trans, rc);
+ if (err < 0) {
+ btrfs_abort_transaction(trans, err);
+ goto out_free;
+ }
+ btrfs_commit_transaction(trans, rc->extent_root);
out_free:
btrfs_free_block_rsv(rc->extent_root, rc->block_rsv);
btrfs_free_path(path);
@@ -4468,10 +4568,16 @@
unset_reloc_control(rc);
trans = btrfs_join_transaction(rc->extent_root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- else
- err = btrfs_commit_transaction(trans, rc->extent_root);
+ goto out_free;
+ }
+ err = qgroup_fix_relocated_data_extents(trans, rc);
+ if (err < 0) {
+ btrfs_abort_transaction(trans, err);
+ goto out_free;
+ }
+ err = btrfs_commit_transaction(trans, rc->extent_root);
out_free:
kfree(rc);
out:
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7fd7e18..0912960 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -272,6 +272,23 @@
root_key.objectid = key.offset;
key.offset++;
+ /*
+ * The root might have been inserted already, as before we look
+ * for orphan roots, log replay might have happened, which
+ * triggers a transaction commit and qgroup accounting, which
+ * in turn reads and inserts fs roots while doing backref
+ * walking.
+ */
+ root = btrfs_lookup_fs_root(tree_root->fs_info,
+ root_key.objectid);
+ if (root) {
+ WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+ &root->state));
+ if (btrfs_root_refs(&root->root_item) == 0)
+ btrfs_add_dead_root(root);
+ continue;
+ }
+
root = btrfs_read_fs_root(tree_root, &root_key);
err = PTR_ERR_OR_ZERO(root);
if (err && err != -ENOENT) {
@@ -310,16 +327,8 @@
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
err = btrfs_insert_fs_root(root->fs_info, root);
- /*
- * The root might have been inserted already, as before we look
- * for orphan roots, log replay might have happened, which
- * triggers a transaction commit and qgroup accounting, which
- * in turn reads and inserts fs roots while doing backref
- * walking.
- */
- if (err == -EEXIST)
- err = 0;
if (err) {
+ BUG_ON(err == -EEXIST);
btrfs_free_fs_root(root);
break;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 864ce33..4071fe2 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2241,6 +2241,13 @@
struct btrfs_trans_handle *trans;
struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+ root->fs_info->fs_frozen = 1;
+ /*
+ * We don't need a barrier here, we'll wait for any transaction that
+ * could be in progress on other threads (and do delayed iputs that
+ * we want to avoid on a frozen filesystem), or do the commit
+ * ourselves.
+ */
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
@@ -2251,6 +2258,14 @@
return btrfs_commit_transaction(trans, root);
}
+static int btrfs_unfreeze(struct super_block *sb)
+{
+ struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+
+ root->fs_info->fs_frozen = 0;
+ return 0;
+}
+
static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
@@ -2299,6 +2314,7 @@
.statfs = btrfs_statfs,
.remount_fs = btrfs_remount,
.freeze_fs = btrfs_freeze,
+ .unfreeze_fs = btrfs_unfreeze,
};
static const struct file_operations btrfs_ctl_fops = {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 9cca0a7..95d4191 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2278,8 +2278,13 @@
kmem_cache_free(btrfs_trans_handle_cachep, trans);
+ /*
+ * If fs has been frozen, we can not handle delayed iputs, otherwise
+ * it'll result in deadlock about SB_FREEZE_FS.
+ */
if (current != root->fs_info->transaction_kthread &&
- current != root->fs_info->cleaner_kthread)
+ current != root->fs_info->cleaner_kthread &&
+ !root->fs_info->fs_frozen)
btrfs_run_delayed_iputs(root);
return ret;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fff3f3e..e935035 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -27,6 +27,7 @@
#include "backref.h"
#include "hash.h"
#include "compression.h"
+#include "qgroup.h"
/* magic values for the inode_only field in btrfs_log_inode:
*
@@ -680,6 +681,21 @@
ins.type = BTRFS_EXTENT_ITEM_KEY;
offset = key->offset - btrfs_file_extent_offset(eb, item);
+ /*
+ * Manually record dirty extent, as here we did a shallow
+ * file extent item copy and skip normal backref update,
+ * but modifying extent tree all by ourselves.
+ * So need to manually record dirty extent for qgroup,
+ * as the owner of the file extent changed from log tree
+ * (doesn't affect qgroup) to fs/file tree(affects qgroup)
+ */
+ ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+ btrfs_file_extent_disk_bytenr(eb, item),
+ btrfs_file_extent_disk_num_bytes(eb, item),
+ GFP_NOFS);
+ if (ret < 0)
+ goto out;
+
if (ins.objectid > 0) {
u64 csum_start;
u64 csum_end;
@@ -2807,7 +2823,7 @@
*/
mutex_unlock(&root->log_mutex);
- btrfs_init_log_ctx(&root_log_ctx);
+ btrfs_init_log_ctx(&root_log_ctx, NULL);
mutex_lock(&log_root_tree->log_mutex);
atomic_inc(&log_root_tree->log_batch);
@@ -4741,7 +4757,8 @@
if (ret < 0) {
err = ret;
goto out_unlock;
- } else if (ret > 0) {
+ } else if (ret > 0 && ctx &&
+ other_ino != btrfs_ino(ctx->inode)) {
struct btrfs_key inode_key;
struct inode *other_inode;
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index a9f1b75..ab858e3 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -30,15 +30,18 @@
int log_transid;
int io_err;
bool log_new_dentries;
+ struct inode *inode;
struct list_head list;
};
-static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx)
+static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
+ struct inode *inode)
{
ctx->log_ret = 0;
ctx->log_transid = 0;
ctx->io_err = 0;
ctx->log_new_dentries = false;
+ ctx->inode = inode;
INIT_LIST_HEAD(&ctx->list);
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 51f1255..035efce 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -834,10 +834,6 @@
struct btrfs_device *device;
device = container_of(work, struct btrfs_device, rcu_work);
-
- if (device->bdev)
- blkdev_put(device->bdev, device->mode);
-
rcu_string_free(device->name);
kfree(device);
}
@@ -852,6 +848,17 @@
schedule_work(&device->rcu_work);
}
+static void btrfs_close_bdev(struct btrfs_device *device)
+{
+ if (device->bdev && device->writeable) {
+ sync_blockdev(device->bdev);
+ invalidate_bdev(device->bdev);
+ }
+
+ if (device->bdev)
+ blkdev_put(device->bdev, device->mode);
+}
+
static void btrfs_close_one_device(struct btrfs_device *device)
{
struct btrfs_fs_devices *fs_devices = device->fs_devices;
@@ -870,10 +877,7 @@
if (device->missing)
fs_devices->missing_devices--;
- if (device->bdev && device->writeable) {
- sync_blockdev(device->bdev);
- invalidate_bdev(device->bdev);
- }
+ btrfs_close_bdev(device);
new_device = btrfs_alloc_device(NULL, &device->devid,
device->uuid);
@@ -1932,6 +1936,8 @@
btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device);
}
+ btrfs_close_bdev(device);
+
call_rcu(&device->rcu, free_device);
num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
@@ -2025,6 +2031,9 @@
/* zero out the old super if it is writable */
btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
}
+
+ btrfs_close_bdev(srcdev);
+
call_rcu(&srcdev->rcu, free_device);
/*
@@ -2080,6 +2089,8 @@
* the device_list_mutex lock.
*/
btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+
+ btrfs_close_bdev(tgtdev);
call_rcu(&tgtdev->rcu, free_device);
}
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index eea6491..466f7d6 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -607,20 +607,54 @@
static const struct file_operations format3_fops;
static const struct file_operations format4_fops;
-static int table_open(struct inode *inode, struct file *file)
+static int table_open1(struct inode *inode, struct file *file)
{
struct seq_file *seq;
- int ret = -1;
+ int ret;
- if (file->f_op == &format1_fops)
- ret = seq_open(file, &format1_seq_ops);
- else if (file->f_op == &format2_fops)
- ret = seq_open(file, &format2_seq_ops);
- else if (file->f_op == &format3_fops)
- ret = seq_open(file, &format3_seq_ops);
- else if (file->f_op == &format4_fops)
- ret = seq_open(file, &format4_seq_ops);
+ ret = seq_open(file, &format1_seq_ops);
+ if (ret)
+ return ret;
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open2(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &format2_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open3(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &format3_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open4(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &format4_seq_ops);
if (ret)
return ret;
@@ -631,7 +665,7 @@
static const struct file_operations format1_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open1,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
@@ -639,7 +673,7 @@
static const struct file_operations format2_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open2,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
@@ -647,7 +681,7 @@
static const struct file_operations format3_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open3,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
@@ -655,7 +689,7 @@
static const struct file_operations format4_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open4,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3131747..c6ea25a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5466,8 +5466,6 @@
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- ext4_set_inode_state(inode,
- EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 1c593aa..3ec8708 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2211,6 +2211,7 @@
/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors(struct super_block *sb,
+ ext4_fsblk_t sb_block,
ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2241,6 +2242,11 @@
grp = i;
block_bitmap = ext4_block_bitmap(sb, gdp);
+ if (block_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Block bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
@@ -2248,6 +2254,11 @@
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
+ if (inode_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
@@ -2255,6 +2266,11 @@
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
+ if (inode_table == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode table for group %u overlaps "
+ "superblock", i);
+ }
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -3757,7 +3773,7 @@
goto failed_mount2;
}
}
- if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
+ if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
ret = -EFSCORRUPTED;
goto failed_mount2;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 39e9cfb..2eb935c 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1353,15 +1353,19 @@
size_t min_offs, free;
int total_ino;
void *base, *start, *end;
- int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+ int error = 0, tried_min_extra_isize = 0;
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+ int isize_diff; /* How much do we need to grow i_extra_isize */
down_write(&EXT4_I(inode)->xattr_sem);
+ /*
+ * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
+ */
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
retry:
- if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
- up_write(&EXT4_I(inode)->xattr_sem);
- return 0;
- }
+ isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
+ if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+ goto out;
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
@@ -1382,7 +1386,7 @@
goto cleanup;
free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
- if (free >= new_extra_isize) {
+ if (free >= isize_diff) {
entry = IFIRST(header);
ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize
- new_extra_isize, (void *)raw_inode +
@@ -1390,8 +1394,7 @@
(void *)header, total_ino,
inode->i_sb->s_blocksize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
- error = 0;
- goto cleanup;
+ goto out;
}
/*
@@ -1414,7 +1417,7 @@
end = bh->b_data + bh->b_size;
min_offs = end - base;
free = ext4_xattr_free_space(first, &min_offs, base, NULL);
- if (free < new_extra_isize) {
+ if (free < isize_diff) {
if (!tried_min_extra_isize && s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
@@ -1428,7 +1431,7 @@
free = inode->i_sb->s_blocksize;
}
- while (new_extra_isize > 0) {
+ while (isize_diff > 0) {
size_t offs, size, entry_size;
struct ext4_xattr_entry *small_entry = NULL;
struct ext4_xattr_info i = {
@@ -1459,7 +1462,7 @@
EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
EXT4_XATTR_LEN(last->e_name_len);
if (total_size <= free && total_size < min_total_size) {
- if (total_size < new_extra_isize) {
+ if (total_size < isize_diff) {
small_entry = last;
} else {
entry = last;
@@ -1514,22 +1517,22 @@
error = ext4_xattr_ibody_set(handle, inode, &i, is);
if (error)
goto cleanup;
+ total_ino -= entry_size;
entry = IFIRST(header);
- if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
- shift_bytes = new_extra_isize;
+ if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff)
+ shift_bytes = isize_diff;
else
- shift_bytes = entry_size + size;
+ shift_bytes = entry_size + EXT4_XATTR_SIZE(size);
/* Adjust the offsets and shift the remaining entries ahead */
- ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
- shift_bytes, (void *)raw_inode +
- EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
- (void *)header, total_ino - entry_size,
- inode->i_sb->s_blocksize);
+ ext4_xattr_shift_entries(entry, -shift_bytes,
+ (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+ EXT4_I(inode)->i_extra_isize + shift_bytes,
+ (void *)header, total_ino, inode->i_sb->s_blocksize);
- extra_isize += shift_bytes;
- new_extra_isize -= shift_bytes;
- EXT4_I(inode)->i_extra_isize = extra_isize;
+ isize_diff -= shift_bytes;
+ EXT4_I(inode)->i_extra_isize += shift_bytes;
+ header = IHDR(inode, raw_inode);
i.name = b_entry_name;
i.value = buffer;
@@ -1551,6 +1554,8 @@
kfree(bs);
}
brelse(bh);
+out:
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return 0;
@@ -1562,6 +1567,10 @@
kfree(is);
kfree(bs);
brelse(bh);
+ /*
+ * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+ * size expansion failed.
+ */
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 69dd3e6..a92e783 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -24,6 +24,7 @@
#define EXT4_XATTR_INDEX_SYSTEM 7
#define EXT4_XATTR_INDEX_RICHACL 8
#define EXT4_XATTR_INDEX_ENCRYPTION 9
+#define EXT4_XATTR_INDEX_HURD 10 /* Reserved for Hurd */
struct ext4_xattr_header {
__le32 h_magic; /* magic number for identification */
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d64d2a5..ccb401e 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1699,11 +1699,11 @@
trace_f2fs_write_end(inode, pos, len, copied);
set_page_dirty(page);
- f2fs_put_page(page, 1);
if (pos + copied > i_size_read(inode))
f2fs_i_size_write(inode, pos + copied);
+ f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 675fa79..14f5fe2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -538,7 +538,7 @@
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
struct radix_tree_root nat_set_root;/* root of the nat set cache */
- struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
+ struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
@@ -787,7 +787,7 @@
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
- struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */
+ struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
wait_queue_head_t cp_wait;
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
@@ -1074,22 +1074,22 @@
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
- percpu_down_read(&sbi->cp_rwsem);
+ down_read(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
- percpu_up_read(&sbi->cp_rwsem);
+ up_read(&sbi->cp_rwsem);
}
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
- percpu_down_write(&sbi->cp_rwsem);
+ down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
{
- percpu_up_write(&sbi->cp_rwsem);
+ up_write(&sbi->cp_rwsem);
}
static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 0e493f6..47abb96 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2086,15 +2086,19 @@
if (unlikely(f2fs_readonly(src->i_sb)))
return -EROFS;
- if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode))
- return -EISDIR;
+ if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
+ return -EINVAL;
if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
return -EOPNOTSUPP;
inode_lock(src);
- if (src != dst)
- inode_lock(dst);
+ if (src != dst) {
+ if (!inode_trylock(dst)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ }
ret = -EINVAL;
if (pos_in + len > src->i_size || pos_in + len < pos_in)
@@ -2152,6 +2156,7 @@
out_unlock:
if (src != dst)
inode_unlock(dst);
+out:
inode_unlock(src);
return ret;
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b2fa4b6..f75d197 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -206,14 +206,14 @@
struct nat_entry *e;
bool need = false;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
if (!get_nat_flag(e, IS_CHECKPOINTED) &&
!get_nat_flag(e, HAS_FSYNCED_INODE))
need = true;
}
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return need;
}
@@ -223,11 +223,11 @@
struct nat_entry *e;
bool is_cp = true;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e && !get_nat_flag(e, IS_CHECKPOINTED))
is_cp = false;
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return is_cp;
}
@@ -237,13 +237,13 @@
struct nat_entry *e;
bool need_update = true;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ino);
if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
(get_nat_flag(e, IS_CHECKPOINTED) ||
get_nat_flag(e, HAS_FSYNCED_INODE)))
need_update = false;
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return need_update;
}
@@ -284,7 +284,7 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
e = grab_nat_entry(nm_i, ni->nid);
@@ -334,7 +334,7 @@
set_nat_flag(e, HAS_FSYNCED_INODE, true);
set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -342,7 +342,8 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
int nr = nr_shrink;
- percpu_down_write(&nm_i->nat_tree_lock);
+ if (!down_write_trylock(&nm_i->nat_tree_lock))
+ return 0;
while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
struct nat_entry *ne;
@@ -351,7 +352,7 @@
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
return nr - nr_shrink;
}
@@ -373,13 +374,13 @@
ni->nid = nid;
/* Check nat cache */
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
ni->ino = nat_get_ino(e);
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return;
}
@@ -403,11 +404,11 @@
node_info_from_raw_nat(ni, &ne);
f2fs_put_page(page, 1);
cache:
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
/* cache nat entry */
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
cache_nat_entry(sbi, nid, &ne);
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
/*
@@ -1788,7 +1789,7 @@
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
@@ -1820,7 +1821,7 @@
remove_free_nid(nm_i, nid);
}
up_read(&curseg->journal_rwsem);
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
@@ -2209,7 +2210,7 @@
if (!nm_i->dirty_nat_cnt)
return;
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
/*
* if there are no enough space in journal to store dirty nat
@@ -2232,7 +2233,7 @@
list_for_each_entry_safe(set, tmp, &sets, set_list)
__flush_nat_entry_set(sbi, set);
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
@@ -2268,8 +2269,7 @@
mutex_init(&nm_i->build_lock);
spin_lock_init(&nm_i->free_nid_list_lock);
- if (percpu_init_rwsem(&nm_i->nat_tree_lock))
- return -ENOMEM;
+ init_rwsem(&nm_i->nat_tree_lock);
nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
@@ -2326,7 +2326,7 @@
spin_unlock(&nm_i->free_nid_list_lock);
/* destroy nat cache */
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_cache(nm_i,
nid, NATVEC_SIZE, natvec))) {
unsigned idx;
@@ -2351,9 +2351,8 @@
kmem_cache_free(nat_entry_set_slab, setvec[idx]);
}
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
- percpu_free_rwsem(&nm_i->nat_tree_lock);
kfree(nm_i->nat_bitmap);
sbi->nm_info = NULL;
kfree(nm_i);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1b86d3f..7f863a6 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -706,8 +706,6 @@
percpu_counter_destroy(&sbi->nr_pages[i]);
percpu_counter_destroy(&sbi->alloc_valid_block_count);
percpu_counter_destroy(&sbi->total_valid_inode_count);
-
- percpu_free_rwsem(&sbi->cp_rwsem);
}
static void f2fs_put_super(struct super_block *sb)
@@ -1483,9 +1481,6 @@
{
int i, err;
- if (percpu_init_rwsem(&sbi->cp_rwsem))
- return -ENOMEM;
-
for (i = 0; i < NR_COUNT_TYPE; i++) {
err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
if (err)
@@ -1686,6 +1681,7 @@
sbi->write_io[i].bio = NULL;
}
+ init_rwsem(&sbi->cp_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index f55a4e7..2178476 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -346,7 +346,7 @@
PAGE_SIZE - 1) & (loff_t)PAGE_MASK;
ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
- (end - start) >> SECTOR_SHIFT);
+ (end - start) >> SECTOR_SHIFT, end);
}
pnfs_ld_write_done(hdr);
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 18e6fd0..efc007f 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -141,6 +141,7 @@
struct rb_root bl_ext_ro;
spinlock_t bl_ext_lock; /* Protects list manipulation */
bool bl_scsi_layout;
+ u64 bl_lwb;
};
static inline struct pnfs_block_layout *
@@ -182,7 +183,7 @@
int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start,
sector_t end);
int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
- sector_t len);
+ sector_t len, u64 lwb);
bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
struct pnfs_block_extent *ret, bool rw);
int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index 992bcb1..c85fbfd 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -402,7 +402,7 @@
int
ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
- sector_t len)
+ sector_t len, u64 lwb)
{
struct rb_root *root = &bl->bl_ext_rw;
sector_t end = start + len;
@@ -471,6 +471,8 @@
}
}
out:
+ if (bl->bl_lwb < lwb)
+ bl->bl_lwb = lwb;
spin_unlock(&bl->bl_ext_lock);
__ext_put_deviceids(&tmp);
@@ -518,7 +520,7 @@
}
static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
- size_t buffer_size, size_t *count)
+ size_t buffer_size, size_t *count, __u64 *lastbyte)
{
struct pnfs_block_extent *be;
int ret = 0;
@@ -542,6 +544,8 @@
p = encode_block_extent(be, p);
be->be_tag = EXTENT_COMMITTING;
}
+ *lastbyte = bl->bl_lwb - 1;
+ bl->bl_lwb = 0;
spin_unlock(&bl->bl_ext_lock);
return ret;
@@ -564,7 +568,7 @@
arg->layoutupdate_pages = &arg->layoutupdate_page;
retry:
- ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count);
+ ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count, &arg->lastbytewritten);
if (unlikely(ret)) {
ext_tree_free_commitdata(arg, buffer_size);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index a7f2e6e..52a2831 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -275,6 +275,7 @@
err_socks:
svc_rpcb_cleanup(serv, net);
err_bind:
+ nn->cb_users[minorversion]--;
dprintk("NFS: Couldn't create callback socket: err = %d; "
"net = %p\n", ret, net);
return ret;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index c92a75e..f953ef6 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -454,11 +454,8 @@
((u32 *)&rclist->rcl_sessionid.data)[3],
ref->rc_sequenceid, ref->rc_slotid);
- spin_lock(&tbl->slot_tbl_lock);
- status = (test_bit(ref->rc_slotid, tbl->used_slots) &&
- tbl->slots[ref->rc_slotid].seq_nr ==
- ref->rc_sequenceid);
- spin_unlock(&tbl->slot_tbl_lock);
+ status = nfs4_slot_wait_on_seqid(tbl, ref->rc_slotid,
+ ref->rc_sequenceid, HZ >> 1) < 0;
if (status)
goto out;
}
@@ -487,7 +484,6 @@
goto out;
tbl = &clp->cl_session->bc_slot_table;
- slot = tbl->slots + args->csa_slotid;
/* Set up res before grabbing the spinlock */
memcpy(&res->csr_sessionid, &args->csa_sessionid,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 003ebce..1e10678 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -426,7 +426,7 @@
* Initialise the timeout values for a connection
*/
void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
- unsigned int timeo, unsigned int retrans)
+ int timeo, int retrans)
{
to->to_initval = timeo * HZ / 10;
to->to_retries = retrans;
@@ -434,9 +434,9 @@
switch (proto) {
case XPRT_TRANSPORT_TCP:
case XPRT_TRANSPORT_RDMA:
- if (to->to_retries == 0)
+ if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_TCP_RETRANS;
- if (to->to_initval == 0)
+ if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0)
to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10;
if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
to->to_initval = NFS_MAX_TCP_TIMEOUT;
@@ -449,9 +449,9 @@
to->to_exponential = 0;
break;
case XPRT_TRANSPORT_UDP:
- if (to->to_retries == 0)
+ if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_UDP_RETRANS;
- if (!to->to_initval)
+ if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0)
to->to_initval = NFS_DEF_UDP_TIMEO * HZ / 10;
if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
to->to_initval = NFS_MAX_UDP_TIMEOUT;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index e6206ea..51b5136 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -37,6 +37,7 @@
if (ffl) {
INIT_LIST_HEAD(&ffl->error_list);
INIT_LIST_HEAD(&ffl->mirrors);
+ ffl->last_report_time = ktime_get();
return &ffl->generic_hdr;
} else
return NULL;
@@ -640,19 +641,18 @@
{
static const ktime_t notime = {0};
s64 report_interval = FF_LAYOUTSTATS_REPORT_INTERVAL;
+ struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(mirror->layout);
nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now);
if (ktime_equal(mirror->start_time, notime))
mirror->start_time = now;
- if (ktime_equal(mirror->last_report_time, notime))
- mirror->last_report_time = now;
if (mirror->report_interval != 0)
report_interval = (s64)mirror->report_interval * 1000LL;
else if (layoutstats_timer != 0)
report_interval = (s64)layoutstats_timer * 1000LL;
- if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >=
+ if (ktime_to_ms(ktime_sub(now, ffl->last_report_time)) >=
report_interval) {
- mirror->last_report_time = now;
+ ffl->last_report_time = now;
return true;
}
@@ -806,11 +806,14 @@
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
struct nfs4_pnfs_ds *ds;
+ bool fail_return = false;
int idx;
/* mirrors are sorted by efficiency */
for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
+ if (idx+1 == fls->mirror_array_cnt)
+ fail_return = true;
+ ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
if (ds) {
*best_idx = idx;
return ds;
@@ -859,6 +862,7 @@
struct nfs4_pnfs_ds *ds;
int ds_idx;
+retry:
/* Use full layout for now */
if (!pgio->pg_lseg)
ff_layout_pg_get_read(pgio, req, false);
@@ -871,10 +875,13 @@
ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
if (!ds) {
- if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
- goto out_pnfs;
- else
+ if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ /* Sleep for 1 second before retrying */
+ ssleep(1);
+ goto retry;
}
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
@@ -890,12 +897,6 @@
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_read_mds(pgio);
- return;
-
-out_pnfs:
- pnfs_set_lo_fail(pgio->pg_lseg);
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
}
static void
@@ -909,6 +910,7 @@
int i;
int status;
+retry:
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
@@ -940,10 +942,13 @@
for (i = 0; i < pgio->pg_mirror_count; i++) {
ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
if (!ds) {
- if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
- goto out_pnfs;
- else
+ if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ /* Sleep for 1 second before retrying */
+ ssleep(1);
+ goto retry;
}
pgm = &pgio->pg_mirrors[i];
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
@@ -956,12 +961,6 @@
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_write_mds(pgio);
- return;
-
-out_pnfs:
- pnfs_set_lo_fail(pgio->pg_lseg);
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
}
static unsigned int
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index 1bcdb15..3ee0c9f 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -84,7 +84,6 @@
struct nfs4_ff_layoutstat read_stat;
struct nfs4_ff_layoutstat write_stat;
ktime_t start_time;
- ktime_t last_report_time;
u32 report_interval;
};
@@ -101,6 +100,7 @@
struct pnfs_ds_commit_info commit_info;
struct list_head mirrors;
struct list_head error_list; /* nfs4_ff_layout_ds_err */
+ ktime_t last_report_time; /* Layoutstat report times */
};
static inline struct nfs4_flexfile_layout *
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 0aa36be..f7a3f6b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -17,8 +17,8 @@
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
-static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS;
+static unsigned int dataserver_retrans;
void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
{
@@ -379,7 +379,7 @@
devid = &mirror->mirror_ds->id_node;
if (ff_layout_test_devid_unavailable(devid))
- goto out;
+ goto out_fail;
ds = mirror->mirror_ds->ds;
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
@@ -405,15 +405,16 @@
mirror->mirror_ds->ds_versions[0].rsize = max_payload;
if (mirror->mirror_ds->ds_versions[0].wsize > max_payload)
mirror->mirror_ds->ds_versions[0].wsize = max_payload;
- } else {
- ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
- mirror, lseg->pls_range.offset,
- lseg->pls_range.length, NFS4ERR_NXIO,
- OP_ILLEGAL, GFP_NOIO);
- if (fail_return || !ff_layout_has_available_ds(lseg))
- pnfs_error_mark_layout_for_return(ino, lseg);
- ds = NULL;
+ goto out;
}
+ ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
+ mirror, lseg->pls_range.offset,
+ lseg->pls_range.length, NFS4ERR_NXIO,
+ OP_ILLEGAL, GFP_NOIO);
+out_fail:
+ if (fail_return || !ff_layout_has_available_ds(lseg))
+ pnfs_error_mark_layout_for_return(ino, lseg);
+ ds = NULL;
out:
return ds;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7ce5e02..74935a1 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -58,6 +58,9 @@
*/
#define NFS_UNSPEC_PORT (-1)
+#define NFS_UNSPEC_RETRANS (UINT_MAX)
+#define NFS_UNSPEC_TIMEO (UINT_MAX)
+
/*
* Maximum number of pages that readdir can use for creating
* a vmapped array of pages.
@@ -156,7 +159,7 @@
int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
void nfs_server_insert_lists(struct nfs_server *);
void nfs_server_remove_lists(struct nfs_server *);
-void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int);
+void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans);
int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
rpc_authflavor_t);
struct nfs_server *nfs_alloc_server(void);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 6f47527..64b43b4 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -318,10 +318,22 @@
nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
{
struct nfs42_layoutstat_data *data = calldata;
- struct nfs_server *server = NFS_SERVER(data->args.inode);
+ struct inode *inode = data->inode;
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct pnfs_layout_hdr *lo;
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (!pnfs_layout_is_valid(lo)) {
+ spin_unlock(&inode->i_lock);
+ rpc_exit(task, 0);
+ return;
+ }
+ nfs4_stateid_copy(&data->args.stateid, &lo->plh_stateid);
+ spin_unlock(&inode->i_lock);
nfs41_setup_sequence(nfs4_get_session(server), &data->args.seq_args,
&data->res.seq_res, task);
+
}
static void
@@ -341,11 +353,11 @@
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_BAD_STATEID:
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match(&data->args.stateid,
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match(&data->args.stateid,
&lo->plh_stateid)) {
LIST_HEAD(head);
@@ -359,11 +371,23 @@
} else
spin_unlock(&inode->i_lock);
break;
+ case -NFS4ERR_OLD_STATEID:
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(&data->args.stateid,
+ &lo->plh_stateid)) {
+ /* Do we need to delay before resending? */
+ if (!nfs4_stateid_is_newer(&lo->plh_stateid,
+ &data->args.stateid))
+ rpc_delay(task, HZ);
+ rpc_restart_call_prepare(task);
+ }
+ spin_unlock(&inode->i_lock);
+ break;
case -ENOTSUPP:
case -EOPNOTSUPP:
NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
- default:
- break;
}
dprintk("%s server returns %d\n", __func__, task->tk_status);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8d7d08d..cd3b7cf 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -817,6 +817,11 @@
goto error;
}
+ if (server->nfs_client == clp) {
+ error = -ELOOP;
+ goto error;
+ }
+
/*
* Query for the lease time on clientid setup or renewal
*
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1949bbd..f5aecaa 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -634,15 +634,11 @@
}
EXPORT_SYMBOL_GPL(nfs40_setup_sequence);
-static int nfs40_sequence_done(struct rpc_task *task,
- struct nfs4_sequence_res *res)
+static void nfs40_sequence_free_slot(struct nfs4_sequence_res *res)
{
struct nfs4_slot *slot = res->sr_slot;
struct nfs4_slot_table *tbl;
- if (slot == NULL)
- goto out;
-
tbl = slot->table;
spin_lock(&tbl->slot_tbl_lock);
if (!nfs41_wake_and_assign_slot(tbl, slot))
@@ -650,7 +646,13 @@
spin_unlock(&tbl->slot_tbl_lock);
res->sr_slot = NULL;
-out:
+}
+
+static int nfs40_sequence_done(struct rpc_task *task,
+ struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL)
+ nfs40_sequence_free_slot(res);
return 1;
}
@@ -666,6 +668,11 @@
tbl = slot->table;
session = tbl->session;
+ /* Bump the slot sequence number */
+ if (slot->seq_done)
+ slot->seq_nr++;
+ slot->seq_done = 0;
+
spin_lock(&tbl->slot_tbl_lock);
/* Be nice to the server: try to ensure that the last transmitted
* value for highest_user_slotid <= target_highest_slotid
@@ -686,9 +693,12 @@
res->sr_slot = NULL;
if (send_new_highest_used_slotid)
nfs41_notify_server(session->clp);
+ if (waitqueue_active(&tbl->slot_waitq))
+ wake_up_all(&tbl->slot_waitq);
}
-int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+static int nfs41_sequence_process(struct rpc_task *task,
+ struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
struct nfs4_slot *slot = res->sr_slot;
@@ -714,7 +724,7 @@
switch (res->sr_status) {
case 0:
/* Update the slot's sequence and clientid lease timer */
- ++slot->seq_nr;
+ slot->seq_done = 1;
clp = session->clp;
do_renew_lease(clp, res->sr_timestamp);
/* Check sequence flags */
@@ -769,16 +779,16 @@
goto retry_nowait;
default:
/* Just update the slot sequence no. */
- ++slot->seq_nr;
+ slot->seq_done = 1;
}
out:
/* The session may be reset by one of the error handlers. */
dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
- nfs41_sequence_free_slot(res);
out_noaction:
return ret;
retry_nowait:
if (rpc_restart_call_prepare(task)) {
+ nfs41_sequence_free_slot(res);
task->tk_status = 0;
ret = 0;
}
@@ -789,8 +799,37 @@
rpc_delay(task, NFS4_POLL_RETRY_MAX);
return 0;
}
+
+int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ if (!nfs41_sequence_process(task, res))
+ return 0;
+ if (res->sr_slot != NULL)
+ nfs41_sequence_free_slot(res);
+ return 1;
+
+}
EXPORT_SYMBOL_GPL(nfs41_sequence_done);
+static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot == NULL)
+ return 1;
+ if (res->sr_slot->table->session != NULL)
+ return nfs41_sequence_process(task, res);
+ return nfs40_sequence_done(task, res);
+}
+
+static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL) {
+ if (res->sr_slot->table->session != NULL)
+ nfs41_sequence_free_slot(res);
+ else
+ nfs40_sequence_free_slot(res);
+ }
+}
+
int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
{
if (res->sr_slot == NULL)
@@ -920,6 +959,17 @@
args, res, task);
}
+static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ return nfs40_sequence_done(task, res);
+}
+
+static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL)
+ nfs40_sequence_free_slot(res);
+}
+
int nfs4_sequence_done(struct rpc_task *task,
struct nfs4_sequence_res *res)
{
@@ -1197,6 +1247,7 @@
struct super_block *sb = p->dentry->d_sb;
nfs_free_seqid(p->o_arg.seqid);
+ nfs4_sequence_free_slot(&p->o_res.seq_res);
if (p->state != NULL)
nfs4_put_open_state(p->state);
nfs4_put_state_owner(p->owner);
@@ -1656,9 +1707,14 @@
static struct nfs4_state *
nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
{
+ struct nfs4_state *ret;
+
if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS)
- return _nfs4_opendata_reclaim_to_nfs4_state(data);
- return _nfs4_opendata_to_nfs4_state(data);
+ ret =_nfs4_opendata_reclaim_to_nfs4_state(data);
+ else
+ ret = _nfs4_opendata_to_nfs4_state(data);
+ nfs4_sequence_free_slot(&data->o_res.seq_res);
+ return ret;
}
static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
@@ -2056,7 +2112,7 @@
data->rpc_status = task->tk_status;
- if (!nfs4_sequence_done(task, &data->o_res.seq_res))
+ if (!nfs4_sequence_process(task, &data->o_res.seq_res))
return;
if (task->tk_status == 0) {
@@ -7864,7 +7920,7 @@
struct nfs4_layoutget *lgp = calldata;
dprintk("--> %s\n", __func__);
- nfs41_sequence_done(task, &lgp->res.seq_res);
+ nfs41_sequence_process(task, &lgp->res.seq_res);
dprintk("<-- %s\n", __func__);
}
@@ -8080,6 +8136,7 @@
/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
if (status == 0 && lgp->res.layoutp->len)
lseg = pnfs_layout_process(lgp);
+ nfs4_sequence_free_slot(&lgp->res.seq_res);
rpc_put_task(task);
dprintk("<-- %s status=%d\n", __func__, status);
if (status)
@@ -8106,7 +8163,7 @@
dprintk("--> %s\n", __func__);
- if (!nfs41_sequence_done(task, &lrp->res.seq_res))
+ if (!nfs41_sequence_process(task, &lrp->res.seq_res))
return;
server = NFS_SERVER(lrp->args.inode);
@@ -8118,6 +8175,7 @@
case -NFS4ERR_DELAY:
if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
break;
+ nfs4_sequence_free_slot(&lrp->res.seq_res);
rpc_restart_call_prepare(task);
return;
}
@@ -8138,6 +8196,7 @@
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
pnfs_clear_layoutreturn_waitbit(lo);
spin_unlock(&lo->plh_inode->i_lock);
+ nfs4_sequence_free_slot(&lrp->res.seq_res);
pnfs_free_lseg_list(&freeme);
pnfs_put_layout_hdr(lrp->args.layout);
nfs_iput_and_deactive(lrp->inode);
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index 332d06e..b629730 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -28,6 +28,7 @@
tbl->highest_used_slotid = NFS4_NO_SLOT;
spin_lock_init(&tbl->slot_tbl_lock);
rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, queue);
+ init_waitqueue_head(&tbl->slot_waitq);
init_completion(&tbl->complete);
}
@@ -172,6 +173,58 @@
return ERR_PTR(-E2BIG);
}
+static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid,
+ u32 *seq_nr)
+ __must_hold(&tbl->slot_tbl_lock)
+{
+ struct nfs4_slot *slot;
+
+ slot = nfs4_lookup_slot(tbl, slotid);
+ if (IS_ERR(slot))
+ return PTR_ERR(slot);
+ *seq_nr = slot->seq_nr;
+ return 0;
+}
+
+/*
+ * nfs4_slot_seqid_in_use - test if a slot sequence id is still in use
+ *
+ * Given a slot table, slot id and sequence number, determine if the
+ * RPC call in question is still in flight. This function is mainly
+ * intended for use by the callback channel.
+ */
+static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr)
+{
+ u32 cur_seq;
+ bool ret = false;
+
+ spin_lock(&tbl->slot_tbl_lock);
+ if (nfs4_slot_get_seqid(tbl, slotid, &cur_seq) == 0 &&
+ cur_seq == seq_nr && test_bit(slotid, tbl->used_slots))
+ ret = true;
+ spin_unlock(&tbl->slot_tbl_lock);
+ return ret;
+}
+
+/*
+ * nfs4_slot_wait_on_seqid - wait until a slot sequence id is complete
+ *
+ * Given a slot table, slot id and sequence number, wait until the
+ * corresponding RPC call completes. This function is mainly
+ * intended for use by the callback channel.
+ */
+int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr,
+ unsigned long timeout)
+{
+ if (wait_event_timeout(tbl->slot_waitq,
+ !nfs4_slot_seqid_in_use(tbl, slotid, seq_nr),
+ timeout) == 0)
+ return -ETIMEDOUT;
+ return 0;
+}
+
/*
* nfs4_alloc_slot - efficiently look for a free slot
*
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 5b51298..f703b75 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -21,7 +21,8 @@
unsigned long generation;
u32 slot_nr;
u32 seq_nr;
- unsigned int interrupted : 1;
+ unsigned int interrupted : 1,
+ seq_done : 1;
};
/* Sessions */
@@ -36,6 +37,7 @@
unsigned long used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
spinlock_t slot_tbl_lock;
struct rpc_wait_queue slot_tbl_waitq; /* allocators may wait here */
+ wait_queue_head_t slot_waitq; /* Completion wait on slot */
u32 max_slots; /* # slots in table */
u32 max_slotid; /* Max allowed slotid value */
u32 highest_used_slotid; /* sent to server on each SEQ.
@@ -78,6 +80,9 @@
extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid);
+extern int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr,
+ unsigned long timeout);
extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 70806ca..6daf034 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1555,6 +1555,7 @@
}
lookup_again:
+ nfs4_client_recover_expired_lease(clp);
first = false;
spin_lock(&ino->i_lock);
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
@@ -2510,7 +2511,6 @@
data->args.fh = NFS_FH(inode);
data->args.inode = inode;
- nfs4_stateid_copy(&data->args.stateid, &hdr->plh_stateid);
status = ld->prepare_layoutstats(&data->args);
if (status)
goto out_free;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 18d446e..d396013 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -923,6 +923,8 @@
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data) {
+ data->timeo = NFS_UNSPEC_TIMEO;
+ data->retrans = NFS_UNSPEC_RETRANS;
data->acregmin = NFS_DEF_ACREGMIN;
data->acregmax = NFS_DEF_ACREGMAX;
data->acdirmin = NFS_DEF_ACDIRMIN;
@@ -1189,6 +1191,19 @@
return rc;
}
+static int nfs_get_option_ul_bound(substring_t args[], unsigned long *option,
+ unsigned long l_bound, unsigned long u_bound)
+{
+ int ret;
+
+ ret = nfs_get_option_ul(args, option);
+ if (ret != 0)
+ return ret;
+ if (*option < l_bound || *option > u_bound)
+ return -ERANGE;
+ return 0;
+}
+
/*
* Error-check and convert a string of mount options from user space into
* a data structure. The whole mount string is processed; bad options are
@@ -1352,12 +1367,12 @@
mnt->bsize = option;
break;
case Opt_timeo:
- if (nfs_get_option_ul(args, &option) || option == 0)
+ if (nfs_get_option_ul_bound(args, &option, 1, INT_MAX))
goto out_invalid_value;
mnt->timeo = option;
break;
case Opt_retrans:
- if (nfs_get_option_ul(args, &option) || option == 0)
+ if (nfs_get_option_ul_bound(args, &option, 0, INT_MAX))
goto out_invalid_value;
mnt->retrans = option;
break;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 19f532e..6dc4296 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -223,8 +223,10 @@
size -= n;
buf += n;
copied += n;
- if (!m->count)
+ if (!m->count) {
+ m->from = 0;
m->index++;
+ }
if (!size)
goto Done;
}
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index b45345d..51157da 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -370,7 +370,7 @@
p = c->gap_lebs;
do {
- ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs);
+ ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs);
written = layout_leb_in_gaps(c, p);
if (written < 0) {
err = written;
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index e237811..11a0041 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -575,7 +575,8 @@
dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name,
inode->i_ino, dentry, size);
- return __ubifs_getxattr(inode, name, buffer, size);
+ name = xattr_full_name(handler, name);
+ return __ubifs_getxattr(inode, name, buffer, size);
}
static int ubifs_xattr_set(const struct xattr_handler *handler,
@@ -586,6 +587,8 @@
dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
name, inode->i_ino, dentry, size);
+ name = xattr_full_name(handler, name);
+
if (value)
return __ubifs_setxattr(inode, name, value, size, flags);
else
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index 1bfa602..5dea1fb 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -72,6 +72,7 @@
/* Returns 0 if exception not found and fixup otherwise. */
extern unsigned long search_exception_table(unsigned long);
+
/*
* architectures with an MMU should override these two
*/
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 59ffaa6..23ddf4b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -71,7 +71,8 @@
{
if (bio &&
bio->bi_iter.bi_size &&
- bio_op(bio) != REQ_OP_DISCARD)
+ bio_op(bio) != REQ_OP_DISCARD &&
+ bio_op(bio) != REQ_OP_SECURE_ERASE)
return true;
return false;
@@ -79,7 +80,9 @@
static inline bool bio_no_advance_iter(struct bio *bio)
{
- return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME;
+ return bio_op(bio) == REQ_OP_DISCARD ||
+ bio_op(bio) == REQ_OP_SECURE_ERASE ||
+ bio_op(bio) == REQ_OP_WRITE_SAME;
}
static inline bool bio_is_rw(struct bio *bio)
@@ -199,6 +202,9 @@
if (bio_op(bio) == REQ_OP_DISCARD)
return 1;
+ if (bio_op(bio) == REQ_OP_SECURE_ERASE)
+ return 1;
+
if (bio_op(bio) == REQ_OP_WRITE_SAME)
return 1;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2c210b6..e79055c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -882,7 +882,7 @@
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
int op)
{
- if (unlikely(op == REQ_OP_DISCARD))
+ if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
if (unlikely(op == REQ_OP_WRITE_SAME))
@@ -913,7 +913,9 @@
if (unlikely(rq->cmd_type != REQ_TYPE_FS))
return q->limits.max_hw_sectors;
- if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD))
+ if (!q->limits.chunk_sectors ||
+ req_op(rq) == REQ_OP_DISCARD ||
+ req_op(rq) == REQ_OP_SECURE_ERASE)
return blk_queue_get_max_sectors(q, req_op(rq));
return min(blk_max_size_offset(q, offset),
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index e294939..573c5a1 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -158,7 +158,7 @@
#define __compiler_offsetof(a, b) \
__builtin_offsetof(a, b)
-#if GCC_VERSION >= 40100 && GCC_VERSION < 40600
+#if GCC_VERSION >= 40100
# define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
#endif
@@ -242,7 +242,11 @@
*/
#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
-#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+/*
+ * sparse (__CHECKER__) pretends to be gcc, but can't do constant
+ * folding in __builtin_bswap*() (yet), so don't set these for it.
+ */
+#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__)
#if GCC_VERSION >= 40400
#define __HAVE_BUILTIN_BSWAP32__
#define __HAVE_BUILTIN_BSWAP64__
@@ -250,7 +254,7 @@
#if GCC_VERSION >= 40800
#define __HAVE_BUILTIN_BSWAP16__
#endif
-#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */
#if GCC_VERSION >= 50000
#define KASAN_ABI_VERSION 4
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index d2ba7d3..1ffbf2a 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -304,6 +304,8 @@
struct tegra_mipi_device *tegra_mipi_request(struct device *device);
void tegra_mipi_free(struct tegra_mipi_device *device);
+int tegra_mipi_enable(struct tegra_mipi_device *device);
+int tegra_mipi_disable(struct tegra_mipi_device *device);
int tegra_mipi_calibrate(struct tegra_mipi_device *device);
#endif
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 56b0b7e..99ac022 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -337,6 +337,7 @@
*/
#define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107
#define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109
+#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307
#define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507
#define E_ITS_MAPD_DEVICE_OOR 0x010801
#define E_ITS_MAPC_PROCNUM_OOR 0x010902
diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h
index 80ca889..664da00 100644
--- a/include/linux/netfilter/nfnetlink_acct.h
+++ b/include/linux/netfilter/nfnetlink_acct.h
@@ -15,6 +15,6 @@
struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name);
void nfnl_acct_put(struct nf_acct *acct);
void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
-extern int nfnl_acct_overquota(const struct sk_buff *skb,
- struct nf_acct *nfacct);
+int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb,
+ struct nf_acct *nfacct);
#endif /* _NFNL_ACCT_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 2599a98..fbc1fa6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1251,10 +1251,12 @@
int pci_set_vga_state(struct pci_dev *pdev, bool decode,
unsigned int command_bits, u32 flags);
-#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */
-#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */
-#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */
-#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */
+#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */
+#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */
+#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */
+#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */
+#define PCI_IRQ_ALL_TYPES \
+ (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX)
/* kmem_cache style wrapper around pci_alloc_consistent() */
diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h
index 76199b7..e302c44 100644
--- a/include/linux/smc91x.h
+++ b/include/linux/smc91x.h
@@ -1,6 +1,16 @@
#ifndef __SMC91X_H__
#define __SMC91X_H__
+/*
+ * These bits define which access sizes a platform can support, rather
+ * than the maximal access size. So, if your platform can do 16-bit
+ * and 32-bit accesses to the SMC91x device, but not 8-bit, set both
+ * SMC91X_USE_16BIT and SMC91X_USE_32BIT.
+ *
+ * The SMC91x driver requires at least one of SMC91X_USE_8BIT or
+ * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is
+ * an invalid configuration.
+ */
#define SMC91X_USE_8BIT (1 << 0)
#define SMC91X_USE_16BIT (1 << 1)
#define SMC91X_USE_32BIT (1 << 2)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 697e160..a4f7203 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -42,6 +42,8 @@
void __user *, size_t *, loff_t *);
extern int proc_dointvec(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
+extern int proc_douintvec(struct ctl_table *, int,
+ void __user *, size_t *, loff_t *);
extern int proc_dointvec_minmax(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_jiffies(struct ctl_table *, int,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index c00e7d5..7717302 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1523,6 +1523,8 @@
{
if (sk->sk_send_head == skb_unlinked)
sk->sk_send_head = NULL;
+ if (tcp_sk(sk)->highest_sack == skb_unlinked)
+ tcp_sk(sk)->highest_sack = NULL;
}
static inline void tcp_init_send_head(struct sock *sk)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 8e90dd2..e1f9673 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2115,22 +2115,17 @@
size_t len)
{
const void __user *p = udata->inbuf + offset;
- bool ret = false;
+ bool ret;
u8 *buf;
if (len > USHRT_MAX)
return false;
- buf = kmalloc(len, GFP_KERNEL);
- if (!buf)
+ buf = memdup_user(p, len);
+ if (IS_ERR(buf))
return false;
- if (copy_from_user(buf, p, len))
- goto free;
-
ret = !memchr_inv(buf, 0, len);
-
-free:
kfree(buf);
return ret;
}
diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h
index 9c9c6ad..5cd4d4d 100644
--- a/include/uapi/linux/atm_zatm.h
+++ b/include/uapi/linux/atm_zatm.h
@@ -14,6 +14,7 @@
#include <linux/atmapi.h>
#include <linux/atmioc.h>
+#include <linux/time.h>
#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc)
/* get pool statistics */
diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h
index 163e8ad..4bd1f55 100644
--- a/include/uapi/linux/if_pppol2tp.h
+++ b/include/uapi/linux/if_pppol2tp.h
@@ -16,7 +16,8 @@
#define _UAPI__LINUX_IF_PPPOL2TP_H
#include <linux/types.h>
-
+#include <linux/in.h>
+#include <linux/in6.h>
/* Structure used to connect() the socket to a particular tunnel UDP
* socket over IPv4.
diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h
index e128769..d37bbb1 100644
--- a/include/uapi/linux/if_pppox.h
+++ b/include/uapi/linux/if_pppox.h
@@ -21,8 +21,11 @@
#include <asm/byteorder.h>
#include <linux/socket.h>
+#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_pppol2tp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
/* For user-space programs to pick up these definitions
* which they wouldn't get otherwise without defining __KERNEL__
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 1046f55..777b6cd 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -2,6 +2,9 @@
#define _UAPI_IF_TUNNEL_H_
#include <linux/types.h>
+#include <linux/if.h>
+#include <linux/ip.h>
+#include <linux/in6.h>
#include <asm/byteorder.h>
diff --git a/include/uapi/linux/ipx.h b/include/uapi/linux/ipx.h
index 3d48014..30f031d 100644
--- a/include/uapi/linux/ipx.h
+++ b/include/uapi/linux/ipx.h
@@ -1,11 +1,13 @@
#ifndef _IPX_H_
#define _IPX_H_
+#include <linux/libc-compat.h> /* for compatibility with glibc netipx/ipx.h */
#include <linux/types.h>
#include <linux/sockios.h>
#include <linux/socket.h>
#define IPX_NODE_LEN 6
#define IPX_MTU 576
+#if __UAPI_DEF_SOCKADDR_IPX
struct sockaddr_ipx {
__kernel_sa_family_t sipx_family;
__be16 sipx_port;
@@ -14,6 +16,7 @@
__u8 sipx_type;
unsigned char sipx_zero; /* 16 byte fill */
};
+#endif /* __UAPI_DEF_SOCKADDR_IPX */
/*
* So we can fit the extra info for SIOCSIFADDR into the address nicely
@@ -23,12 +26,15 @@
#define IPX_DLTITF 0
#define IPX_CRTITF 1
+#if __UAPI_DEF_IPX_ROUTE_DEFINITION
struct ipx_route_definition {
__be32 ipx_network;
__be32 ipx_router_network;
unsigned char ipx_router_node[IPX_NODE_LEN];
};
+#endif /* __UAPI_DEF_IPX_ROUTE_DEFINITION */
+#if __UAPI_DEF_IPX_INTERFACE_DEFINITION
struct ipx_interface_definition {
__be32 ipx_network;
unsigned char ipx_device[16];
@@ -45,16 +51,20 @@
#define IPX_INTERNAL 2
unsigned char ipx_node[IPX_NODE_LEN];
};
-
+#endif /* __UAPI_DEF_IPX_INTERFACE_DEFINITION */
+
+#if __UAPI_DEF_IPX_CONFIG_DATA
struct ipx_config_data {
unsigned char ipxcfg_auto_select_primary;
unsigned char ipxcfg_auto_create_interfaces;
};
+#endif /* __UAPI_DEF_IPX_CONFIG_DATA */
/*
* OLD Route Definition for backward compatibility.
*/
+#if __UAPI_DEF_IPX_ROUTE_DEF
struct ipx_route_def {
__be32 ipx_network;
__be32 ipx_router_network;
@@ -67,6 +77,7 @@
#define IPX_RT_BLUEBOOK 2
#define IPX_RT_ROUTED 1
};
+#endif /* __UAPI_DEF_IPX_ROUTE_DEF */
#define SIOCAIPXITFCRT (SIOCPROTOPRIVATE)
#define SIOCAIPXPRISLT (SIOCPROTOPRIVATE + 1)
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index e4f048e..44b8a6b 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -139,6 +139,25 @@
#endif /* _NETINET_IN_H */
+/* Coordinate with glibc netipx/ipx.h header. */
+#if defined(__NETIPX_IPX_H)
+
+#define __UAPI_DEF_SOCKADDR_IPX 0
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 0
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 0
+#define __UAPI_DEF_IPX_CONFIG_DATA 0
+#define __UAPI_DEF_IPX_ROUTE_DEF 0
+
+#else /* defined(__NETIPX_IPX_H) */
+
+#define __UAPI_DEF_SOCKADDR_IPX 1
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1
+#define __UAPI_DEF_IPX_CONFIG_DATA 1
+#define __UAPI_DEF_IPX_ROUTE_DEF 1
+
+#endif /* defined(__NETIPX_IPX_H) */
+
/* Definitions for xattr.h */
#if defined(_SYS_XATTR_H)
#define __UAPI_DEF_XATTR 0
@@ -179,6 +198,13 @@
#define __UAPI_DEF_IN6_PKTINFO 1
#define __UAPI_DEF_IP6_MTUINFO 1
+/* Definitions for ipx.h */
+#define __UAPI_DEF_SOCKADDR_IPX 1
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1
+#define __UAPI_DEF_IPX_CONFIG_DATA 1
+#define __UAPI_DEF_IPX_ROUTE_DEF 1
+
/* Definitions for xattr.h */
#define __UAPI_DEF_XATTR 1
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index d95a301..54c3b4f 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -583,7 +583,7 @@
#define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
struct ovs_action_trunc {
- uint32_t max_len; /* Max packet size in bytes. */
+ __u32 max_len; /* Max packet size in bytes. */
};
/**
@@ -632,8 +632,8 @@
* @hash_basis: basis used for computing hash.
*/
struct ovs_action_hash {
- uint32_t hash_alg; /* One of ovs_hash_alg. */
- uint32_t hash_basis;
+ __u32 hash_alg; /* One of ovs_hash_alg. */
+ __u32 hash_basis;
};
/**
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 9a37c541..b5486e6 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -9,8 +9,8 @@
DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
-DECLARE_PER_CPU(int, xen_vcpu_id);
-static inline int xen_vcpu_nr(int cpu)
+DECLARE_PER_CPU(uint32_t, xen_vcpu_id);
+static inline uint32_t xen_vcpu_nr(int cpu)
{
return per_cpu(xen_vcpu_id, cpu);
}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index c7fd277..c27e533 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2069,6 +2069,20 @@
mutex_unlock(&cpuset_mutex);
}
+/*
+ * Make sure the new task conform to the current state of its parent,
+ * which could have been changed by cpuset just after it inherits the
+ * state from the parent and before it sits on the cgroup's task list.
+ */
+void cpuset_fork(struct task_struct *task)
+{
+ if (task_css_is_root(task, cpuset_cgrp_id))
+ return;
+
+ set_cpus_allowed_ptr(task, ¤t->cpus_allowed);
+ task->mems_allowed = current->mems_allowed;
+}
+
struct cgroup_subsys cpuset_cgrp_subsys = {
.css_alloc = cpuset_css_alloc,
.css_online = cpuset_css_online,
@@ -2079,6 +2093,7 @@
.attach = cpuset_attach,
.post_attach = cpuset_post_attach,
.bind = cpuset_bind,
+ .fork = cpuset_fork,
.legacy_cftypes = files,
.early_init = true,
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5650f53..3cfabdf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6166,7 +6166,7 @@
{
struct perf_event *event = info;
struct pmu *pmu = event->pmu;
- struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
struct remote_output ro = {
.rb = event->rb,
};
diff --git a/kernel/fork.c b/kernel/fork.c
index 52e725d4..aaf7823 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1404,7 +1404,6 @@
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
- threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
@@ -1556,6 +1555,7 @@
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
@@ -1656,6 +1656,7 @@
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p);
bad_fork_free_pid:
+ threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
@@ -1688,7 +1689,6 @@
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
- threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f689593..32f6cfc 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -39,6 +39,7 @@
return NULL;
}
+ get_online_cpus();
if (max_vecs >= num_online_cpus()) {
cpumask_copy(affinity_mask, cpu_online_mask);
*nr_vecs = num_online_cpus();
@@ -56,6 +57,7 @@
}
*nr_vecs = vecs;
}
+ put_online_cpus();
return affinity_mask;
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b4c1bc7..6373890 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -820,6 +820,17 @@
desc->name = name;
if (handle != handle_bad_irq && is_chained) {
+ /*
+ * We're about to start this interrupt immediately,
+ * hence the need to set the trigger configuration.
+ * But the .set_type callback may have overridden the
+ * flow handler, ignoring that we're dealing with a
+ * chained interrupt. Reset it immediately because we
+ * do know better.
+ */
+ __irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data));
+ desc->handle_irq = handle;
+
irq_settings_set_noprobe(desc);
irq_settings_set_norequest(desc);
irq_settings_set_nothread(desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 73a2b78..9530fcd 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1681,8 +1681,10 @@
action->dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
- if (retval < 0)
+ if (retval < 0) {
+ kfree(action);
return retval;
+ }
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
@@ -1985,8 +1987,10 @@
action->percpu_dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
- if (retval < 0)
+ if (retval < 0) {
+ kfree(action);
return retval;
+ }
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index 276762f..d5760c4 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -9,10 +9,10 @@
char *_braille_console_setup(char **str, char **brl_options)
{
- if (!memcmp(*str, "brl,", 4)) {
+ if (!strncmp(*str, "brl,", 4)) {
*brl_options = "";
*str += 4;
- } else if (!memcmp(str, "brl=", 4)) {
+ } else if (!strncmp(*str, "brl=", 4)) {
*brl_options = *str + 4;
*str = strchr(*brl_options, ',');
if (!*str)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b43d0b2..a13bbda 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2140,6 +2140,21 @@
return 0;
}
+static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
+ int *valp,
+ int write, void *data)
+{
+ if (write) {
+ if (*negp)
+ return -EINVAL;
+ *valp = *lvalp;
+ } else {
+ unsigned int val = *valp;
+ *lvalp = (unsigned long)val;
+ }
+ return 0;
+}
+
static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
@@ -2259,8 +2274,27 @@
int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,buffer,lenp,ppos,
- NULL,NULL);
+ return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
+/**
+ * proc_douintvec - read a vector of unsigned integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
+ do_proc_douintvec_conv, NULL);
}
/*
@@ -2858,6 +2892,12 @@
return -ENOSYS;
}
+int proc_douintvec(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+
int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -2903,6 +2943,7 @@
* exception granted :-)
*/
EXPORT_SYMBOL(proc_dointvec);
+EXPORT_SYMBOL(proc_douintvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
EXPORT_SYMBOL(proc_dointvec_minmax);
EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3b65746..e07fb09 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -401,7 +401,10 @@
do {
seq = raw_read_seqcount_latch(&tkf->seq);
tkr = tkf->base + (seq & 0x01);
- now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+ now = ktime_to_ns(tkr->base);
+
+ now += clocksource_delta(tkr->read(tkr->clock),
+ tkr->cycle_last, tkr->mask);
} while (read_seqcount_retry(&tkf->seq, seq));
return now;
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index f6bd652..107310a 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -23,7 +23,9 @@
#include "timekeeping_internal.h"
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
{
@@ -69,6 +71,9 @@
void tk_debug_account_sleep_time(struct timespec64 *t)
{
- sleep_time_bin[fls(t->tv_sec)]++;
+ /* Cap bin index so we don't overflow the array */
+ int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+ sleep_time_bin[bin]++;
}
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7598e6c..dbafc5d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -223,7 +223,7 @@
what |= MASK_TC_BIT(op_flags, META);
what |= MASK_TC_BIT(op_flags, PREFLUSH);
what |= MASK_TC_BIT(op_flags, FUA);
- if (op == REQ_OP_DISCARD)
+ if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
what |= BLK_TC_ACT(BLK_TC_DISCARD);
if (op == REQ_OP_FLUSH)
what |= BLK_TC_ACT(BLK_TC_FLUSH);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2307d7c..2e2cca5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1686,24 +1686,6 @@
Enable this option if you want to use the LatencyTOP tool
to find out which userspace is blocking on what kernel operations.
-config ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
- bool
-
-config DEBUG_STRICT_USER_COPY_CHECKS
- bool "Strict user copy size checks"
- depends on ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
- depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING
- help
- Enabling this option turns a certain set of sanity checks for user
- copy operations into compile time failures.
-
- The copy_from_user() etc checks are there to help test if there
- are sufficient security checks on the length argument of
- the copy operation, by having gcc prove that the argument is
- within bounds.
-
- If unsure, say N.
-
source kernel/trace/Kconfig
menu "Runtime Testing"
diff --git a/lib/Makefile b/lib/Makefile
index cfa68eb..5dc77a8 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -24,7 +24,6 @@
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o
-obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
lib-$(CONFIG_HAS_DMA) += dma-noop.o
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 5ba520b..56054e5 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -77,17 +77,18 @@
size = min_t(unsigned int, size, tbl->size >> 1);
if (sizeof(spinlock_t) != 0) {
+ tbl->locks = NULL;
#ifdef CONFIG_NUMA
if (size * sizeof(spinlock_t) > PAGE_SIZE &&
gfp == GFP_KERNEL)
tbl->locks = vmalloc(size * sizeof(spinlock_t));
- else
#endif
if (gfp != GFP_KERNEL)
gfp |= __GFP_NOWARN | __GFP_NORETRY;
- tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
- gfp);
+ if (!tbl->locks)
+ tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
+ gfp);
if (!tbl->locks)
return -ENOMEM;
for (i = 0; i < size; i++)
diff --git a/lib/usercopy.c b/lib/usercopy.c
deleted file mode 100644
index 4f5b1dd..0000000
--- a/lib/usercopy.c
+++ /dev/null
@@ -1,9 +0,0 @@
-#include <linux/export.h>
-#include <linux/bug.h>
-#include <linux/uaccess.h>
-
-void copy_from_user_overflow(void)
-{
- WARN(1, "Buffer overflow detected!\n");
-}
-EXPORT_SYMBOL(copy_from_user_overflow);
diff --git a/mm/Kconfig b/mm/Kconfig
index 78a23c5..be0ee11 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -262,7 +262,14 @@
select MIGRATION
depends on MMU
help
- Allows the compaction of memory for the allocation of huge pages.
+ Compaction is the only memory management component to form
+ high order (larger physically contiguous) memory blocks
+ reliably. The page allocator relies on compaction heavily and
+ the lack of the feature can lead to unexpected OOM killer
+ invocations for high order memory requests. You shouldn't
+ disable this option unless there really is a strong reason for
+ it and then we would be really interested to hear about that at
+ linux-mm@kvack.org.
#
# support for page migration
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2373f0a..2db2112 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1512,7 +1512,7 @@
struct page *page;
pgtable_t pgtable;
pmd_t _pmd;
- bool young, write, dirty;
+ bool young, write, dirty, soft_dirty;
unsigned long addr;
int i;
@@ -1546,6 +1546,7 @@
write = pmd_write(*pmd);
young = pmd_young(*pmd);
dirty = pmd_dirty(*pmd);
+ soft_dirty = pmd_soft_dirty(*pmd);
pmdp_huge_split_prepare(vma, haddr, pmd);
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
@@ -1562,6 +1563,8 @@
swp_entry_t swp_entry;
swp_entry = make_migration_entry(page + i, write);
entry = swp_entry_to_pte(swp_entry);
+ if (soft_dirty)
+ entry = pte_swp_mksoft_dirty(entry);
} else {
entry = mk_pte(page + i, vma->vm_page_prot);
entry = maybe_mkwrite(entry, vma);
@@ -1569,6 +1572,8 @@
entry = pte_wrprotect(entry);
if (!young)
entry = pte_mkold(entry);
+ if (soft_dirty)
+ entry = pte_mksoft_dirty(entry);
}
if (dirty)
SetPageDirty(page + i);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2ff0289..9a6a51a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4082,24 +4082,6 @@
atomic_add(n, &memcg->id.ref);
}
-static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
-{
- while (!atomic_inc_not_zero(&memcg->id.ref)) {
- /*
- * The root cgroup cannot be destroyed, so it's refcount must
- * always be >= 1.
- */
- if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
- VM_BUG_ON(1);
- break;
- }
- memcg = parent_mem_cgroup(memcg);
- if (!memcg)
- memcg = root_mem_cgroup;
- }
- return memcg;
-}
-
static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
{
if (atomic_sub_and_test(n, &memcg->id.ref)) {
@@ -5821,6 +5803,24 @@
subsys_initcall(mem_cgroup_init);
#ifdef CONFIG_MEMCG_SWAP
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
+{
+ while (!atomic_inc_not_zero(&memcg->id.ref)) {
+ /*
+ * The root cgroup cannot be destroyed, so it's refcount must
+ * always be >= 1.
+ */
+ if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+ VM_BUG_ON(1);
+ break;
+ }
+ memcg = parent_mem_cgroup(memcg);
+ if (!memcg)
+ memcg = root_mem_cgroup;
+ }
+ return memcg;
+}
+
/**
* mem_cgroup_swapout - transfer a memsw charge to swap
* @page: page whose memsw charge to transfer
diff --git a/mm/readahead.c b/mm/readahead.c
index 65ec288..c8a955b 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,6 +8,7 @@
*/
#include <linux/kernel.h>
+#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/blkdev.h>
@@ -544,6 +545,14 @@
if (!mapping || !mapping->a_ops)
return -EINVAL;
+ /*
+ * Readahead doesn't make sense for DAX inodes, but we don't want it
+ * to report a failure either. Instead, we just return success and
+ * don't do any work.
+ */
+ if (dax_mapping(mapping))
+ return 0;
+
return force_page_cache_readahead(mapping, filp, index, nr);
}
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 8ebae91..a3cc305 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -83,7 +83,7 @@
unsigned long check_high = check_low + n;
/* Does not overlap if entirely above or entirely below. */
- if (check_low >= high || check_high < low)
+ if (check_low >= high || check_high <= low)
return false;
return true;
@@ -124,7 +124,7 @@
static inline const char *check_bogus_address(const void *ptr, unsigned long n)
{
/* Reject if object wraps past end of memory. */
- if (ptr + n < ptr)
+ if ((unsigned long)ptr + n < (unsigned long)ptr)
return "<wrapped address>";
/* Reject if NULL or ZERO-allocation. */
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index ece45e0..0b5f729 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -250,7 +250,7 @@
skb_free_datagram(sk, skb);
- if (msg->msg_flags & MSG_TRUNC)
+ if (flags & MSG_TRUNC)
copied = skblen;
return err ? : copied;
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index c045b3c..b0e23df 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -262,6 +262,8 @@
break;
}
+ kfree_skb(hdev->req_skb);
+ hdev->req_skb = NULL;
hdev->req_status = hdev->req_result = 0;
BT_DBG("%s end: err %d", hdev->name, err);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 6ef8a01..96f04b7 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1091,7 +1091,7 @@
skb_free_datagram(sk, skb);
- if (msg->msg_flags & MSG_TRUNC)
+ if (flags & MSG_TRUNC)
copied = skblen;
return err ? : copied;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 54ceb1f..d4cad29b0 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -32,6 +32,7 @@
#include <linux/debugfs.h>
#include <linux/crc16.h>
+#include <linux/filter.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -5835,6 +5836,9 @@
if (chan->sdu)
break;
+ if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE))
+ break;
+
chan->sdu_len = get_unaligned_le16(skb->data);
skb_pull(skb, L2CAP_SDULEN_SIZE);
@@ -6610,6 +6614,10 @@
goto drop;
}
+ if ((chan->mode == L2CAP_MODE_ERTM ||
+ chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb))
+ goto drop;
+
if (!control->sframe) {
int err;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1842141..a8ba752 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1019,7 +1019,7 @@
goto done;
if (pi->rx_busy_skb) {
- if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb))
+ if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb))
pi->rx_busy_skb = NULL;
else
goto done;
@@ -1270,7 +1270,17 @@
goto done;
}
- err = sock_queue_rcv_skb(sk, skb);
+ if (chan->mode != L2CAP_MODE_ERTM &&
+ chan->mode != L2CAP_MODE_STREAMING) {
+ /* Even if no filter is attached, we could potentially
+ * get errors from security modules, etc.
+ */
+ err = sk_filter(sk, skb);
+ if (err)
+ goto done;
+ }
+
+ err = __sock_queue_rcv_skb(sk, skb);
/* For ERTM, handle one skb that doesn't fit into the recv
* buffer. This is important to do because the data frames
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index febca0f..e2ffc2a 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -249,7 +249,7 @@
* index into the parent's child array. That is, they will be used to find
* 'n' among tp's children.
*
- * The bits from (n->pos + n->bits) to (tn->pos - 1) - "S" - are skipped bits
+ * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits
* for the node n.
*
* All the bits we have seen so far are significant to the node n. The rest
@@ -258,7 +258,7 @@
* The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into
* n's child array, and will of course be different for each child.
*
- * The rest of the bits, from 0 to (n->pos + n->bits), are completely unknown
+ * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown
* at this point.
*/
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 9d847c3..0f227db 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -73,9 +73,11 @@
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- if (skb_iif && proto == IPPROTO_UDP) {
- /* Arrived from an ingress interface and got udp encapuslated.
- * The encapsulated network segment length may exceed dst mtu.
+ if (skb_iif && !(df & htons(IP_DF))) {
+ /* Arrived from an ingress interface, got encapsulated, with
+ * fragmentation of encapulating frames allowed.
+ * If skb is gso, the resulting encapsulated network segments
+ * may exceed dst mtu.
* Allow IP Fragmentation of segments.
*/
IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 032a96d..ffbb218 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3193,7 +3193,6 @@
local_bh_enable();
return 0;
}
- sock_gen_put(sk);
return -EOPNOTSUPP;
}
@@ -3222,7 +3221,6 @@
bh_unlock_sock(sk);
local_bh_enable();
release_sock(sk);
- sock_put(sk);
return 0;
}
EXPORT_SYMBOL_GPL(tcp_abort);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 4d61093..a748c74 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -54,11 +54,16 @@
{
struct net *net = sock_net(in_skb->sk);
struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req);
+ int err;
if (IS_ERR(sk))
return PTR_ERR(sk);
- return sock_diag_destroy(sk, ECONNABORTED);
+ err = sock_diag_destroy(sk, ECONNABORTED);
+
+ sock_gen_put(sk);
+
+ return err;
}
#endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 32b048e..7158d4f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -814,8 +814,14 @@
u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
tcp_sk(sk)->snd_nxt;
+ /* RFC 7323 2.3
+ * The window field (SEG.WND) of every outgoing segment, with the
+ * exception of <SYN> segments, MUST be right-shifted by
+ * Rcv.Wind.Shift bits:
+ */
tcp_v4_send_ack(sock_net(sk), skb, seq,
- tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+ tcp_rsk(req)->rcv_nxt,
+ req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp,
req->ts_recent,
0,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e61f7cd..5fdcb8d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1182,13 +1182,13 @@
* @sk: socket
*
* Drops all bad checksum frames, until a valid one is found.
- * Returns the length of found skb, or 0 if none is found.
+ * Returns the length of found skb, or -1 if none is found.
*/
-static unsigned int first_packet_length(struct sock *sk)
+static int first_packet_length(struct sock *sk)
{
struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue;
struct sk_buff *skb;
- unsigned int res;
+ int res;
__skb_queue_head_init(&list_kill);
@@ -1203,7 +1203,7 @@
__skb_unlink(skb, rcvq);
__skb_queue_tail(&list_kill, skb);
}
- res = skb ? skb->len : 0;
+ res = skb ? skb->len : -1;
spin_unlock_bh(&rcvq->lock);
if (!skb_queue_empty(&list_kill)) {
@@ -1232,7 +1232,7 @@
case SIOCINQ:
{
- unsigned int amount = first_packet_length(sk);
+ int amount = max_t(int, 0, first_packet_length(sk));
return put_user(amount, (int __user *)arg);
}
@@ -2184,7 +2184,7 @@
/* Check for false positives due to checksum errors */
if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
- !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk))
+ !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(POLLIN | POLLRDNORM);
return mask;
@@ -2216,7 +2216,6 @@
.sysctl_wmem = &sysctl_udp_wmem_min,
.sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 3b3efbd..2eea073 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -55,7 +55,6 @@
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,
.obj_size = sizeof(struct udp_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index df8425f..f418d2e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1872,7 +1872,6 @@
void addrconf_dad_failure(struct inet6_ifaddr *ifp)
{
- struct in6_addr addr;
struct inet6_dev *idev = ifp->idev;
struct net *net = dev_net(ifp->idev->dev);
@@ -1934,18 +1933,6 @@
in6_ifa_put(ifp2);
lock_errdad:
spin_lock_bh(&ifp->lock);
- } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) {
- addr.s6_addr32[0] = htonl(0xfe800000);
- addr.s6_addr32[1] = 0;
-
- if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
- ipv6_addr_equal(&ifp->addr, &addr)) {
- /* DAD failed for link-local based on MAC address */
- idev->cnf.disable_ipv6 = 1;
-
- pr_info("%s: IPv6 being disabled!\n",
- ifp->idev->dev->name);
- }
}
errdad:
@@ -3821,6 +3808,7 @@
dad_work);
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
+ bool disable_ipv6 = false;
enum {
DAD_PROCESS,
@@ -3837,6 +3825,24 @@
} else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
action = DAD_ABORT;
ifp->state = INET6_IFADDR_STATE_POSTDAD;
+
+ if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 &&
+ !(ifp->flags & IFA_F_STABLE_PRIVACY)) {
+ struct in6_addr addr;
+
+ addr.s6_addr32[0] = htonl(0xfe800000);
+ addr.s6_addr32[1] = 0;
+
+ if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
+ ipv6_addr_equal(&ifp->addr, &addr)) {
+ /* DAD failed for link-local based on MAC */
+ idev->cnf.disable_ipv6 = 1;
+
+ pr_info("%s: IPv6 being disabled!\n",
+ ifp->idev->dev->name);
+ disable_ipv6 = true;
+ }
+ }
}
spin_unlock_bh(&ifp->lock);
@@ -3845,6 +3851,8 @@
goto out;
} else if (action == DAD_ABORT) {
addrconf_dad_stop(ifp, 1);
+ if (disable_ipv6)
+ addrconf_ifdown(idev->dev, 0);
goto out;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 33df8b8..94f4f89 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -944,9 +944,15 @@
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
+ /* RFC 7323 2.3
+ * The window field (SEG.WND) of every outgoing segment, with the
+ * exception of <SYN> segments, MUST be right-shifted by
+ * Rcv.Wind.Shift bits:
+ */
tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
- tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+ tcp_rsk(req)->rcv_nxt,
+ req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
0, 0);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 81e2f98..19ac3a1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1460,7 +1460,6 @@
.sysctl_wmem = &sysctl_udp_wmem_min,
.sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udpv6_setsockopt,
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 9cf097e..fd6ef41 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -50,7 +50,6 @@
.unhash = udp_lib_unhash,
.get_port = udp_v6_get_port,
.obj_size = sizeof(struct udp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udpv6_setsockopt,
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index d9560aa..232cb92 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -856,7 +856,7 @@
error = -ENOTCONN;
if (sk == NULL)
goto end;
- if (sk->sk_state != PPPOX_CONNECTED)
+ if (!(sk->sk_state & PPPOX_CONNECTED))
goto end;
error = -EBADF;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 958a145..9f267c3 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -205,6 +205,7 @@
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
const struct nf_conntrack_l3proto *l3proto;
const struct nf_conntrack_l4proto *l4proto;
+ struct net *net = seq_file_net(s);
int ret = 0;
NF_CT_ASSERT(ct);
@@ -215,6 +216,9 @@
if (NF_CT_DIRECTION(hash))
goto release;
+ if (!net_eq(nf_ct_net(ct), net))
+ goto release;
+
l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
NF_CT_ASSERT(l3proto);
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 1b4de4b..70eb2f6a 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -326,14 +326,14 @@
{
int ret = 0;
- /* we want to avoid races with nfnl_acct_find_get. */
- if (atomic_dec_and_test(&cur->refcnt)) {
+ /* We want to avoid races with nfnl_acct_put. So only when the current
+ * refcnt is 1, we decrease it to 0.
+ */
+ if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) {
/* We are protected by nfnl mutex. */
list_del_rcu(&cur->head);
kfree_rcu(cur, rcu_head);
} else {
- /* still in use, restore reference counter. */
- atomic_inc(&cur->refcnt);
ret = -EBUSY;
}
return ret;
@@ -443,7 +443,7 @@
}
EXPORT_SYMBOL_GPL(nfnl_acct_update);
-static void nfnl_overquota_report(struct nf_acct *nfacct)
+static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct)
{
int ret;
struct sk_buff *skb;
@@ -458,11 +458,12 @@
kfree_skb(skb);
return;
}
- netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
+ netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
GFP_ATOMIC);
}
-int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct)
+int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb,
+ struct nf_acct *nfacct)
{
u64 now;
u64 *quota;
@@ -480,7 +481,7 @@
if (now >= *quota &&
!test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) {
- nfnl_overquota_report(nfacct);
+ nfnl_overquota_report(net, nfacct);
}
return ret;
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 4cdcd96..68216cd 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -330,16 +330,16 @@
{
int ret = 0;
- /* we want to avoid races with nf_ct_timeout_find_get. */
- if (atomic_dec_and_test(&timeout->refcnt)) {
+ /* We want to avoid races with ctnl_timeout_put. So only when the
+ * current refcnt is 1, we decrease it to 0.
+ */
+ if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) {
/* We are protected by nfnl mutex. */
list_del_rcu(&timeout->head);
nf_ct_l4proto_put(timeout->l4proto);
ctnl_untimeout(net, timeout);
kfree_rcu(timeout, rcu_head);
} else {
- /* still in use, restore reference counter. */
- atomic_inc(&timeout->refcnt);
ret = -EBUSY;
}
return ret;
@@ -543,7 +543,9 @@
static void ctnl_timeout_put(struct ctnl_timeout *timeout)
{
- atomic_dec(&timeout->refcnt);
+ if (atomic_dec_and_test(&timeout->refcnt))
+ kfree_rcu(timeout, rcu_head);
+
module_put(THIS_MODULE);
}
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
@@ -591,7 +593,9 @@
list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) {
list_del_rcu(&cur->head);
nf_ct_l4proto_put(cur->l4proto);
- kfree_rcu(cur, rcu_head);
+
+ if (atomic_dec_and_test(&cur->refcnt))
+ kfree_rcu(cur, rcu_head);
}
}
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index cbcfdfb..6577db5 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1147,6 +1147,7 @@
MODULE_ALIAS_NF_LOGGER(AF_INET, 1);
MODULE_ALIAS_NF_LOGGER(AF_INET6, 1);
MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1);
+MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */
module_init(nfnetlink_log_init);
module_exit(nfnetlink_log_fini);
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 7f4414d..663c4c3 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -127,6 +127,8 @@
daddr, dport,
in->ifindex);
+ if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
@@ -195,6 +197,8 @@
daddr, ntohs(dport),
in->ifindex);
+ if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
index 3048a7e..cf32759 100644
--- a/net/netfilter/xt_nfacct.c
+++ b/net/netfilter/xt_nfacct.c
@@ -26,7 +26,7 @@
nfnl_acct_update(skb, info->nfacct);
- overquota = nfnl_acct_overquota(skb, info->nfacct);
+ overquota = nfnl_acct_overquota(par->net, skb, info->nfacct);
return overquota == NFACCT_UNDERQUOTA ? false : true;
}
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 141a06e..e87cd81 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -53,7 +53,7 @@
u32 *tlv = (u32 *)(skbdata);
u16 totlen = nla_total_size(dlen); /*alignment + hdr */
char *dptr = (char *)tlv + NLA_HDRLEN;
- u32 htlv = attrtype << 16 | totlen;
+ u32 htlv = attrtype << 16 | dlen;
*tlv = htonl(htlv);
memset(dptr, 0, totlen - NLA_HDRLEN);
@@ -135,7 +135,7 @@
int ife_validate_meta_u32(void *val, int len)
{
- if (len == 4)
+ if (len == sizeof(u32))
return 0;
return -EINVAL;
@@ -144,8 +144,8 @@
int ife_validate_meta_u16(void *val, int len)
{
- /* length will include padding */
- if (len == NLA_ALIGN(2))
+ /* length will not include padding */
+ if (len == sizeof(u16))
return 0;
return -EINVAL;
@@ -652,12 +652,14 @@
u8 *tlvdata = (u8 *)tlv;
u16 mtype = tlv->type;
u16 mlen = tlv->len;
+ u16 alen;
mtype = ntohs(mtype);
mlen = ntohs(mlen);
+ alen = NLA_ALIGN(mlen);
- if (find_decode_metaid(skb, ife, mtype, (mlen - 4),
- (void *)(tlvdata + 4))) {
+ if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN),
+ (void *)(tlvdata + NLA_HDRLEN))) {
/* abuse overlimits to count when we receive metadata
* but dont have an ops for it
*/
@@ -666,8 +668,8 @@
ife->tcf_qstats.overlimits++;
}
- tlvdata += mlen;
- ifehdrln -= mlen;
+ tlvdata += alen;
+ ifehdrln -= alen;
tlv = (struct meta_tlvhdr *)tlvdata;
}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index e95b67c..657c133 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -643,18 +643,19 @@
struct Qdisc *sch;
if (!try_module_get(ops->owner))
- goto errout;
+ return NULL;
sch = qdisc_alloc(dev_queue, ops);
- if (IS_ERR(sch))
- goto errout;
+ if (IS_ERR(sch)) {
+ module_put(ops->owner);
+ return NULL;
+ }
sch->parent = parentid;
if (!ops->init || ops->init(sch, NULL) == 0)
return sch;
qdisc_destroy(sch);
-errout:
return NULL;
}
EXPORT_SYMBOL(qdisc_create_dflt);
diff --git a/net/sctp/input.c b/net/sctp/input.c
index c182db7..69444d3 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -119,7 +119,13 @@
skb_transport_offset(skb))
goto discard_it;
- if (!pskb_may_pull(skb, sizeof(struct sctphdr)))
+ /* If the packet is fragmented and we need to do crc checking,
+ * it's better to just linearize it otherwise crc computing
+ * takes longer.
+ */
+ if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) &&
+ skb_linearize(skb)) ||
+ !pskb_may_pull(skb, sizeof(struct sctphdr)))
goto discard_it;
/* Pull up the IP header. */
@@ -1177,9 +1183,6 @@
if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP)
return NULL;
- if (skb_linearize(skb))
- return NULL;
-
ch = (sctp_chunkhdr_t *) skb->data;
/* The code below will attempt to walk the chunk and extract
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index c30ddb0..6437aa9 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -170,19 +170,6 @@
chunk = list_entry(entry, struct sctp_chunk, list);
- /* Linearize if it's not GSO */
- if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP &&
- skb_is_nonlinear(chunk->skb)) {
- if (skb_linearize(chunk->skb)) {
- __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS);
- sctp_chunk_free(chunk);
- goto next_chunk;
- }
-
- /* Update sctp_hdr as it probably changed */
- chunk->sctp_hdr = sctp_hdr(chunk->skb);
- }
-
if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) {
/* GSO-marked skbs but without frags, handle
* them normally
diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index bb69153..f3508aa 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -424,11 +424,13 @@
paddr.v4.sin_family = AF_INET;
} else {
laddr.v6.sin6_port = req->id.idiag_sport;
- memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, 64);
+ memcpy(&laddr.v6.sin6_addr, req->id.idiag_src,
+ sizeof(laddr.v6.sin6_addr));
laddr.v6.sin6_family = AF_INET6;
paddr.v6.sin6_port = req->id.idiag_dport;
- memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, 64);
+ memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst,
+ sizeof(paddr.v6.sin6_addr));
paddr.v6.sin6_family = AF_INET6;
}
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 7f79fb7..66f23b3 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -453,7 +453,7 @@
struct rpc_xprt_switch *xps;
if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) {
- WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+ WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC));
xps = args->bc_xprt->xpt_bc_xps;
xprt_switch_get(xps);
} else {
@@ -520,7 +520,7 @@
char servername[48];
if (args->bc_xprt) {
- WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+ WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC));
xprt = args->bc_xprt->xpt_bc_xprt;
if (xprt) {
xprt_get(xprt);
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index b016c01..ae7e14c 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -396,10 +396,13 @@
tuncfg.encap_destroy = NULL;
setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg);
- if (enable_mcast(ub, remote))
+ err = enable_mcast(ub, remote);
+ if (err)
goto err;
return 0;
err:
+ if (ub->ubsock)
+ udp_tunnel_sock_release(ub->ubsock);
kfree(ub);
return err;
}
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 49a00d5..aed4511 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -2136,9 +2136,11 @@
my $cmd = $VCS_cmds{"file_exists_cmd"};
$cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd
-
+ $cmd .= " 2>&1";
$exists = &{$VCS_cmds{"execute_cmd"}}($cmd);
+ return 0 if ($? != 0);
+
return $exists;
}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 574b1b4..7100f05 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4828,7 +4828,7 @@
ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC292_FIXUP_TPT440_DOCK,
ALC292_FIXUP_TPT440,
- ALC283_FIXUP_BXBT2807_MIC,
+ ALC283_FIXUP_HEADSET_MIC,
ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
ALC282_FIXUP_ASPIRE_V5_PINS,
ALC280_FIXUP_HP_GPIO4,
@@ -5321,7 +5321,7 @@
.chained = true,
.chain_id = ALC292_FIXUP_TPT440_DOCK,
},
- [ALC283_FIXUP_BXBT2807_MIC] = {
+ [ALC283_FIXUP_HEADSET_MIC] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
{ 0x19, 0x04a110f0 },
@@ -5651,7 +5651,8 @@
SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN),
SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
- SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC),
+ SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 54c09ac..16e459a 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -299,8 +299,9 @@
clk_enable(ssc_p->ssc->clk);
ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk);
- /* Reset the SSC to keep it at a clean status */
- ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
+ /* Reset the SSC unless initialized to keep it in a clean state */
+ if (!ssc_p->initialized)
+ ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
dir = 0;
diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c
index e5527bc..bcf1834 100644
--- a/sound/soc/codecs/da7213.c
+++ b/sound/soc/codecs/da7213.c
@@ -1247,8 +1247,8 @@
return -EINVAL;
}
- /* By default only 32 BCLK per WCLK is supported */
- dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_32;
+ /* By default only 64 BCLK per WCLK is supported */
+ dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_64;
snd_soc_write(codec, DA7213_DAI_CLK_MODE, dai_clk_mode);
snd_soc_update_bits(codec, DA7213_DAI_CTRL, DA7213_DAI_FORMAT_MASK,
diff --git a/sound/soc/codecs/max98371.c b/sound/soc/codecs/max98371.c
index cf0a39b..02352ed 100644
--- a/sound/soc/codecs/max98371.c
+++ b/sound/soc/codecs/max98371.c
@@ -412,6 +412,7 @@
static const struct i2c_device_id max98371_i2c_id[] = {
{ "max98371", 0 },
+ { }
};
MODULE_DEVICE_TABLE(i2c, max98371_i2c_id);
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index 5c9707a..2e59a85 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -212,31 +212,6 @@
0xfa2f, 0xfaea, 0xfba5, 0xfc60, 0xfd1a, 0xfdd4, 0xfe8e, 0xff47
};
-static struct snd_soc_dai *nau8825_get_codec_dai(struct nau8825 *nau8825)
-{
- struct snd_soc_codec *codec = snd_soc_dapm_to_codec(nau8825->dapm);
- struct snd_soc_component *component = &codec->component;
- struct snd_soc_dai *codec_dai, *_dai;
-
- list_for_each_entry_safe(codec_dai, _dai, &component->dai_list, list) {
- if (!strncmp(codec_dai->name, NUVOTON_CODEC_DAI,
- strlen(NUVOTON_CODEC_DAI)))
- return codec_dai;
- }
- return NULL;
-}
-
-static bool nau8825_dai_is_active(struct nau8825 *nau8825)
-{
- struct snd_soc_dai *codec_dai = nau8825_get_codec_dai(nau8825);
-
- if (codec_dai) {
- if (codec_dai->playback_active || codec_dai->capture_active)
- return true;
- }
- return false;
-}
-
/**
* nau8825_sema_acquire - acquire the semaphore of nau88l25
* @nau8825: component to register the codec private data with
@@ -250,19 +225,26 @@
* Acquires the semaphore without jiffies. If no more tasks are allowed
* to acquire the semaphore, calling this function will put the task to
* sleep until the semaphore is released.
- * It returns if the semaphore was acquired.
+ * If the semaphore is not released within the specified number of jiffies,
+ * this function returns -ETIME.
+ * If the sleep is interrupted by a signal, this function will return -EINTR.
+ * It returns 0 if the semaphore was acquired successfully.
*/
-static void nau8825_sema_acquire(struct nau8825 *nau8825, long timeout)
+static int nau8825_sema_acquire(struct nau8825 *nau8825, long timeout)
{
int ret;
- if (timeout)
+ if (timeout) {
ret = down_timeout(&nau8825->xtalk_sem, timeout);
- else
+ if (ret < 0)
+ dev_warn(nau8825->dev, "Acquire semaphone timeout\n");
+ } else {
ret = down_interruptible(&nau8825->xtalk_sem);
+ if (ret < 0)
+ dev_warn(nau8825->dev, "Acquire semaphone fail\n");
+ }
- if (ret < 0)
- dev_warn(nau8825->dev, "Acquire semaphone fail\n");
+ return ret;
}
/**
@@ -1205,6 +1187,8 @@
struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
unsigned int val_len = 0;
+ nau8825_sema_acquire(nau8825, 2 * HZ);
+
switch (params_width(params)) {
case 16:
val_len |= NAU8825_I2S_DL_16;
@@ -1225,6 +1209,9 @@
regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL1,
NAU8825_I2S_DL_MASK, val_len);
+ /* Release the semaphone. */
+ nau8825_sema_release(nau8825);
+
return 0;
}
@@ -1234,6 +1221,8 @@
struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
unsigned int ctrl1_val = 0, ctrl2_val = 0;
+ nau8825_sema_acquire(nau8825, 2 * HZ);
+
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBM_CFM:
ctrl2_val |= NAU8825_I2S_MS_MASTER;
@@ -1282,6 +1271,9 @@
regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2,
NAU8825_I2S_MS_MASK, ctrl2_val);
+ /* Release the semaphone. */
+ nau8825_sema_release(nau8825);
+
return 0;
}
@@ -1611,8 +1603,11 @@
* cess and restore changes if process
* is ongoing when ejection.
*/
+ int ret;
nau8825->xtalk_protect = true;
- nau8825_sema_acquire(nau8825, 0);
+ ret = nau8825_sema_acquire(nau8825, 0);
+ if (ret < 0)
+ nau8825->xtalk_protect = false;
}
/* Startup cross talk detection process */
nau8825->xtalk_state = NAU8825_XTALK_PREPARE;
@@ -2238,23 +2233,14 @@
static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec)
{
struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
+ int ret;
regcache_cache_only(nau8825->regmap, false);
regcache_sync(nau8825->regmap);
- if (nau8825_is_jack_inserted(nau8825->regmap)) {
- /* If the jack is inserted, we need to check whether the play-
- * back is active before suspend. If active, the driver has to
- * raise the protection for cross talk function to avoid the
- * playback recovers before cross talk process finish. Other-
- * wise, the playback will be interfered by cross talk func-
- * tion. It is better to apply hardware related parameters
- * before starting playback or record.
- */
- if (nau8825_dai_is_active(nau8825)) {
- nau8825->xtalk_protect = true;
- nau8825_sema_acquire(nau8825, 0);
- }
- }
+ nau8825->xtalk_protect = true;
+ ret = nau8825_sema_acquire(nau8825, 0);
+ if (ret < 0)
+ nau8825->xtalk_protect = false;
enable_irq(nau8825->irq);
return 0;
diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c
index a67ea10..f266439 100644
--- a/sound/soc/codecs/wm2000.c
+++ b/sound/soc/codecs/wm2000.c
@@ -581,7 +581,7 @@
if (anc_transitions[i].dest == ANC_OFF)
clk_disable_unprepare(wm2000->mclk);
- return ret;
+ return 0;
}
static int wm2000_anc_set_mode(struct wm2000_priv *wm2000)
diff --git a/sound/soc/generic/Makefile b/sound/soc/generic/Makefile
index 45602ca..2d53c8d 100644
--- a/sound/soc/generic/Makefile
+++ b/sound/soc/generic/Makefile
@@ -1,5 +1,5 @@
-obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) := simple-card-utils.o
-
+snd-soc-simple-card-utils-objs := simple-card-utils.o
snd-soc-simple-card-objs := simple-card.o
-obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o
+obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) += snd-soc-simple-card-utils.o
+obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index d89a9a1..9599de6 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -7,6 +7,7 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+#include <linux/module.h>
#include <linux/of.h>
#include <sound/simple_card_utils.h>
@@ -95,3 +96,8 @@
return 0;
}
EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name);
+
+/* Module information */
+MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
+MODULE_DESCRIPTION("ALSA SoC Simple Card Utils");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/intel/skylake/skl-sst-utils.c b/sound/soc/intel/skylake/skl-sst-utils.c
index 25fcb79..ddcb52a 100644
--- a/sound/soc/intel/skylake/skl-sst-utils.c
+++ b/sound/soc/intel/skylake/skl-sst-utils.c
@@ -123,6 +123,11 @@
uuid_mod = (uuid_le *)uuid;
+ if (list_empty(&ctx->uuid_list)) {
+ dev_err(ctx->dev, "Module list is empty\n");
+ return -EINVAL;
+ }
+
list_for_each_entry(module, &ctx->uuid_list, list) {
if (uuid_le_cmp(*uuid_mod, module->uuid) == 0) {
dfw_config->module_id = module->id;
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index cd59536..e3e7641 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -672,8 +672,10 @@
skl->nhlt = skl_nhlt_init(bus->dev);
- if (skl->nhlt == NULL)
+ if (skl->nhlt == NULL) {
+ err = -ENODEV;
goto out_free;
+ }
skl_nhlt_update_topology_bin(skl);
diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c
index 0843a68..f61b3b5 100644
--- a/sound/soc/omap/omap-abe-twl6040.c
+++ b/sound/soc/omap/omap-abe-twl6040.c
@@ -38,10 +38,10 @@
struct abe_twl6040 {
int jack_detection; /* board can detect jack events */
int mclk_freq; /* MCLK frequency speed for twl6040 */
-
- struct platform_device *dmic_codec_dev;
};
+struct platform_device *dmic_codec_dev;
+
static int omap_abe_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params)
{
@@ -258,8 +258,6 @@
if (priv == NULL)
return -ENOMEM;
- priv->dmic_codec_dev = ERR_PTR(-EINVAL);
-
if (snd_soc_of_parse_card_name(card, "ti,model")) {
dev_err(&pdev->dev, "Card name is not provided\n");
return -ENODEV;
@@ -284,13 +282,6 @@
num_links = 2;
abe_twl6040_dai_links[1].cpu_of_node = dai_node;
abe_twl6040_dai_links[1].platform_of_node = dai_node;
-
- priv->dmic_codec_dev = platform_device_register_simple(
- "dmic-codec", -1, NULL, 0);
- if (IS_ERR(priv->dmic_codec_dev)) {
- dev_err(&pdev->dev, "Can't instantiate dmic-codec\n");
- return PTR_ERR(priv->dmic_codec_dev);
- }
} else {
num_links = 1;
}
@@ -299,16 +290,14 @@
of_property_read_u32(node, "ti,mclk-freq", &priv->mclk_freq);
if (!priv->mclk_freq) {
dev_err(&pdev->dev, "MCLK frequency not provided\n");
- ret = -EINVAL;
- goto err_unregister;
+ return -EINVAL;
}
card->fully_routed = 1;
if (!priv->mclk_freq) {
dev_err(&pdev->dev, "MCLK frequency missing\n");
- ret = -ENODEV;
- goto err_unregister;
+ return -ENODEV;
}
card->dai_link = abe_twl6040_dai_links;
@@ -317,17 +306,9 @@
snd_soc_card_set_drvdata(card, priv);
ret = snd_soc_register_card(card);
- if (ret) {
+ if (ret)
dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n",
ret);
- goto err_unregister;
- }
-
- return 0;
-
-err_unregister:
- if (!IS_ERR(priv->dmic_codec_dev))
- platform_device_unregister(priv->dmic_codec_dev);
return ret;
}
@@ -335,13 +316,9 @@
static int omap_abe_remove(struct platform_device *pdev)
{
struct snd_soc_card *card = platform_get_drvdata(pdev);
- struct abe_twl6040 *priv = snd_soc_card_get_drvdata(card);
snd_soc_unregister_card(card);
- if (!IS_ERR(priv->dmic_codec_dev))
- platform_device_unregister(priv->dmic_codec_dev);
-
return 0;
}
@@ -361,7 +338,33 @@
.remove = omap_abe_remove,
};
-module_platform_driver(omap_abe_driver);
+static int __init omap_abe_init(void)
+{
+ int ret;
+
+ dmic_codec_dev = platform_device_register_simple("dmic-codec", -1, NULL,
+ 0);
+ if (IS_ERR(dmic_codec_dev)) {
+ pr_err("%s: dmic-codec device registration failed\n", __func__);
+ return PTR_ERR(dmic_codec_dev);
+ }
+
+ ret = platform_driver_register(&omap_abe_driver);
+ if (ret) {
+ pr_err("%s: platform driver registration failed\n", __func__);
+ platform_device_unregister(dmic_codec_dev);
+ }
+
+ return ret;
+}
+module_init(omap_abe_init);
+
+static void __exit omap_abe_exit(void)
+{
+ platform_driver_unregister(&omap_abe_driver);
+ platform_device_unregister(dmic_codec_dev);
+}
+module_exit(omap_abe_exit);
MODULE_AUTHOR("Misael Lopez Cruz <misael.lopez@ti.com>");
MODULE_DESCRIPTION("ALSA SoC for OMAP boards with ABE and twl6040 codec");
diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c
index e7cdc51..64609c7 100644
--- a/sound/soc/omap/omap-mcpdm.c
+++ b/sound/soc/omap/omap-mcpdm.c
@@ -31,7 +31,6 @@
#include <linux/err.h>
#include <linux/io.h>
#include <linux/irq.h>
-#include <linux/clk.h>
#include <linux/slab.h>
#include <linux/pm_runtime.h>
#include <linux/of_device.h>
@@ -55,7 +54,6 @@
unsigned long phys_base;
void __iomem *io_base;
int irq;
- struct clk *pdmclk;
struct mutex mutex;
@@ -390,15 +388,14 @@
struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
int ret;
- clk_prepare_enable(mcpdm->pdmclk);
pm_runtime_enable(mcpdm->dev);
/* Disable lines while request is ongoing */
pm_runtime_get_sync(mcpdm->dev);
omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, 0x00);
- ret = devm_request_irq(mcpdm->dev, mcpdm->irq, omap_mcpdm_irq_handler,
- 0, "McPDM", (void *)mcpdm);
+ ret = request_irq(mcpdm->irq, omap_mcpdm_irq_handler, 0, "McPDM",
+ (void *)mcpdm);
pm_runtime_put_sync(mcpdm->dev);
@@ -423,9 +420,9 @@
{
struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
+ free_irq(mcpdm->irq, (void *)mcpdm);
pm_runtime_disable(mcpdm->dev);
- clk_disable_unprepare(mcpdm->pdmclk);
return 0;
}
@@ -445,8 +442,6 @@
mcpdm->pm_active_count++;
}
- clk_disable_unprepare(mcpdm->pdmclk);
-
return 0;
}
@@ -454,8 +449,6 @@
{
struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
- clk_prepare_enable(mcpdm->pdmclk);
-
if (mcpdm->pm_active_count) {
while (mcpdm->pm_active_count--)
pm_runtime_get_sync(mcpdm->dev);
@@ -549,15 +542,6 @@
mcpdm->dev = &pdev->dev;
- mcpdm->pdmclk = devm_clk_get(&pdev->dev, "pdmclk");
- if (IS_ERR(mcpdm->pdmclk)) {
- if (PTR_ERR(mcpdm->pdmclk) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
- dev_warn(&pdev->dev, "Error getting pdmclk (%ld)!\n",
- PTR_ERR(mcpdm->pdmclk));
- mcpdm->pdmclk = NULL;
- }
-
ret = devm_snd_soc_register_component(&pdev->dev,
&omap_mcpdm_component,
&omap_mcpdm_dai, 1);
diff --git a/sound/soc/samsung/s3c24xx_uda134x.c b/sound/soc/samsung/s3c24xx_uda134x.c
index 50849e1..92e88bc 100644
--- a/sound/soc/samsung/s3c24xx_uda134x.c
+++ b/sound/soc/samsung/s3c24xx_uda134x.c
@@ -58,10 +58,12 @@
static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream)
{
- int ret = 0;
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
#ifdef ENFORCE_RATES
struct snd_pcm_runtime *runtime = substream->runtime;
#endif
+ int ret = 0;
mutex_lock(&clk_lock);
pr_debug("%s %d\n", __func__, clk_users);
@@ -71,8 +73,7 @@
printk(KERN_ERR "%s cannot get xtal\n", __func__);
ret = PTR_ERR(xtal);
} else {
- pclk = clk_get(&s3c24xx_uda134x_snd_device->dev,
- "pclk");
+ pclk = clk_get(cpu_dai->dev, "iis");
if (IS_ERR(pclk)) {
printk(KERN_ERR "%s cannot get pclk\n",
__func__);
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index e39f916..969a516 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -226,8 +226,12 @@
ifscr = 0;
fsrate = 0;
if (fin != fout) {
+ u64 n;
+
ifscr = 1;
- fsrate = 0x0400000 / fout * fin;
+ n = (u64)0x0400000 * fin;
+ do_div(n, fout);
+ fsrate = n;
}
/*
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index d2df46c..bf7b52f 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -121,7 +121,7 @@
dpcm_be_disconnect(fe, stream);
fe->dpcm[stream].runtime = NULL;
- goto fe_err;
+ goto path_err;
}
dpcm_clear_pending_state(fe, stream);
@@ -136,6 +136,8 @@
return 0;
+path_err:
+ dpcm_path_put(&list);
fe_err:
if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
fe->dai_link->compr_ops->shutdown(cstream);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 16369ca..4afa8db 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1056,7 +1056,7 @@
if (!rtd->platform) {
dev_err(card->dev, "ASoC: platform %s not registered\n",
dai_link->platform_name);
- return -EPROBE_DEFER;
+ goto _err_defer;
}
soc_add_pcm_runtime(card, rtd);
@@ -2083,14 +2083,13 @@
/* remove auxiliary devices */
soc_remove_aux_devices(card);
+ snd_soc_dapm_free(&card->dapm);
soc_cleanup_card_debugfs(card);
/* remove the card */
if (card->remove)
card->remove(card);
- snd_soc_dapm_free(&card->dapm);
-
snd_card_free(card->snd_card);
return 0;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 8698c26..d908ff8 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3493,6 +3493,7 @@
const struct snd_soc_pcm_stream *config = w->params + w->params_select;
struct snd_pcm_substream substream;
struct snd_pcm_hw_params *params = NULL;
+ struct snd_pcm_runtime *runtime = NULL;
u64 fmt;
int ret;
@@ -3541,6 +3542,14 @@
memset(&substream, 0, sizeof(substream));
+ /* Allocate a dummy snd_pcm_runtime for startup() and other ops() */
+ runtime = kzalloc(sizeof(*runtime), GFP_KERNEL);
+ if (!runtime) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ substream.runtime = runtime;
+
switch (event) {
case SND_SOC_DAPM_PRE_PMU:
substream.stream = SNDRV_PCM_STREAM_CAPTURE;
@@ -3606,6 +3615,7 @@
}
out:
+ kfree(runtime);
kfree(params);
return ret;
}
diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c
index 204cc07..41aa335 100644
--- a/sound/usb/line6/pcm.c
+++ b/sound/usb/line6/pcm.c
@@ -55,7 +55,6 @@
err = line6_pcm_acquire(line6pcm, LINE6_STREAM_IMPULSE);
if (err < 0) {
line6pcm->impulse_volume = 0;
- line6_pcm_release(line6pcm, LINE6_STREAM_IMPULSE);
return err;
}
} else {
@@ -211,7 +210,9 @@
spin_lock_irqsave(&pstr->lock, flags);
clear_bit(type, &pstr->running);
if (!pstr->running) {
+ spin_unlock_irqrestore(&pstr->lock, flags);
line6_unlink_audio_urbs(line6pcm, pstr);
+ spin_lock_irqsave(&pstr->lock, flags);
if (direction == SNDRV_PCM_STREAM_CAPTURE) {
line6pcm->prev_fbuf = NULL;
line6pcm->prev_fsize = 0;
diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c
index daf81d1..45dd348 100644
--- a/sound/usb/line6/pod.c
+++ b/sound/usb/line6/pod.c
@@ -244,8 +244,8 @@
static ssize_t serial_number_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct usb_interface *interface = to_usb_interface(dev);
- struct usb_line6_pod *pod = usb_get_intfdata(interface);
+ struct snd_card *card = dev_to_snd_card(dev);
+ struct usb_line6_pod *pod = card->private_data;
return sprintf(buf, "%u\n", pod->serial_number);
}
@@ -256,8 +256,8 @@
static ssize_t firmware_version_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct usb_interface *interface = to_usb_interface(dev);
- struct usb_line6_pod *pod = usb_get_intfdata(interface);
+ struct snd_card *card = dev_to_snd_card(dev);
+ struct usb_line6_pod *pod = card->private_data;
return sprintf(buf, "%d.%02d\n", pod->firmware_version / 100,
pod->firmware_version % 100);
@@ -269,8 +269,8 @@
static ssize_t device_id_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct usb_interface *interface = to_usb_interface(dev);
- struct usb_line6_pod *pod = usb_get_intfdata(interface);
+ struct snd_card *card = dev_to_snd_card(dev);
+ struct usb_line6_pod *pod = card->private_data;
return sprintf(buf, "%d\n", pod->device_id);
}
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index b968794..f436d24 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -8,7 +8,11 @@
int strtobool(const char *s, bool *res);
-#ifdef __GLIBC__
+/*
+ * glibc based builds needs the extern while uClibc doesn't.
+ * However uClibc headers also define __GLIBC__ hence the hack below
+ */
+#if defined(__GLIBC__) && !defined(__UCLIBC__)
extern size_t strlcpy(char *dest, const char *src, size_t size);
#endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d9b80ef..21fd573 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -507,17 +507,17 @@
u8 op, result, type = (config >> 0) & 0xff;
const char *err = "unknown-ext-hardware-cache-type";
- if (type > PERF_COUNT_HW_CACHE_MAX)
+ if (type >= PERF_COUNT_HW_CACHE_MAX)
goto out_err;
op = (config >> 8) & 0xff;
err = "unknown-ext-hardware-cache-op";
- if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+ if (op >= PERF_COUNT_HW_CACHE_OP_MAX)
goto out_err;
result = (config >> 16) & 0xff;
err = "unknown-ext-hardware-cache-result";
- if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+ if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
goto out_err;
err = "invalid-cache";
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index cf5e250..783a53f 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -66,7 +66,7 @@
if (__report_module(&al, ip, ui))
return -1;
- e->ip = ip;
+ e->ip = al.addr;
e->map = al.map;
e->sym = al.sym;
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 97c0f8f..20c2e57 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -542,7 +542,7 @@
thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
MAP__FUNCTION, ip, &al);
- e.ip = ip;
+ e.ip = al.addr;
e.map = al.map;
e.sym = al.sym;
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 4fde8c7..77e6ccf 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -33,6 +33,7 @@
static struct timecounter *timecounter;
static struct workqueue_struct *wqueue;
static unsigned int host_vtimer_irq;
+static u32 host_vtimer_irq_flags;
void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
{
@@ -365,7 +366,7 @@
static void kvm_timer_init_interrupt(void *info)
{
- enable_percpu_irq(host_vtimer_irq, 0);
+ enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
}
int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
@@ -432,6 +433,14 @@
}
host_vtimer_irq = info->virtual_irq;
+ host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq);
+ if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH &&
+ host_vtimer_irq_flags != IRQF_TRIGGER_LOW) {
+ kvm_err("Invalid trigger for IRQ%d, assuming level low\n",
+ host_vtimer_irq);
+ host_vtimer_irq_flags = IRQF_TRIGGER_LOW;
+ }
+
err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler,
"kvm guest timer", kvm_get_running_vcpus());
if (err) {
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 07411cf..4660a7d 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -51,7 +51,7 @@
irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL);
if (!irq)
- return NULL;
+ return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&irq->lpi_list);
INIT_LIST_HEAD(&irq->ap_list);
@@ -441,39 +441,63 @@
* Find the target VCPU and the LPI number for a given devid/eventid pair
* and make this IRQ pending, possibly injecting it.
* Must be called with the its_lock mutex held.
+ * Returns 0 on success, a positive error value for any ITS mapping
+ * related errors and negative error values for generic errors.
*/
-static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
- u32 devid, u32 eventid)
+static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
+ u32 devid, u32 eventid)
{
+ struct kvm_vcpu *vcpu;
struct its_itte *itte;
if (!its->enabled)
- return;
+ return -EBUSY;
itte = find_itte(its, devid, eventid);
- /* Triggering an unmapped IRQ gets silently dropped. */
- if (itte && its_is_collection_mapped(itte->collection)) {
- struct kvm_vcpu *vcpu;
+ if (!itte || !its_is_collection_mapped(itte->collection))
+ return E_ITS_INT_UNMAPPED_INTERRUPT;
- vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
- if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) {
- spin_lock(&itte->irq->irq_lock);
- itte->irq->pending = true;
- vgic_queue_irq_unlock(kvm, itte->irq);
- }
- }
+ vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+ if (!vcpu)
+ return E_ITS_INT_UNMAPPED_INTERRUPT;
+
+ if (!vcpu->arch.vgic_cpu.lpis_enabled)
+ return -EBUSY;
+
+ spin_lock(&itte->irq->irq_lock);
+ itte->irq->pending = true;
+ vgic_queue_irq_unlock(kvm, itte->irq);
+
+ return 0;
+}
+
+static struct vgic_io_device *vgic_get_its_iodev(struct kvm_io_device *dev)
+{
+ struct vgic_io_device *iodev;
+
+ if (dev->ops != &kvm_io_gic_ops)
+ return NULL;
+
+ iodev = container_of(dev, struct vgic_io_device, dev);
+
+ if (iodev->iodev_type != IODEV_ITS)
+ return NULL;
+
+ return iodev;
}
/*
* Queries the KVM IO bus framework to get the ITS pointer from the given
* doorbell address.
* We then call vgic_its_trigger_msi() with the decoded data.
+ * According to the KVM_SIGNAL_MSI API description returns 1 on success.
*/
int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
{
u64 address;
struct kvm_io_device *kvm_io_dev;
struct vgic_io_device *iodev;
+ int ret;
if (!vgic_has_its(kvm))
return -ENODEV;
@@ -485,15 +509,28 @@
kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address);
if (!kvm_io_dev)
- return -ENODEV;
+ return -EINVAL;
- iodev = container_of(kvm_io_dev, struct vgic_io_device, dev);
+ iodev = vgic_get_its_iodev(kvm_io_dev);
+ if (!iodev)
+ return -EINVAL;
mutex_lock(&iodev->its->its_lock);
- vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data);
+ ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data);
mutex_unlock(&iodev->its->its_lock);
- return 0;
+ if (ret < 0)
+ return ret;
+
+ /*
+ * KVM_SIGNAL_MSI demands a return value > 0 for success and 0
+ * if the guest has blocked the MSI. So we map any LPI mapping
+ * related error to that.
+ */
+ if (ret)
+ return 0;
+ else
+ return 1;
}
/* Requires the its_lock to be held. */
@@ -502,7 +539,8 @@
list_del(&itte->itte_list);
/* This put matches the get in vgic_add_lpi. */
- vgic_put_irq(kvm, itte->irq);
+ if (itte->irq)
+ vgic_put_irq(kvm, itte->irq);
kfree(itte);
}
@@ -697,6 +735,7 @@
struct its_device *device;
struct its_collection *collection, *new_coll = NULL;
int lpi_nr;
+ struct vgic_irq *irq;
device = find_its_device(its, device_id);
if (!device)
@@ -710,6 +749,10 @@
lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser))
return E_ITS_MAPTI_PHYSICALID_OOR;
+ /* If there is an existing mapping, behavior is UNPREDICTABLE. */
+ if (find_itte(its, device_id, event_id))
+ return 0;
+
collection = find_collection(its, coll_id);
if (!collection) {
int ret = vgic_its_alloc_collection(its, &collection, coll_id);
@@ -718,22 +761,28 @@
new_coll = collection;
}
- itte = find_itte(its, device_id, event_id);
+ itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
if (!itte) {
- itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
- if (!itte) {
- if (new_coll)
- vgic_its_free_collection(its, coll_id);
- return -ENOMEM;
- }
-
- itte->event_id = event_id;
- list_add_tail(&itte->itte_list, &device->itt_head);
+ if (new_coll)
+ vgic_its_free_collection(its, coll_id);
+ return -ENOMEM;
}
+ itte->event_id = event_id;
+ list_add_tail(&itte->itte_list, &device->itt_head);
+
itte->collection = collection;
itte->lpi = lpi_nr;
- itte->irq = vgic_add_lpi(kvm, lpi_nr);
+
+ irq = vgic_add_lpi(kvm, lpi_nr);
+ if (IS_ERR(irq)) {
+ if (new_coll)
+ vgic_its_free_collection(its, coll_id);
+ its_free_itte(kvm, itte);
+ return PTR_ERR(irq);
+ }
+ itte->irq = irq;
+
update_affinity_itte(kvm, itte);
/*
@@ -981,9 +1030,7 @@
u32 msi_data = its_cmd_get_id(its_cmd);
u64 msi_devid = its_cmd_get_deviceid(its_cmd);
- vgic_its_trigger_msi(kvm, its, msi_devid, msi_data);
-
- return 0;
+ return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data);
}
/*
@@ -1288,13 +1335,13 @@
its_sync_lpi_pending_table(vcpu);
}
-static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its)
+static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
{
struct vgic_io_device *iodev = &its->iodev;
int ret;
- if (its->initialized)
- return 0;
+ if (!its->initialized)
+ return -EBUSY;
if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
return -ENXIO;
@@ -1311,9 +1358,6 @@
KVM_VGIC_V3_ITS_SIZE, &iodev->dev);
mutex_unlock(&kvm->slots_lock);
- if (!ret)
- its->initialized = true;
-
return ret;
}
@@ -1435,9 +1479,6 @@
if (type != KVM_VGIC_ITS_ADDR_TYPE)
return -ENODEV;
- if (its->initialized)
- return -EBUSY;
-
if (copy_from_user(&addr, uaddr, sizeof(addr)))
return -EFAULT;
@@ -1453,7 +1494,9 @@
case KVM_DEV_ARM_VGIC_GRP_CTRL:
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
- return vgic_its_init_its(dev->kvm, its);
+ its->initialized = true;
+
+ return 0;
}
break;
}
@@ -1498,3 +1541,30 @@
return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
KVM_DEV_TYPE_ARM_VGIC_ITS);
}
+
+/*
+ * Registers all ITSes with the kvm_io_bus framework.
+ * To follow the existing VGIC initialization sequence, this has to be
+ * done as late as possible, just before the first VCPU runs.
+ */
+int vgic_register_its_iodevs(struct kvm *kvm)
+{
+ struct kvm_device *dev;
+ int ret = 0;
+
+ list_for_each_entry(dev, &kvm->devices, vm_node) {
+ if (dev->ops != &kvm_arm_vgic_its_ops)
+ continue;
+
+ ret = vgic_register_its_iodev(kvm, dev->private);
+ if (ret)
+ return ret;
+ /*
+ * We don't need to care about tearing down previously
+ * registered ITSes, as the kvm_io_bus framework removes
+ * them for us if the VM gets destroyed.
+ */
+ }
+
+ return ret;
+}
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index ff668e0..90d8181 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -306,16 +306,19 @@
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- u64 propbaser = dist->propbaser;
+ u64 old_propbaser, propbaser;
/* Storing a value with LPIs already enabled is undefined */
if (vgic_cpu->lpis_enabled)
return;
- propbaser = update_64bit_reg(propbaser, addr & 4, len, val);
- propbaser = vgic_sanitise_propbaser(propbaser);
-
- dist->propbaser = propbaser;
+ do {
+ old_propbaser = dist->propbaser;
+ propbaser = old_propbaser;
+ propbaser = update_64bit_reg(propbaser, addr & 4, len, val);
+ propbaser = vgic_sanitise_propbaser(propbaser);
+ } while (cmpxchg64(&dist->propbaser, old_propbaser,
+ propbaser) != old_propbaser);
}
static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu,
@@ -331,16 +334,19 @@
unsigned long val)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- u64 pendbaser = vgic_cpu->pendbaser;
+ u64 old_pendbaser, pendbaser;
/* Storing a value with LPIs already enabled is undefined */
if (vgic_cpu->lpis_enabled)
return;
- pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val);
- pendbaser = vgic_sanitise_pendbaser(pendbaser);
-
- vgic_cpu->pendbaser = pendbaser;
+ do {
+ old_pendbaser = vgic_cpu->pendbaser;
+ pendbaser = old_pendbaser;
+ pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val);
+ pendbaser = vgic_sanitise_pendbaser(pendbaser);
+ } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser,
+ pendbaser) != old_pendbaser);
}
/*
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 0506543..9f0dae3 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -289,6 +289,14 @@
goto out;
}
+ if (vgic_has_its(kvm)) {
+ ret = vgic_register_its_iodevs(kvm);
+ if (ret) {
+ kvm_err("Unable to register VGIC ITS MMIO regions\n");
+ goto out;
+ }
+ }
+
dist->ready = true;
out:
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index e7aeac7..e83b7fe 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -117,17 +117,17 @@
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
- struct vgic_dist *dist;
+ struct vgic_dist *dist = &kvm->arch.vgic;
if (irq->intid < VGIC_MIN_LPI)
return;
- if (!kref_put(&irq->refcount, vgic_irq_release))
- return;
-
- dist = &kvm->arch.vgic;
-
spin_lock(&dist->lpi_list_lock);
+ if (!kref_put(&irq->refcount, vgic_irq_release)) {
+ spin_unlock(&dist->lpi_list_lock);
+ return;
+ };
+
list_del(&irq->lpi_list);
dist->lpi_list_count--;
spin_unlock(&dist->lpi_list_lock);
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 1d8e21d..6c4625c 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -84,6 +84,7 @@
int vgic_v3_probe(const struct gic_kvm_info *info);
int vgic_v3_map_resources(struct kvm *kvm);
int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
+int vgic_register_its_iodevs(struct kvm *kvm);
bool vgic_has_its(struct kvm *kvm);
int kvm_vgic_register_its_device(void);
void vgic_enable_lpis(struct kvm_vcpu *vcpu);
@@ -140,6 +141,11 @@
return -ENODEV;
}
+static inline int vgic_register_its_iodevs(struct kvm *kvm)
+{
+ return -ENODEV;
+}
+
static inline bool vgic_has_its(struct kvm *kvm)
{
return false;