Re: Linux 4.19.38
From: Greg KH
Date: Thu May 02 2019 - 06:15:13 EST
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f5acf35c712f..8b6567f7cb9b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2805,7 +2805,7 @@
check bypass). With this option data leaks are possible
in the system.
- nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2
+ nospectre_v2 [X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2
(indirect branch prediction) vulnerability. System may
allow data leaks with this option, which is equivalent
to spectre_v2=off.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 960de8fe3f40..2c31208528d5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -410,6 +410,7 @@ tcp_min_rtt_wlen - INTEGER
minimum RTT when it is moved to a longer path (e.g., due to traffic
engineering). A longer window makes the filter more resistant to RTT
inflations such as transient congestion. The unit is seconds.
+ Possible values: 0 - 86400 (1 day)
Default: 300
tcp_moderate_rcvbuf - BOOLEAN
diff --git a/Makefile b/Makefile
index 7b495cad8c2e..14d4aeb48907 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 19
-SUBLEVEL = 37
+SUBLEVEL = 38
EXTRAVERSION =
NAME = "People's Front"
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 517e0e18f0b8..e205bbbe2794 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -1395,7 +1395,21 @@ ENTRY(efi_stub_entry)
@ Preserve return value of efi_entry() in r4
mov r4, r0
- bl cache_clean_flush
+
+ @ our cache maintenance code relies on CP15 barrier instructions
+ @ but since we arrived here with the MMU and caches configured
+ @ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
+ @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
+ @ the enable path will be executed on v7+ only.
+ mrc p15, 0, r1, c1, c0, 0 @ read SCTLR
+ tst r1, #(1 << 5) @ CP15BEN bit set?
+ bne 0f
+ orr r1, r1, #(1 << 5) @ CP15 barrier instructions
+ mcr p15, 0, r1, c1, c0, 0 @ write SCTLR
+ ARM( .inst 0xf57ff06f @ v7+ isb )
+ THUMB( isb )
+
+0: bl cache_clean_flush
bl cache_off
@ Set parameters for booting zImage according to boot protocol
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 73913f072e39..579608342ac6 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -125,7 +125,7 @@ trace_a_syscall:
subu t1, v0, __NR_O32_Linux
move a1, v0
bnez t1, 1f /* __NR_syscall at offset 0 */
- lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
+ ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
.set pop
1: jal syscall_trace_enter
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 6bd5e7261335..ffeaed63675b 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -195,6 +195,7 @@ CONFIG_UDF_FS=m
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_PROC_KCORE=y
+CONFIG_HUGETLBFS=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
# CONFIG_MISC_FILESYSTEMS is not set
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 769c2624e0a6..75cff3f336b3 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -98,7 +98,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
* can be used, r7 contains NSEC_PER_SEC.
*/
- lwz r5,WTOM_CLOCK_SEC(r9)
+ lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
lwz r6,WTOM_CLOCK_NSEC(r9)
/* We now have our offset in r5,r6. We create a fake dependency
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 6c6a7c72cae4..ad0216c41d2c 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -330,7 +330,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
config PPC_RADIX_MMU
bool "Radix MMU Support"
- depends on PPC_BOOK3S_64
+ depends on PPC_BOOK3S_64 && HUGETLB_PAGE
select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
default y
help
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index b84f61bc5e7a..ffc823a8312f 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -224,6 +224,15 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
# Avoid indirect branches in kernel to deal with Spectre
ifdef CONFIG_RETPOLINE
KBUILD_CFLAGS += $(RETPOLINE_CFLAGS)
+ # Additionally, avoid generating expensive indirect jumps which
+ # are subject to retpolines for small number of switch cases.
+ # clang turns off jump table generation by default when under
+ # retpoline builds, however, gcc does not for x86. This has
+ # only been fixed starting from gcc stable version 8.4.0 and
+ # onwards, but not for older ones. See gcc bug #86952.
+ ifndef CONFIG_CC_IS_CLANG
+ KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables)
+ endif
endif
archscripts: scripts_basic
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f8084f18d58..6eb76106c469 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -76,15 +76,15 @@
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
- * Available model: HSW ULT,GLM,CNL
+ * Available model: HSW ULT,KBL,GLM,CNL
* Scope: Package (physical package)
*
*/
@@ -572,8 +572,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cec5fae23eb3..baa549f8e918 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -82,8 +82,7 @@ struct efi_scratch {
#define arch_efi_call_virt_setup() \
({ \
efi_sync_low_kernel_mappings(); \
- preempt_disable(); \
- __kernel_fpu_begin(); \
+ kernel_fpu_begin(); \
firmware_restrict_branch_speculation_start(); \
\
if (!efi_enabled(EFI_OLD_MEMMAP)) \
@@ -99,8 +98,7 @@ struct efi_scratch {
efi_switch_mm(efi_scratch.prev_mm); \
\
firmware_restrict_branch_speculation_end(); \
- __kernel_fpu_end(); \
- preempt_enable(); \
+ kernel_fpu_end(); \
})
extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index a9caac9d4a72..b56d504af654 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -12,17 +12,12 @@
#define _ASM_X86_FPU_API_H
/*
- * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
- * and they don't touch the preempt state on their own.
- * If you enable preemption after __kernel_fpu_begin(), preempt notifier
- * should call the __kernel_fpu_end() to prevent the kernel/user FPU
- * state from getting corrupted. KVM for example uses this model.
- *
- * All other cases use kernel_fpu_begin/end() which disable preemption
- * during kernel FPU usage.
+ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
+ * disables preemption so be careful if you intend to use it for long periods
+ * of time.
+ * If you intend to use the FPU in softirq you need to check first with
+ * irq_fpu_usable() if it is possible.
*/
-extern void __kernel_fpu_begin(void);
-extern void __kernel_fpu_end(void);
extern void kernel_fpu_begin(void);
extern void kernel_fpu_end(void);
extern bool irq_fpu_usable(void);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2ea85b32421a..2e5003fef51a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -93,7 +93,7 @@ bool irq_fpu_usable(void)
}
EXPORT_SYMBOL(irq_fpu_usable);
-void __kernel_fpu_begin(void)
+static void __kernel_fpu_begin(void)
{
struct fpu *fpu = ¤t->thread.fpu;
@@ -111,9 +111,8 @@ void __kernel_fpu_begin(void)
__cpu_invalidate_fpregs_state();
}
}
-EXPORT_SYMBOL(__kernel_fpu_begin);
-void __kernel_fpu_end(void)
+static void __kernel_fpu_end(void)
{
struct fpu *fpu = ¤t->thread.fpu;
@@ -122,7 +121,6 @@ void __kernel_fpu_end(void)
kernel_fpu_enable();
}
-EXPORT_SYMBOL(__kernel_fpu_end);
void kernel_fpu_begin(void)
{
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 030c98f35cca..a654ccfd1a22 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -958,14 +958,13 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
index = page - alloc->pages;
page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+
+ mm = alloc->vma_vm_mm;
+ if (!mmget_not_zero(mm))
+ goto err_mmget;
+ if (!down_write_trylock(&mm->mmap_sem))
+ goto err_down_write_mmap_sem_failed;
vma = binder_alloc_get_vma(alloc);
- if (vma) {
- if (!mmget_not_zero(alloc->vma_vm_mm))
- goto err_mmget;
- mm = alloc->vma_vm_mm;
- if (!down_write_trylock(&mm->mmap_sem))
- goto err_down_write_mmap_sem_failed;
- }
list_lru_isolate(lru, item);
spin_unlock(lock);
@@ -978,10 +977,9 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
PAGE_SIZE);
trace_binder_unmap_user_end(alloc, index);
-
- up_write(&mm->mmap_sem);
- mmput(mm);
}
+ up_write(&mm->mmap_sem);
+ mmput(mm);
trace_binder_unmap_kernel_start(alloc, index);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a63da9e07341..f1e63eb7cbca 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1112,8 +1112,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
err = __blkdev_reread_part(bdev);
else
err = blkdev_reread_part(bdev);
- pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
- __func__, lo_number, err);
+ if (err)
+ pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
+ __func__, lo_number, err);
/* Device is gone, no point in returning error */
err = 0;
}
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index a65505db09e5..70cbd0ee1b07 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -515,18 +515,18 @@ struct zram_work {
struct zram *zram;
unsigned long entry;
struct bio *bio;
+ struct bio_vec bvec;
};
#if PAGE_SIZE != 4096
static void zram_sync_read(struct work_struct *work)
{
- struct bio_vec bvec;
struct zram_work *zw = container_of(work, struct zram_work, work);
struct zram *zram = zw->zram;
unsigned long entry = zw->entry;
struct bio *bio = zw->bio;
- read_from_bdev_async(zram, &bvec, entry, bio);
+ read_from_bdev_async(zram, &zw->bvec, entry, bio);
}
/*
@@ -539,6 +539,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
{
struct zram_work work;
+ work.bvec = *bvec;
work.zram = zram;
work.entry = entry;
work.bio = bio;
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 48ee35e2bce6..0b05a1e08d21 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1281,6 +1281,9 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
enum dma_status status;
unsigned int residue = 0;
unsigned int dptr = 0;
+ unsigned int chcrb;
+ unsigned int tcrb;
+ unsigned int i;
if (!desc)
return 0;
@@ -1328,6 +1331,24 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
return 0;
}
+ /*
+ * We need to read two registers.
+ * Make sure the control register does not skip to next chunk
+ * while reading the counter.
+ * Trying it 3 times should be enough: Initial read, retry, retry
+ * for the paranoid.
+ */
+ for (i = 0; i < 3; i++) {
+ chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+ RCAR_DMACHCRB_DPTR_MASK;
+ tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB);
+ /* Still the same? */
+ if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+ RCAR_DMACHCRB_DPTR_MASK))
+ break;
+ }
+ WARN_ONCE(i >= 3, "residue might be not continuous!");
+
/*
* In descriptor mode the descriptor running pointer is not maintained
* by the interrupt handler, find the running descriptor from the
@@ -1335,8 +1356,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
* mode just use the running descriptor pointer.
*/
if (desc->hwdescs.use) {
- dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
- RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
+ dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT;
if (dptr == 0)
dptr = desc->nchunks;
dptr--;
@@ -1354,7 +1374,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
}
/* Add the residue for the current chunk. */
- residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
+ residue += tcrb << desc->xfer_shift;
return residue;
}
@@ -1367,6 +1387,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
enum dma_status status;
unsigned long flags;
unsigned int residue;
+ bool cyclic;
status = dma_cookie_status(chan, cookie, txstate);
if (status == DMA_COMPLETE || !txstate)
@@ -1374,10 +1395,11 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
spin_lock_irqsave(&rchan->lock, flags);
residue = rcar_dmac_chan_get_residue(rchan, cookie);
+ cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false;
spin_unlock_irqrestore(&rchan->lock, flags);
/* if there's no residue, the cookie is complete */
- if (!residue)
+ if (!residue && !cyclic)
return DMA_COMPLETE;
dma_set_residue(txstate, residue);
diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index e41223c05f6e..6cf2e2ce4093 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -414,6 +414,7 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
irq_set_handler_locked(data, handle_edge_irq);
break;
case IRQ_TYPE_EDGE_BOTH:
+ sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1);
irq_set_handler_locked(data, handle_edge_irq);
break;
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 6f91634880aa..2d6506c08bf7 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -334,8 +334,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
bool *enabled, int width, int height)
{
struct drm_i915_private *dev_priv = to_i915(fb_helper->dev);
+ unsigned long conn_configured, conn_seq, mask;
unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
- unsigned long conn_configured, conn_seq;
int i, j;
bool *save_enabled;
bool fallback = true, ret = true;
@@ -353,9 +353,10 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
drm_modeset_backoff(&ctx);
memcpy(save_enabled, enabled, count);
- conn_seq = GENMASK(count - 1, 0);
+ mask = GENMASK(count - 1, 0);
conn_configured = 0;
retry:
+ conn_seq = conn_configured;
for (i = 0; i < count; i++) {
struct drm_fb_helper_connector *fb_conn;
struct drm_connector *connector;
@@ -368,8 +369,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
if (conn_configured & BIT(i))
continue;
- /* First pass, only consider tiled connectors */
- if (conn_seq == GENMASK(count - 1, 0) && !connector->has_tile)
+ if (conn_seq == 0 && !connector->has_tile)
continue;
if (connector->status == connector_status_connected)
@@ -473,10 +473,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
conn_configured |= BIT(i);
}
- if (conn_configured != conn_seq) { /* repeat until no more are found */
- conn_seq = conn_configured;
+ if ((conn_configured & mask) != mask && conn_configured != conn_seq)
goto retry;
- }
/*
* If the BIOS didn't enable everything it could, fall back to have the
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-reg.c b/drivers/gpu/drm/rockchip/cdn-dp-reg.c
index 5a485489a1e2..6c8b14fb1d2f 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-reg.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-reg.c
@@ -113,7 +113,7 @@ static int cdp_dp_mailbox_write(struct cdn_dp_device *dp, u8 val)
static int cdn_dp_mailbox_validate_receive(struct cdn_dp_device *dp,
u8 module_id, u8 opcode,
- u8 req_size)
+ u16 req_size)
{
u32 mbox_size, i;
u8 header[4];
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 0e6a121858d1..5615ceb15708 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -998,7 +998,7 @@ static void
vc4_crtc_reset(struct drm_crtc *crtc)
{
if (crtc->state)
- __drm_atomic_helper_crtc_destroy_state(crtc->state);
+ vc4_crtc_destroy_state(crtc, crtc->state);
crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL);
if (crtc->state)
diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c
index cc287cf6eb29..edc52d75e6bd 100644
--- a/drivers/hwtracing/intel_th/gth.c
+++ b/drivers/hwtracing/intel_th/gth.c
@@ -616,7 +616,7 @@ static void intel_th_gth_unassign(struct intel_th_device *thdev,
othdev->output.port = -1;
othdev->output.active = false;
gth->output[port].output = NULL;
- for (master = 0; master < TH_CONFIGURABLE_MASTERS; master++)
+ for (master = 0; master <= TH_CONFIGURABLE_MASTERS; master++)
if (gth->master[master] == port)
gth->master[master] = -1;
spin_unlock(>h->gth_lock);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 50be240df331..8cc4da62f050 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2014,6 +2014,7 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
if (vma->vm_flags & VM_WRITE)
return -EPERM;
+ vma->vm_flags &= ~VM_MAYWRITE;
if (!dev->mdev->clock_info_page)
return -EOPNOTSUPP;
@@ -2197,6 +2198,7 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
if (vma->vm_flags & VM_WRITE)
return -EPERM;
+ vma->vm_flags &= ~VM_MAYWRITE;
/* Don't expose to user-space information it shouldn't have */
if (PAGE_SIZE > 4096)
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 49c9541050d4..5819c9d6ffdc 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -611,11 +611,6 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
if (unlikely(mapped_segs == mr->mr.max_segs))
return -ENOMEM;
- if (mr->mr.length == 0) {
- mr->mr.user_base = addr;
- mr->mr.iova = addr;
- }
-
m = mapped_segs / RVT_SEGSZ;
n = mapped_segs % RVT_SEGSZ;
mr->mr.map[m]->segs[n].vaddr = (void *)addr;
@@ -633,17 +628,24 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
* @sg_nents: number of entries in sg
* @sg_offset: offset in bytes into sg
*
+ * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages.
+ *
* Return: number of sg elements mapped to the memory region
*/
int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
int sg_nents, unsigned int *sg_offset)
{
struct rvt_mr *mr = to_imr(ibmr);
+ int ret;
mr->mr.length = 0;
mr->mr.page_shift = PAGE_SHIFT;
- return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset,
- rvt_set_page);
+ ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page);
+ mr->mr.user_base = ibmr->iova;
+ mr->mr.iova = ibmr->iova;
+ mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr;
+ mr->mr.length = (size_t)ibmr->length;
+ return ret;
}
/**
@@ -674,6 +676,7 @@ int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key,
ibmr->rkey = key;
mr->mr.lkey = key;
mr->mr.access_flags = access;
+ mr->mr.iova = ibmr->iova;
atomic_set(&mr->mr.lkey_invalid, 0);
return 0;
diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c
index df64d6aed4f7..93901ebd122a 100644
--- a/drivers/input/rmi4/rmi_f11.c
+++ b/drivers/input/rmi4/rmi_f11.c
@@ -1230,7 +1230,7 @@ static int rmi_f11_initialize(struct rmi_function *fn)
}
rc = f11_write_control_regs(fn, &f11->sens_query,
- &f11->dev_controls, fn->fd.query_base_addr);
+ &f11->dev_controls, fn->fd.control_base_addr);
if (rc)
dev_warn(&fn->dev, "Failed to write control registers\n");
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index dabe89968a78..2caa5c0c2bc4 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4821,6 +4821,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
if (err)
goto out;
+ mv88e6xxx_ports_cmode_init(chip);
mv88e6xxx_phy_init(chip);
if (chip->info->ops->get_eeprom) {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index b043370c2685..cc84133c184d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1169,6 +1169,12 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
if (!h->phy_dev)
return 0;
+ phy_dev->supported &= h->if_support;
+ phy_dev->advertising = phy_dev->supported;
+
+ if (h->phy_if == PHY_INTERFACE_MODE_XGMII)
+ phy_dev->autoneg = false;
+
if (h->phy_if != PHY_INTERFACE_MODE_XGMII) {
phy_dev->dev_flags = 0;
@@ -1180,15 +1186,6 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
if (unlikely(ret))
return -ENODEV;
- phy_dev->supported &= h->if_support;
- phy_dev->advertising = phy_dev->supported;
-
- if (h->phy_if == PHY_INTERFACE_MODE_XGMII)
- phy_dev->autoneg = false;
-
- if (h->phy_if == PHY_INTERFACE_MODE_SGMII)
- phy_stop(phy_dev);
-
return 0;
}
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index a475f36ddf8c..426789e2c23d 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1859,7 +1859,7 @@ static int do_reset(struct ibmvnic_adapter *adapter,
if (adapter->reset_reason != VNIC_RESET_FAILOVER &&
adapter->reset_reason != VNIC_RESET_CHANGE_PARAM)
- netdev_notify_peers(netdev);
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev);
netif_carrier_on(netdev);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 3f536541f45f..78a43d688cb1 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -41,6 +41,8 @@ static int __init fm10k_init_module(void)
/* create driver workqueue */
fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
fm10k_driver_name);
+ if (!fm10k_workqueue)
+ return -ENOMEM;
fm10k_dbg_init();
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 9988c89ed9fd..9b10abb604cb 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4272,7 +4272,7 @@ static void mvpp2_phylink_validate(struct net_device *dev,
case PHY_INTERFACE_MODE_RGMII_ID:
case PHY_INTERFACE_MODE_RGMII_RXID:
case PHY_INTERFACE_MODE_RGMII_TXID:
- if (port->gop_id == 0)
+ if (port->priv->hw_version == MVPP22 && port->gop_id == 0)
goto empty_set;
break;
default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 4a33c9a7cac7..599114ab7821 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -33,6 +33,26 @@
#include <linux/bpf_trace.h>
#include "en/xdp.h"
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
+{
+ int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM;
+
+ /* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
+ * The condition checked in mlx5e_rx_is_linear_skb is:
+ * SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE (1)
+ * (Note that hw_mtu == sw_mtu + hard_mtu.)
+ * What is returned from this function is:
+ * max_mtu = PAGE_SIZE - S - hr - hard_mtu (2)
+ * After assigning sw_mtu := max_mtu, the left side of (1) turns to
+ * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE,
+ * because both PAGE_SIZE and S are already aligned. Any number greater
+ * than max_mtu would make the left side of (1) greater than PAGE_SIZE,
+ * so max_mtu is the maximum MTU allowed.
+ */
+
+ return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr));
+}
+
static inline bool
mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
struct xdp_buff *xdp)
@@ -207,9 +227,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
sqcc++;
if (is_redirect) {
- xdp_return_frame(xdpi->xdpf);
dma_unmap_single(sq->pdev, xdpi->dma_addr,
xdpi->xdpf->len, DMA_TO_DEVICE);
+ xdp_return_frame(xdpi->xdpf);
} else {
/* Recycle RX page */
mlx5e_page_release(rq, &xdpi->di, true);
@@ -243,9 +263,9 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
sq->cc++;
if (is_redirect) {
- xdp_return_frame(xdpi->xdpf);
dma_unmap_single(sq->pdev, xdpi->dma_addr,
xdpi->xdpf->len, DMA_TO_DEVICE);
+ xdp_return_frame(xdpi->xdpf);
} else {
/* Recycle RX page */
mlx5e_page_release(rq, &xdpi->di, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 4d096623178b..827ceef5fa93 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -34,12 +34,11 @@
#include "en.h"
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
- MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
#define MLX5E_XDP_TX_DS_COUNT \
((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params);
bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
void *va, u16 *rx_headroom, u32 *len);
bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 5e5423076b03..9ca4f88d7cf6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1317,7 +1317,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
break;
case MLX5_MODULE_ID_SFP:
modinfo->type = ETH_MODULE_SFF_8472;
- modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+ modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
break;
default:
netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 637d59c01fe5..b190c447aeb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3761,7 +3761,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
if (params->xdp_prog &&
!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
- new_mtu, MLX5E_XDP_MAX_MTU);
+ new_mtu, mlx5e_xdp_max_mtu(params));
err = -EINVAL;
goto out;
}
@@ -4227,7 +4227,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
- new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+ new_channels.params.sw_mtu,
+ mlx5e_xdp_max_mtu(&new_channels.params));
return -EINVAL;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 31a9cbd85689..09b6b1bfbfa8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -404,10 +404,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
i2c_addr = MLX5_I2C_ADDR_LOW;
- if (offset >= MLX5_EEPROM_PAGE_LENGTH) {
- i2c_addr = MLX5_I2C_ADDR_HIGH;
- offset -= MLX5_EEPROM_PAGE_LENGTH;
- }
MLX5_SET(mcia_reg, in, l, 0);
MLX5_SET(mcia_reg, in, module, module_num);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 72cdaa01d56d..100618531021 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
#define MLXSW_PCI_SW_RESET 0xF0010
#define MLXSW_PCI_SW_RESET_RST_BIT BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 13000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 20000
#define MLXSW_PCI_SW_RESET_WAIT_MSECS 100
#define MLXSW_PCI_FW_READY 0xA1844
#define MLXSW_PCI_FW_READY_MASK 0xFFFF
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f9bef030ee05..c5b82e283d13 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2504,11 +2504,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
if (err)
return err;
+ mlxsw_sp_port->link.autoneg = autoneg;
+
if (!netif_running(dev))
return 0;
- mlxsw_sp_port->link.autoneg = autoneg;
-
mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
@@ -2783,7 +2783,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HIERARCY_TC,
i + 8, i,
- false, 0);
+ true, 100);
if (err)
return err;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 886176be818e..62460a5b4ad9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2595,8 +2595,6 @@ static int stmmac_open(struct net_device *dev)
u32 chan;
int ret;
- stmmac_check_ether_addr(priv);
-
if (priv->hw->pcs != STMMAC_PCS_RGMII &&
priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI) {
@@ -4296,6 +4294,8 @@ int stmmac_dvr_probe(struct device *device,
if (ret)
goto error_hw_init;
+ stmmac_check_ether_addr(priv);
+
/* Configure real RX and TX queues */
netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index d819e8eaba12..cc1e887e47b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = {
},
.driver_data = (void *)&galileo_stmmac_dmi_data,
},
+ /*
+ * There are 2 types of SIMATIC IOT2000: IOT20202 and IOT2040.
+ * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
+ * has only one pci network device while other asset tags are
+ * for IOT2040 which has two.
+ */
{
.matches = {
DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
@@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = {
{
.matches = {
DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
- DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG,
- "6ES7647-0AA00-1YA2"),
},
.driver_data = (void *)&iot2040_stmmac_dmi_data,
},
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index f4e93f5fc204..ea90db3c7705 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -153,7 +153,7 @@ slhc_init(int rslots, int tslots)
void
slhc_free(struct slcompress *comp)
{
- if ( comp == NULLSLCOMPR )
+ if ( IS_ERR_OR_NULL(comp) )
return;
if ( comp->tstate != NULLSLSTATE )
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index e23eaf3f6d03..6c6230b44bcd 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1160,6 +1160,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
return -EINVAL;
}
+ if (netdev_has_upper_dev(dev, port_dev)) {
+ NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface");
+ netdev_err(dev, "Device %s is already an upper device of the team interface\n",
+ portname);
+ return -EBUSY;
+ }
+
if (port_dev->features & NETIF_F_VLAN_CHALLENGED &&
vlan_uses_dev(dev)) {
NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up");
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index a1f225f077cd..ef47c226e1d2 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1899,14 +1899,11 @@ int usb_runtime_idle(struct device *dev)
return -EBUSY;
}
-int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable)
+static int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable)
{
struct usb_hcd *hcd = bus_to_hcd(udev->bus);
int ret = -EPERM;
- if (enable && !udev->usb2_hw_lpm_allowed)
- return 0;
-
if (hcd->driver->set_usb2_hw_lpm) {
ret = hcd->driver->set_usb2_hw_lpm(hcd, udev, enable);
if (!ret)
@@ -1916,6 +1913,24 @@ int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable)
return ret;
}
+int usb_enable_usb2_hardware_lpm(struct usb_device *udev)
+{
+ if (!udev->usb2_hw_lpm_capable ||
+ !udev->usb2_hw_lpm_allowed ||
+ udev->usb2_hw_lpm_enabled)
+ return 0;
+
+ return usb_set_usb2_hardware_lpm(udev, 1);
+}
+
+int usb_disable_usb2_hardware_lpm(struct usb_device *udev)
+{
+ if (!udev->usb2_hw_lpm_enabled)
+ return 0;
+
+ return usb_set_usb2_hardware_lpm(udev, 0);
+}
+
#endif /* CONFIG_PM */
struct bus_type usb_bus_type = {
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 3adff4da2ee1..bbcfa63d0233 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -3217,8 +3217,7 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
}
/* disable USB2 hardware LPM */
- if (udev->usb2_hw_lpm_enabled == 1)
- usb_set_usb2_hardware_lpm(udev, 0);
+ usb_disable_usb2_hardware_lpm(udev);
if (usb_disable_ltm(udev)) {
dev_err(&udev->dev, "Failed to disable LTM before suspend\n");
@@ -3256,8 +3255,7 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
usb_enable_ltm(udev);
err_ltm:
/* Try to enable USB2 hardware LPM again */
- if (udev->usb2_hw_lpm_capable == 1)
- usb_set_usb2_hardware_lpm(udev, 1);
+ usb_enable_usb2_hardware_lpm(udev);
if (udev->do_remote_wakeup)
(void) usb_disable_remote_wakeup(udev);
@@ -3540,8 +3538,7 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
hub_port_logical_disconnect(hub, port1);
} else {
/* Try to enable USB2 hardware LPM */
- if (udev->usb2_hw_lpm_capable == 1)
- usb_set_usb2_hardware_lpm(udev, 1);
+ usb_enable_usb2_hardware_lpm(udev);
/* Try to enable USB3 LTM */
usb_enable_ltm(udev);
@@ -4432,7 +4429,7 @@ static void hub_set_initial_usb2_lpm_policy(struct usb_device *udev)
if ((udev->bos->ext_cap->bmAttributes & cpu_to_le32(USB_BESL_SUPPORT)) ||
connect_type == USB_PORT_CONNECT_TYPE_HARD_WIRED) {
udev->usb2_hw_lpm_allowed = 1;
- usb_set_usb2_hardware_lpm(udev, 1);
+ usb_enable_usb2_hardware_lpm(udev);
}
}
@@ -5608,8 +5605,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
/* Disable USB2 hardware LPM.
* It will be re-enabled by the enumeration process.
*/
- if (udev->usb2_hw_lpm_enabled == 1)
- usb_set_usb2_hardware_lpm(udev, 0);
+ usb_disable_usb2_hardware_lpm(udev);
/* Disable LPM while we reset the device and reinstall the alt settings.
* Device-initiated LPM, and system exit latency settings are cleared
@@ -5712,7 +5708,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
done:
/* Now that the alt settings are re-installed, enable LTM and LPM. */
- usb_set_usb2_hardware_lpm(udev, 1);
+ usb_enable_usb2_hardware_lpm(udev);
usb_unlocked_enable_lpm(udev);
usb_enable_ltm(udev);
usb_release_bos_descriptor(udev);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index bfa5eda0cc26..4f33eb632a88 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1243,8 +1243,7 @@ void usb_disable_device(struct usb_device *dev, int skip_ep0)
dev->actconfig->interface[i] = NULL;
}
- if (dev->usb2_hw_lpm_enabled == 1)
- usb_set_usb2_hardware_lpm(dev, 0);
+ usb_disable_usb2_hardware_lpm(dev);
usb_unlocked_disable_lpm(dev);
usb_disable_ltm(dev);
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index ea18284dfa9a..7e88fdfe3cf5 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -528,7 +528,10 @@ static ssize_t usb2_hardware_lpm_store(struct device *dev,
if (!ret) {
udev->usb2_hw_lpm_allowed = value;
- ret = usb_set_usb2_hardware_lpm(udev, value);
+ if (value)
+ ret = usb_enable_usb2_hardware_lpm(udev);
+ else
+ ret = usb_disable_usb2_hardware_lpm(udev);
}
usb_unlock_device(udev);
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 546a2219454b..d95a5358f73d 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -92,7 +92,8 @@ extern int usb_remote_wakeup(struct usb_device *dev);
extern int usb_runtime_suspend(struct device *dev);
extern int usb_runtime_resume(struct device *dev);
extern int usb_runtime_idle(struct device *dev);
-extern int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable);
+extern int usb_enable_usb2_hardware_lpm(struct usb_device *udev);
+extern int usb_disable_usb2_hardware_lpm(struct usb_device *udev);
#else
@@ -112,7 +113,12 @@ static inline int usb_autoresume_device(struct usb_device *udev)
return 0;
}
-static inline int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable)
+static inline int usb_enable_usb2_hardware_lpm(struct usb_device *udev)
+{
+ return 0;
+}
+
+static inline int usb_disable_usb2_hardware_lpm(struct usb_device *udev)
{
return 0;
}
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 64cbc2d007c9..c36275754086 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -58,12 +58,18 @@ module_param_named(disable_hugepages,
MODULE_PARM_DESC(disable_hugepages,
"Disable VFIO IOMMU support for IOMMU hugepages.");
+static unsigned int dma_entry_limit __read_mostly = U16_MAX;
+module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644);
+MODULE_PARM_DESC(dma_entry_limit,
+ "Maximum number of user DMA mappings per container (65535).");
+
struct vfio_iommu {
struct list_head domain_list;
struct vfio_domain *external_domain; /* domain for external user */
struct mutex lock;
struct rb_root dma_list;
struct blocking_notifier_head notifier;
+ unsigned int dma_avail;
bool v2;
bool nesting;
};
@@ -836,6 +842,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
vfio_unlink_dma(iommu, dma);
put_task_struct(dma->task);
kfree(dma);
+ iommu->dma_avail++;
}
static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
@@ -1110,12 +1117,18 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
goto out_unlock;
}
+ if (!iommu->dma_avail) {
+ ret = -ENOSPC;
+ goto out_unlock;
+ }
+
dma = kzalloc(sizeof(*dma), GFP_KERNEL);
if (!dma) {
ret = -ENOMEM;
goto out_unlock;
}
+ iommu->dma_avail--;
dma->iova = iova;
dma->vaddr = vaddr;
dma->prot = prot;
@@ -1612,6 +1625,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
INIT_LIST_HEAD(&iommu->domain_list);
iommu->dma_list = RB_ROOT;
+ iommu->dma_avail = dma_entry_limit;
mutex_init(&iommu->lock);
BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
diff --git a/fs/aio.c b/fs/aio.c
index 45d5ef8dd0a8..911e23087dfb 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -161,9 +161,13 @@ struct kioctx {
unsigned id;
};
+/*
+ * First field must be the file pointer in all the
+ * iocb unions! See also 'struct kiocb' in <linux/fs.h>
+ */
struct fsync_iocb {
- struct work_struct work;
struct file *file;
+ struct work_struct work;
bool datasync;
};
@@ -171,14 +175,21 @@ struct poll_iocb {
struct file *file;
struct wait_queue_head *head;
__poll_t events;
- bool woken;
+ bool done;
bool cancelled;
struct wait_queue_entry wait;
struct work_struct work;
};
+/*
+ * NOTE! Each of the iocb union members has the file pointer
+ * as the first entry in their struct definition. So you can
+ * access the file pointer through any of the sub-structs,
+ * or directly as just 'ki_filp' in this struct.
+ */
struct aio_kiocb {
union {
+ struct file *ki_filp;
struct kiocb rw;
struct fsync_iocb fsync;
struct poll_iocb poll;
@@ -187,8 +198,7 @@ struct aio_kiocb {
struct kioctx *ki_ctx;
kiocb_cancel_fn *ki_cancel;
- struct iocb __user *ki_user_iocb; /* user's aiocb */
- __u64 ki_user_data; /* user's data for completion */
+ struct io_event ki_res;
struct list_head ki_list; /* the aio core uses this
* for cancellation */
@@ -902,7 +912,7 @@ static void put_reqs_available(struct kioctx *ctx, unsigned nr)
local_irq_restore(flags);
}
-static bool get_reqs_available(struct kioctx *ctx)
+static bool __get_reqs_available(struct kioctx *ctx)
{
struct kioctx_cpu *kcpu;
bool ret = false;
@@ -994,32 +1004,35 @@ static void user_refill_reqs_available(struct kioctx *ctx)
spin_unlock_irq(&ctx->completion_lock);
}
+static bool get_reqs_available(struct kioctx *ctx)
+{
+ if (__get_reqs_available(ctx))
+ return true;
+ user_refill_reqs_available(ctx);
+ return __get_reqs_available(ctx);
+}
+
/* aio_get_req
* Allocate a slot for an aio request.
* Returns NULL if no requests are free.
+ *
+ * The refcount is initialized to 2 - one for the async op completion,
+ * one for the synchronous code that does this.
*/
static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
{
struct aio_kiocb *req;
- if (!get_reqs_available(ctx)) {
- user_refill_reqs_available(ctx);
- if (!get_reqs_available(ctx))
- return NULL;
- }
-
- req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
+ req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
if (unlikely(!req))
- goto out_put;
+ return NULL;
percpu_ref_get(&ctx->reqs);
- INIT_LIST_HEAD(&req->ki_list);
- refcount_set(&req->ki_refcnt, 0);
req->ki_ctx = ctx;
+ INIT_LIST_HEAD(&req->ki_list);
+ refcount_set(&req->ki_refcnt, 2);
+ req->ki_eventfd = NULL;
return req;
-out_put:
- put_reqs_available(ctx, 1);
- return NULL;
}
static struct kioctx *lookup_ioctx(unsigned long ctx_id)
@@ -1050,19 +1063,18 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
return ret;
}
-static inline void iocb_put(struct aio_kiocb *iocb)
+static inline void iocb_destroy(struct aio_kiocb *iocb)
{
- if (refcount_read(&iocb->ki_refcnt) == 0 ||
- refcount_dec_and_test(&iocb->ki_refcnt)) {
- percpu_ref_put(&iocb->ki_ctx->reqs);
- kmem_cache_free(kiocb_cachep, iocb);
- }
+ if (iocb->ki_filp)
+ fput(iocb->ki_filp);
+ percpu_ref_put(&iocb->ki_ctx->reqs);
+ kmem_cache_free(kiocb_cachep, iocb);
}
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
-static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb)
{
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
@@ -1086,17 +1098,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
event = ev_page + pos % AIO_EVENTS_PER_PAGE;
- event->obj = (u64)(unsigned long)iocb->ki_user_iocb;
- event->data = iocb->ki_user_data;
- event->res = res;
- event->res2 = res2;
+ *event = iocb->ki_res;
kunmap_atomic(ev_page);
flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
- pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
- ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data,
- res, res2);
+ pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb,
+ (void __user *)(unsigned long)iocb->ki_res.obj,
+ iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2);
/* after flagging the request as done, we
* must never even look at it again
@@ -1138,7 +1147,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
- iocb_put(iocb);
+}
+
+static inline void iocb_put(struct aio_kiocb *iocb)
+{
+ if (refcount_dec_and_test(&iocb->ki_refcnt)) {
+ aio_complete(iocb);
+ iocb_destroy(iocb);
+ }
}
/* aio_read_events_ring
@@ -1412,18 +1428,17 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
file_end_write(kiocb->ki_filp);
}
- fput(kiocb->ki_filp);
- aio_complete(iocb, res, res2);
+ iocb->ki_res.res = res;
+ iocb->ki_res.res2 = res2;
+ iocb_put(iocb);
}
-static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
+static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
{
int ret;
- req->ki_filp = fget(iocb->aio_fildes);
- if (unlikely(!req->ki_filp))
- return -EBADF;
req->ki_complete = aio_complete_rw;
+ req->private = NULL;
req->ki_pos = iocb->aio_offset;
req->ki_flags = iocb_flags(req->ki_filp);
if (iocb->aio_flags & IOCB_FLAG_RESFD)
@@ -1438,7 +1453,6 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
ret = ioprio_check_cap(iocb->aio_reqprio);
if (ret) {
pr_debug("aio ioprio check cap error: %d\n", ret);
- fput(req->ki_filp);
return ret;
}
@@ -1448,11 +1462,13 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
if (unlikely(ret))
- fput(req->ki_filp);
- return ret;
+ return ret;
+
+ req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */
+ return 0;
}
-static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
+static int aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec,
bool vectored, bool compat, struct iov_iter *iter)
{
void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf;
@@ -1487,12 +1503,12 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
ret = -EINTR;
/*FALLTHRU*/
default:
- aio_complete_rw(req, ret, 0);
+ req->ki_complete(req, ret, 0);
}
}
-static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
- bool compat)
+static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb,
+ bool vectored, bool compat)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
@@ -1503,29 +1519,24 @@ static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
if (ret)
return ret;
file = req->ki_filp;
-
- ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_READ)))
- goto out_fput;
+ return -EBADF;
ret = -EINVAL;
if (unlikely(!file->f_op->read_iter))
- goto out_fput;
+ return -EINVAL;
ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
if (ret)
- goto out_fput;
+ return ret;
ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
if (!ret)
aio_rw_done(req, call_read_iter(file, req, &iter));
kfree(iovec);
-out_fput:
- if (unlikely(ret))
- fput(file);
return ret;
}
-static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
- bool compat)
+static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb,
+ bool vectored, bool compat)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
@@ -1537,16 +1548,14 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
return ret;
file = req->ki_filp;
- ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_WRITE)))
- goto out_fput;
- ret = -EINVAL;
+ return -EBADF;
if (unlikely(!file->f_op->write_iter))
- goto out_fput;
+ return -EINVAL;
ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
if (ret)
- goto out_fput;
+ return ret;
ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
if (!ret) {
/*
@@ -1564,35 +1573,26 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
aio_rw_done(req, call_write_iter(file, req, &iter));
}
kfree(iovec);
-out_fput:
- if (unlikely(ret))
- fput(file);
return ret;
}
static void aio_fsync_work(struct work_struct *work)
{
- struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
- int ret;
+ struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work);
- ret = vfs_fsync(req->file, req->datasync);
- fput(req->file);
- aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+ iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync);
+ iocb_put(iocb);
}
-static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
+static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
+ bool datasync)
{
if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
iocb->aio_rw_flags))
return -EINVAL;
- req->file = fget(iocb->aio_fildes);
- if (unlikely(!req->file))
- return -EBADF;
- if (unlikely(!req->file->f_op->fsync)) {
- fput(req->file);
+ if (unlikely(!req->file->f_op->fsync))
return -EINVAL;
- }
req->datasync = datasync;
INIT_WORK(&req->work, aio_fsync_work);
@@ -1600,14 +1600,6 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
return 0;
}
-static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
- struct file *file = iocb->poll.file;
-
- aio_complete(iocb, mangle_poll(mask), 0);
- fput(file);
-}
-
static void aio_poll_complete_work(struct work_struct *work)
{
struct poll_iocb *req = container_of(work, struct poll_iocb, work);
@@ -1633,9 +1625,11 @@ static void aio_poll_complete_work(struct work_struct *work)
return;
}
list_del_init(&iocb->ki_list);
+ iocb->ki_res.res = mangle_poll(mask);
+ req->done = true;
spin_unlock_irq(&ctx->ctx_lock);
- aio_poll_complete(iocb, mask);
+ iocb_put(iocb);
}
/* assumes we are called with irqs disabled */
@@ -1663,31 +1657,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
__poll_t mask = key_to_poll(key);
unsigned long flags;
- req->woken = true;
-
/* for instances that support it check for an event match first: */
- if (mask) {
- if (!(mask & req->events))
- return 0;
+ if (mask && !(mask & req->events))
+ return 0;
+
+ list_del_init(&req->wait.entry);
+ if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
/*
* Try to complete the iocb inline if we can. Use
* irqsave/irqrestore because not all filesystems (e.g. fuse)
* call this function with IRQs disabled and because IRQs
* have to be disabled before ctx_lock is obtained.
*/
- if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
- list_del(&iocb->ki_list);
- spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
-
- list_del_init(&req->wait.entry);
- aio_poll_complete(iocb, mask);
- return 1;
- }
+ list_del(&iocb->ki_list);
+ iocb->ki_res.res = mangle_poll(mask);
+ req->done = true;
+ spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
+ iocb_put(iocb);
+ } else {
+ schedule_work(&req->work);
}
-
- list_del_init(&req->wait.entry);
- schedule_work(&req->work);
return 1;
}
@@ -1714,11 +1704,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
add_wait_queue(head, &pt->iocb->poll.wait);
}
-static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
{
struct kioctx *ctx = aiocb->ki_ctx;
struct poll_iocb *req = &aiocb->poll;
struct aio_poll_table apt;
+ bool cancel = false;
__poll_t mask;
/* reject any unknown events outside the normal event mask. */
@@ -1730,9 +1721,10 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
INIT_WORK(&req->work, aio_poll_complete_work);
req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
- req->file = fget(iocb->aio_fildes);
- if (unlikely(!req->file))
- return -EBADF;
+
+ req->head = NULL;
+ req->done = false;
+ req->cancelled = false;
apt.pt._qproc = aio_poll_queue_proc;
apt.pt._key = req->events;
@@ -1743,83 +1735,79 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
INIT_LIST_HEAD(&req->wait.entry);
init_waitqueue_func_entry(&req->wait, aio_poll_wake);
- /* one for removal from waitqueue, one for this function */
- refcount_set(&aiocb->ki_refcnt, 2);
-
mask = vfs_poll(req->file, &apt.pt) & req->events;
- if (unlikely(!req->head)) {
- /* we did not manage to set up a waitqueue, done */
- goto out;
- }
-
spin_lock_irq(&ctx->ctx_lock);
- spin_lock(&req->head->lock);
- if (req->woken) {
- /* wake_up context handles the rest */
- mask = 0;
+ if (likely(req->head)) {
+ spin_lock(&req->head->lock);
+ if (unlikely(list_empty(&req->wait.entry))) {
+ if (apt.error)
+ cancel = true;
+ apt.error = 0;
+ mask = 0;
+ }
+ if (mask || apt.error) {
+ list_del_init(&req->wait.entry);
+ } else if (cancel) {
+ WRITE_ONCE(req->cancelled, true);
+ } else if (!req->done) { /* actually waiting for an event */
+ list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+ aiocb->ki_cancel = aio_poll_cancel;
+ }
+ spin_unlock(&req->head->lock);
+ }
+ if (mask) { /* no async, we'd stolen it */
+ aiocb->ki_res.res = mangle_poll(mask);
apt.error = 0;
- } else if (mask || apt.error) {
- /* if we get an error or a mask we are done */
- WARN_ON_ONCE(list_empty(&req->wait.entry));
- list_del_init(&req->wait.entry);
- } else {
- /* actually waiting for an event */
- list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
- aiocb->ki_cancel = aio_poll_cancel;
}
- spin_unlock(&req->head->lock);
spin_unlock_irq(&ctx->ctx_lock);
-
-out:
- if (unlikely(apt.error)) {
- fput(req->file);
- return apt.error;
- }
-
if (mask)
- aio_poll_complete(aiocb, mask);
- iocb_put(aiocb);
- return 0;
+ iocb_put(aiocb);
+ return apt.error;
}
-static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
- bool compat)
+static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
+ struct iocb __user *user_iocb, bool compat)
{
struct aio_kiocb *req;
- struct iocb iocb;
ssize_t ret;
- if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
- return -EFAULT;
-
/* enforce forwards compatibility on users */
- if (unlikely(iocb.aio_reserved2)) {
+ if (unlikely(iocb->aio_reserved2)) {
pr_debug("EINVAL: reserve field set\n");
return -EINVAL;
}
/* prevent overflows */
if (unlikely(
- (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
- (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
- ((ssize_t)iocb.aio_nbytes < 0)
+ (iocb->aio_buf != (unsigned long)iocb->aio_buf) ||
+ (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
+ ((ssize_t)iocb->aio_nbytes < 0)
)) {
pr_debug("EINVAL: overflow check\n");
return -EINVAL;
}
+ if (!get_reqs_available(ctx))
+ return -EAGAIN;
+
+ ret = -EAGAIN;
req = aio_get_req(ctx);
if (unlikely(!req))
- return -EAGAIN;
+ goto out_put_reqs_available;
+
+ req->ki_filp = fget(iocb->aio_fildes);
+ ret = -EBADF;
+ if (unlikely(!req->ki_filp))
+ goto out_put_req;
- if (iocb.aio_flags & IOCB_FLAG_RESFD) {
+ if (iocb->aio_flags & IOCB_FLAG_RESFD) {
/*
* If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
* instance of the file* now. The file descriptor must be
* an eventfd() fd, and will be signaled for each completed
* event using the eventfd_signal() function.
*/
- req->ki_eventfd = eventfd_ctx_fdget((int) iocb.aio_resfd);
+ req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
if (IS_ERR(req->ki_eventfd)) {
ret = PTR_ERR(req->ki_eventfd);
req->ki_eventfd = NULL;
@@ -1833,54 +1821,70 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
goto out_put_req;
}
- req->ki_user_iocb = user_iocb;
- req->ki_user_data = iocb.aio_data;
+ req->ki_res.obj = (u64)(unsigned long)user_iocb;
+ req->ki_res.data = iocb->aio_data;
+ req->ki_res.res = 0;
+ req->ki_res.res2 = 0;
- switch (iocb.aio_lio_opcode) {
+ switch (iocb->aio_lio_opcode) {
case IOCB_CMD_PREAD:
- ret = aio_read(&req->rw, &iocb, false, compat);
+ ret = aio_read(&req->rw, iocb, false, compat);
break;
case IOCB_CMD_PWRITE:
- ret = aio_write(&req->rw, &iocb, false, compat);
+ ret = aio_write(&req->rw, iocb, false, compat);
break;
case IOCB_CMD_PREADV:
- ret = aio_read(&req->rw, &iocb, true, compat);
+ ret = aio_read(&req->rw, iocb, true, compat);
break;
case IOCB_CMD_PWRITEV:
- ret = aio_write(&req->rw, &iocb, true, compat);
+ ret = aio_write(&req->rw, iocb, true, compat);
break;
case IOCB_CMD_FSYNC:
- ret = aio_fsync(&req->fsync, &iocb, false);
+ ret = aio_fsync(&req->fsync, iocb, false);
break;
case IOCB_CMD_FDSYNC:
- ret = aio_fsync(&req->fsync, &iocb, true);
+ ret = aio_fsync(&req->fsync, iocb, true);
break;
case IOCB_CMD_POLL:
- ret = aio_poll(req, &iocb);
+ ret = aio_poll(req, iocb);
break;
default:
- pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
+ pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
ret = -EINVAL;
break;
}
+ /* Done with the synchronous reference */
+ iocb_put(req);
+
/*
* If ret is 0, we'd either done aio_complete() ourselves or have
* arranged for that to be done asynchronously. Anything non-zero
* means that we need to destroy req ourselves.
*/
- if (ret)
- goto out_put_req;
- return 0;
+ if (!ret)
+ return 0;
+
out_put_req:
- put_reqs_available(ctx, 1);
- percpu_ref_put(&ctx->reqs);
if (req->ki_eventfd)
eventfd_ctx_put(req->ki_eventfd);
- kmem_cache_free(kiocb_cachep, req);
+ iocb_destroy(req);
+out_put_reqs_available:
+ put_reqs_available(ctx, 1);
return ret;
}
+static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
+ bool compat)
+{
+ struct iocb iocb;
+
+ if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
+ return -EFAULT;
+
+ return __io_submit_one(ctx, &iocb, user_iocb, compat);
+}
+
/* sys_io_submit:
* Queue the nr iocbs pointed to by iocbpp for processing. Returns
* the number of iocbs queued. May return -EINVAL if the aio_context
@@ -1973,24 +1977,6 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
}
#endif
-/* lookup_kiocb
- * Finds a given iocb for cancellation.
- */
-static struct aio_kiocb *
-lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb)
-{
- struct aio_kiocb *kiocb;
-
- assert_spin_locked(&ctx->ctx_lock);
-
- /* TODO: use a hash or array, this sucks. */
- list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
- if (kiocb->ki_user_iocb == iocb)
- return kiocb;
- }
- return NULL;
-}
-
/* sys_io_cancel:
* Attempts to cancel an iocb previously passed to io_submit. If
* the operation is successfully cancelled, the resulting event is
@@ -2008,6 +1994,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
struct aio_kiocb *kiocb;
int ret = -EINVAL;
u32 key;
+ u64 obj = (u64)(unsigned long)iocb;
if (unlikely(get_user(key, &iocb->aio_key)))
return -EFAULT;
@@ -2019,10 +2006,13 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
return -EINVAL;
spin_lock_irq(&ctx->ctx_lock);
- kiocb = lookup_kiocb(ctx, iocb);
- if (kiocb) {
- ret = kiocb->ki_cancel(&kiocb->rw);
- list_del_init(&kiocb->ki_list);
+ /* TODO: use a hash or array, this sucks. */
+ list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
+ if (kiocb->ki_res.obj == obj) {
+ ret = kiocb->ki_cancel(&kiocb->rw);
+ list_del_init(&kiocb->ki_list);
+ break;
+ }
}
spin_unlock_irq(&ctx->ctx_lock);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 82928cea0209..7f3f64ba464f 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1470,6 +1470,7 @@ void ceph_dentry_lru_del(struct dentry *dn)
unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
{
struct ceph_inode_info *dci = ceph_inode(dir);
+ unsigned hash;
switch (dci->i_dir_layout.dl_dir_hash) {
case 0: /* for backward compat */
@@ -1477,8 +1478,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
return dn->d_name.hash;
default:
- return ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
+ spin_lock(&dn->d_lock);
+ hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
dn->d_name.name, dn->d_name.len);
+ spin_unlock(&dn->d_lock);
+ return hash;
}
}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index bc43c822426a..bfcf11c70bfa 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1290,6 +1290,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
ci->i_prealloc_cap_flush = NULL;
}
+
+ if (drop &&
+ ci->i_wrbuffer_ref_head == 0 &&
+ ci->i_wr_ref == 0 &&
+ ci->i_dirty_caps == 0 &&
+ ci->i_flushing_caps == 0) {
+ ceph_put_snap_context(ci->i_head_snapc);
+ ci->i_head_snapc = NULL;
+ }
}
spin_unlock(&ci->i_ceph_lock);
while (!list_empty(&to_remove)) {
@@ -1945,10 +1954,39 @@ char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
return path;
}
+/* Duplicate the dentry->d_name.name safely */
+static int clone_dentry_name(struct dentry *dentry, const char **ppath,
+ int *ppathlen)
+{
+ u32 len;
+ char *name;
+
+retry:
+ len = READ_ONCE(dentry->d_name.len);
+ name = kmalloc(len + 1, GFP_NOFS);
+ if (!name)
+ return -ENOMEM;
+
+ spin_lock(&dentry->d_lock);
+ if (dentry->d_name.len != len) {
+ spin_unlock(&dentry->d_lock);
+ kfree(name);
+ goto retry;
+ }
+ memcpy(name, dentry->d_name.name, len);
+ spin_unlock(&dentry->d_lock);
+
+ name[len] = '\0';
+ *ppath = name;
+ *ppathlen = len;
+ return 0;
+}
+
static int build_dentry_path(struct dentry *dentry, struct inode *dir,
const char **ppath, int *ppathlen, u64 *pino,
- int *pfreepath)
+ bool *pfreepath, bool parent_locked)
{
+ int ret;
char *path;
rcu_read_lock();
@@ -1957,8 +1995,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
*pino = ceph_ino(dir);
rcu_read_unlock();
- *ppath = dentry->d_name.name;
- *ppathlen = dentry->d_name.len;
+ if (parent_locked) {
+ *ppath = dentry->d_name.name;
+ *ppathlen = dentry->d_name.len;
+ } else {
+ ret = clone_dentry_name(dentry, ppath, ppathlen);
+ if (ret)
+ return ret;
+ *pfreepath = true;
+ }
return 0;
}
rcu_read_unlock();
@@ -1966,13 +2011,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
if (IS_ERR(path))
return PTR_ERR(path);
*ppath = path;
- *pfreepath = 1;
+ *pfreepath = true;
return 0;
}
static int build_inode_path(struct inode *inode,
const char **ppath, int *ppathlen, u64 *pino,
- int *pfreepath)
+ bool *pfreepath)
{
struct dentry *dentry;
char *path;
@@ -1988,7 +2033,7 @@ static int build_inode_path(struct inode *inode,
if (IS_ERR(path))
return PTR_ERR(path);
*ppath = path;
- *pfreepath = 1;
+ *pfreepath = true;
return 0;
}
@@ -1999,7 +2044,7 @@ static int build_inode_path(struct inode *inode,
static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
struct inode *rdiri, const char *rpath,
u64 rino, const char **ppath, int *pathlen,
- u64 *ino, int *freepath)
+ u64 *ino, bool *freepath, bool parent_locked)
{
int r = 0;
@@ -2009,7 +2054,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
ceph_snap(rinode));
} else if (rdentry) {
r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino,
- freepath);
+ freepath, parent_locked);
dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
*ppath);
} else if (rpath || rino) {
@@ -2035,7 +2080,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
const char *path2 = NULL;
u64 ino1 = 0, ino2 = 0;
int pathlen1 = 0, pathlen2 = 0;
- int freepath1 = 0, freepath2 = 0;
+ bool freepath1 = false, freepath2 = false;
int len;
u16 releases;
void *p, *end;
@@ -2043,16 +2088,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
ret = set_request_path_attr(req->r_inode, req->r_dentry,
req->r_parent, req->r_path1, req->r_ino1.ino,
- &path1, &pathlen1, &ino1, &freepath1);
+ &path1, &pathlen1, &ino1, &freepath1,
+ test_bit(CEPH_MDS_R_PARENT_LOCKED,
+ &req->r_req_flags));
if (ret < 0) {
msg = ERR_PTR(ret);
goto out;
}
+ /* If r_old_dentry is set, then assume that its parent is locked */
ret = set_request_path_attr(NULL, req->r_old_dentry,
req->r_old_dentry_dir,
req->r_path2, req->r_ino2.ino,
- &path2, &pathlen2, &ino2, &freepath2);
+ &path2, &pathlen2, &ino2, &freepath2, true);
if (ret < 0) {
msg = ERR_PTR(ret);
goto out_free1;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index f74193da0e09..1f46b02f7314 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -568,7 +568,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
old_snapc = NULL;
update_snapc:
- if (ci->i_head_snapc) {
+ if (ci->i_wrbuffer_ref_head == 0 &&
+ ci->i_wr_ref == 0 &&
+ ci->i_dirty_caps == 0 &&
+ ci->i_flushing_caps == 0) {
+ ci->i_head_snapc = NULL;
+ } else {
ci->i_head_snapc = ceph_get_snap_context(new_snapc);
dout(" new snapc is %p\n", new_snapc);
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index b59ebed4f615..1fadd314ae7f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
if (rc == 0 || rc != -EBUSY)
goto do_rename_exit;
+ /* Don't fall back to using SMB on SMB 2+ mount */
+ if (server->vals->protocol_id != 0)
+ goto do_rename_exit;
+
/* open-file renames don't work across directories */
if (to_dentry->d_parent != from_dentry->d_parent)
goto do_rename_exit;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index c6fd3acc5560..33afb637e6f8 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3285,6 +3285,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
rc);
}
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+ cifs_small_buf_release(req);
return rc == -ENODATA ? 0 : rc;
} else
trace_smb3_read_done(xid, req->PersistentFileId,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c0ba5206cd9d..006c277dc22e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -829,6 +829,7 @@ int ext4_get_inode_usage(struct inode *inode, qsize_t *usage)
bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO);
if (IS_ERR(bh)) {
ret = PTR_ERR(bh);
+ bh = NULL;
goto out;
}
@@ -2907,6 +2908,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
if (error == -EIO)
EXT4_ERROR_INODE(inode, "block %llu read error",
EXT4_I(inode)->i_file_acl);
+ bh = NULL;
goto cleanup;
}
error = ext4_xattr_check_block(inode, bh);
@@ -3063,6 +3065,7 @@ ext4_xattr_block_cache_find(struct inode *inode,
if (IS_ERR(bh)) {
if (PTR_ERR(bh) == -ENOMEM)
return NULL;
+ bh = NULL;
EXT4_ERROR_INODE(inode, "block %lu read error",
(unsigned long)ce->e_value);
} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 6b666d187907..6df9b85caf20 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2052,7 +2052,8 @@ static int nfs23_validate_mount_data(void *options,
memcpy(sap, &data->addr, sizeof(data->addr));
args->nfs_server.addrlen = sizeof(data->addr);
args->nfs_server.port = ntohs(data->addr.sin_port);
- if (!nfs_verify_server_address(sap))
+ if (sap->sa_family != AF_INET ||
+ !nfs_verify_server_address(sap))
goto out_no_address;
if (!(data->flags & NFS_MOUNT_TCP))
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 601bf33c26a0..ebbb0285addb 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -926,8 +926,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
cb->cb_seq_status = 1;
cb->cb_status = 0;
if (minorversion) {
- if (!nfsd41_cb_get_slot(clp, task))
+ if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task))
return;
+ cb->cb_holds_slot = true;
}
rpc_call_start(task);
}
@@ -954,6 +955,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
return true;
}
+ if (!cb->cb_holds_slot)
+ goto need_restart;
+
switch (cb->cb_seq_status) {
case 0:
/*
@@ -992,6 +996,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
cb->cb_seq_status);
}
+ cb->cb_holds_slot = false;
clear_bit(0, &clp->cl_cb_slot_busy);
rpc_wake_up_next(&clp->cl_cb_waitq);
dprintk("%s: freed slot, new seqid=%d\n", __func__,
@@ -1199,6 +1204,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
cb->cb_seq_status = 1;
cb->cb_status = 0;
cb->cb_need_restart = false;
+ cb->cb_holds_slot = false;
}
void nfsd4_run_cb(struct nfsd4_callback *cb)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 0b15dac7e609..0f07ad6dc1ef 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -70,6 +70,7 @@ struct nfsd4_callback {
int cb_seq_status;
int cb_status;
bool cb_need_restart;
+ bool cb_holds_slot;
};
struct nfsd4_callback_ops {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d65390727541..7325baa8f9d4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1626,9 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header)
if (--header->nreg)
return;
- if (parent)
+ if (parent) {
put_links(header);
- start_unregistering(header);
+ start_unregistering(header);
+ }
+
if (!--header->count)
kfree_rcu(header, rcu);
diff --git a/fs/splice.c b/fs/splice.c
index 29e92b506394..c78e0e3ff6c4 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -333,8 +333,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = {
.get = generic_pipe_buf_get,
};
-static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
+int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
{
return 1;
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7b6084854bfe..111c94c4baa1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -304,13 +304,19 @@ enum rw_hint {
struct kiocb {
struct file *ki_filp;
+
+ /* The 'ki_filp' pointer is shared in a union for aio */
+ randomized_struct_fields_start
+
loff_t ki_pos;
void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
void *private;
int ki_flags;
u16 ki_hint;
u16 ki_ioprio; /* See linux/ioprio.h */
-} __randomize_layout;
+
+ randomized_struct_fields_end
+};
static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 3ecd7ea212ae..66ee63cd5968 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -181,6 +181,7 @@ void free_pipe_info(struct pipe_inode_info *);
void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *);
void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 0f39ac487012..f2be5d041ba3 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -382,6 +382,7 @@ void nft_unregister_set(struct nft_set_type *type);
* @dtype: data type (verdict or numeric type defined by userspace)
* @objtype: object type (see NFT_OBJECT_* definitions)
* @size: maximum set size
+ * @use: number of rules references to this set
* @nelems: number of elements
* @ndeact: number of deactivated elements queued for removal
* @timeout: default timeout value in jiffies
@@ -407,6 +408,7 @@ struct nft_set {
u32 dtype;
u32 objtype;
u32 size;
+ u32 use;
atomic_t nelems;
u32 ndeact;
u64 timeout;
@@ -416,7 +418,8 @@ struct nft_set {
unsigned char *udata;
/* runtime data below here */
const struct nft_set_ops *ops ____cacheline_aligned;
- u16 flags:14,
+ u16 flags:13,
+ bound:1,
genmask:2;
u8 klen;
u8 dlen;
@@ -466,10 +469,15 @@ struct nft_set_binding {
u32 flags;
};
+enum nft_trans_phase;
+void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
+ struct nft_set_binding *binding,
+ enum nft_trans_phase phase);
int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *binding);
void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding);
+ struct nft_set_binding *binding, bool commit);
+void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
/**
* enum nft_set_extensions - set extension type IDs
@@ -689,10 +697,12 @@ static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb,
gcb->elems[gcb->head.cnt++] = elem;
}
+struct nft_expr_ops;
/**
* struct nft_expr_type - nf_tables expression type
*
* @select_ops: function to select nft_expr_ops
+ * @release_ops: release nft_expr_ops
* @ops: default ops, used when no select_ops functions is present
* @list: used internally
* @name: Identifier
@@ -705,6 +715,7 @@ static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb,
struct nft_expr_type {
const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *,
const struct nlattr * const tb[]);
+ void (*release_ops)(const struct nft_expr_ops *ops);
const struct nft_expr_ops *ops;
struct list_head list;
const char *name;
@@ -718,13 +729,22 @@ struct nft_expr_type {
#define NFT_EXPR_STATEFUL 0x1
#define NFT_EXPR_GC 0x2
+enum nft_trans_phase {
+ NFT_TRANS_PREPARE,
+ NFT_TRANS_ABORT,
+ NFT_TRANS_COMMIT,
+ NFT_TRANS_RELEASE
+};
+
/**
* struct nft_expr_ops - nf_tables expression operations
*
* @eval: Expression evaluation function
* @size: full expression size, including private data size
* @init: initialization function
- * @destroy: destruction function
+ * @activate: activate expression in the next generation
+ * @deactivate: deactivate expression in next generation
+ * @destroy: destruction function, called after synchronize_rcu
* @dump: function to dump parameters
* @type: expression type
* @validate: validate expression, called during loop detection
@@ -745,7 +765,8 @@ struct nft_expr_ops {
void (*activate)(const struct nft_ctx *ctx,
const struct nft_expr *expr);
void (*deactivate)(const struct nft_ctx *ctx,
- const struct nft_expr *expr);
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase);
void (*destroy)(const struct nft_ctx *ctx,
const struct nft_expr *expr);
void (*destroy_clone)(const struct nft_ctx *ctx,
diff --git a/include/net/netrom.h b/include/net/netrom.h
index 5a0714ff500f..80f15b1c1a48 100644
--- a/include/net/netrom.h
+++ b/include/net/netrom.h
@@ -266,7 +266,7 @@ void nr_stop_idletimer(struct sock *);
int nr_t1timer_running(struct sock *);
/* sysctl_net_netrom.c */
-void nr_register_sysctl(void);
+int nr_register_sysctl(void);
void nr_unregister_sysctl(void);
#endif
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 91e4202b0634..72c07059ef37 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p)
if (dl_entity_is_special(dl_se))
return;
- WARN_ON(hrtimer_active(&dl_se->inactive_timer));
WARN_ON(dl_se->dl_non_contending);
zerolag_time = dl_se->deadline -
@@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p)
* If the "0-lag time" already passed, decrease the active
* utilization now, instead of starting a timer
*/
- if (zerolag_time < 0) {
+ if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
if (dl_task(p))
sub_running_bw(dl_se, dl_rq);
if (!dl_task(p) || p->state == TASK_DEAD) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4aa8e7d90c25..d31916366d39 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2016,6 +2016,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
if (p->last_task_numa_placement) {
delta = runtime - p->last_sum_exec_runtime;
*period = now - p->last_task_numa_placement;
+
+ /* Avoid time going backwards, prevent potential divide error: */
+ if (unlikely((s64)*period < 0))
+ *period = 0;
} else {
delta = p->se.avg.load_sum;
*period = LOAD_AVG_MAX;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 34b4c32b0692..805aef83b5cf 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -730,7 +730,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
preempt_disable_notrace();
time = rb_time_stamp(buffer);
- preempt_enable_no_resched_notrace();
+ preempt_enable_notrace();
return time;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c65cea71d1ee..5455ee05bc3b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -496,8 +496,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
* not modified.
*/
pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
- if (!pid_list)
+ if (!pid_list) {
+ trace_parser_put(&parser);
return -ENOMEM;
+ }
pid_list->pid_max = READ_ONCE(pid_max);
@@ -507,6 +509,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
if (!pid_list->pids) {
+ trace_parser_put(&parser);
kfree(pid_list);
return -ENOMEM;
}
@@ -6800,19 +6803,23 @@ struct buffer_ref {
struct ring_buffer *buffer;
void *page;
int cpu;
- int ref;
+ refcount_t refcount;
};
+static void buffer_ref_release(struct buffer_ref *ref)
+{
+ if (!refcount_dec_and_test(&ref->refcount))
+ return;
+ ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
+ kfree(ref);
+}
+
static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct buffer_ref *ref = (struct buffer_ref *)buf->private;
- if (--ref->ref)
- return;
-
- ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
- kfree(ref);
+ buffer_ref_release(ref);
buf->private = 0;
}
@@ -6821,7 +6828,7 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
{
struct buffer_ref *ref = (struct buffer_ref *)buf->private;
- ref->ref++;
+ refcount_inc(&ref->refcount);
}
/* Pipe buffer operations for a buffer. */
@@ -6829,7 +6836,7 @@ static const struct pipe_buf_operations buffer_pipe_buf_ops = {
.can_merge = 0,
.confirm = generic_pipe_buf_confirm,
.release = buffer_pipe_buf_release,
- .steal = generic_pipe_buf_steal,
+ .steal = generic_pipe_buf_nosteal,
.get = buffer_pipe_buf_get,
};
@@ -6842,11 +6849,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
struct buffer_ref *ref =
(struct buffer_ref *)spd->partial[i].private;
- if (--ref->ref)
- return;
-
- ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
- kfree(ref);
+ buffer_ref_release(ref);
spd->partial[i].private = 0;
}
@@ -6901,7 +6904,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- ref->ref = 1;
+ refcount_set(&ref->refcount, 1);
ref->buffer = iter->trace_buffer->buffer;
ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
if (IS_ERR(ref->page)) {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0280deac392e..cd8b61bded78 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2908,6 +2908,9 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
if (WARN_ON(!wq_online))
return false;
+ if (WARN_ON(!work->func))
+ return false;
+
if (!from_cancel) {
lock_map_acquire(&work->lockdep_map);
lock_map_release(&work->lockdep_map);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4966c4fbe7f7..3dea52f7be9c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1934,6 +1934,7 @@ config TEST_KMOD
depends on m
depends on BLOCK && (64BIT || LBDAF) # for XFS, BTRFS
depends on NETDEVICES && NET_CORE && INET # for TUN
+ depends on BLOCK
select TEST_LKM
select XFS_FS
select TUN
diff --git a/mm/memory.c b/mm/memory.c
index 5b3f71bcd1ae..9c69278173b7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1787,10 +1787,15 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
* in may not match the PFN we have mapped if the
* mapped PFN is a writeable COW page. In the mkwrite
* case we are creating a writable PTE for a shared
- * mapping and we expect the PFNs to match.
+ * mapping and we expect the PFNs to match. If they
+ * don't match, we are likely racing with block
+ * allocation and mapping invalidation so just skip the
+ * update.
*/
- if (WARN_ON_ONCE(pte_pfn(*pte) != pfn_t_to_pfn(pfn)))
+ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
goto out_unlock;
+ }
entry = *pte;
goto out_mkwrite;
} else
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index f77888ec93f1..0bb4d712b80c 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2032,7 +2032,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32,
if (match_kern)
match_kern->match_size = ret;
- if (WARN_ON(type == EBT_COMPAT_TARGET && size_left))
+ /* rule should have no remaining data after target */
+ if (type == EBT_COMPAT_TARGET && size_left)
return -EINVAL;
match32 = (struct compat_ebt_entry_mwt *) buf;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 98c81c21b753..8bacbcd2db90 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1185,25 +1185,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
return dst;
}
-static void ipv4_link_failure(struct sk_buff *skb)
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
{
struct ip_options opt;
- struct rtable *rt;
int res;
/* Recompile ip options since IPCB may not be valid anymore.
+ * Also check we have a reasonable ipv4 header.
*/
- memset(&opt, 0, sizeof(opt));
- opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+ ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+ return;
- rcu_read_lock();
- res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
- rcu_read_unlock();
+ memset(&opt, 0, sizeof(opt));
+ if (ip_hdr(skb)->ihl > 5) {
+ if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+ return;
+ opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
- if (res)
- return;
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ rcu_read_unlock();
+ if (res)
+ return;
+ }
__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
+static void ipv4_link_failure(struct sk_buff *skb)
+{
+ struct rtable *rt;
+
+ ipv4_send_dest_unreach(skb);
rt = skb_rtable(skb);
if (rt)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 891ed2f91467..ce64453d337d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
static int comp_sack_nr_max = 255;
static u32 u32_max_div_HZ = UINT_MAX / HZ;
+static int one_day_secs = 24 * 3600;
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
@@ -1140,7 +1141,9 @@ static struct ctl_table ipv4_net_table[] = {
.data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one_day_secs
},
{
.procname = "tcp_autocorking",
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 8fd8d06454d6..2d4e048762f6 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -896,12 +896,13 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
{
struct ip_vs_dest *dest;
unsigned int atype, i;
- int ret = 0;
EnterFunction(2);
#ifdef CONFIG_IP_VS_IPV6
if (udest->af == AF_INET6) {
+ int ret;
+
atype = ipv6_addr_type(&udest->addr.in6);
if ((!(atype & IPV6_ADDR_UNICAST) ||
atype & IPV6_ADDR_LINKLOCAL) &&
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c06393fc716d..1af54119bafc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -112,6 +112,23 @@ static void nft_trans_destroy(struct nft_trans *trans)
kfree(trans);
}
+static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+ struct net *net = ctx->net;
+ struct nft_trans *trans;
+
+ if (!nft_set_is_anonymous(set))
+ return;
+
+ list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
+ if (trans->msg_type == NFT_MSG_NEWSET &&
+ nft_trans_set(trans) == set) {
+ set->bound = true;
+ break;
+ }
+ }
+}
+
static int nf_tables_register_hook(struct net *net,
const struct nft_table *table,
struct nft_chain *chain)
@@ -222,14 +239,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
}
static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
- struct nft_rule *rule)
+ struct nft_rule *rule,
+ enum nft_trans_phase phase)
{
struct nft_expr *expr;
expr = nft_expr_first(rule);
while (expr != nft_expr_last(rule) && expr->ops) {
if (expr->ops->deactivate)
- expr->ops->deactivate(ctx, expr);
+ expr->ops->deactivate(ctx, expr, phase);
expr = nft_expr_next(expr);
}
@@ -280,7 +298,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
nft_trans_destroy(trans);
return err;
}
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE);
return 0;
}
@@ -301,7 +319,7 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx)
return 0;
}
-static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type,
+static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
struct nft_set *set)
{
struct nft_trans *trans;
@@ -321,7 +339,7 @@ static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type,
return 0;
}
-static int nft_delset(struct nft_ctx *ctx, struct nft_set *set)
+static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
{
int err;
@@ -2105,6 +2123,7 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx,
{
struct nft_expr_info info;
struct nft_expr *expr;
+ struct module *owner;
int err;
err = nf_tables_expr_parse(ctx, nla, &info);
@@ -2124,7 +2143,11 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx,
err3:
kfree(expr);
err2:
- module_put(info.ops->type->owner);
+ owner = info.ops->type->owner;
+ if (info.ops->type->release_ops)
+ info.ops->type->release_ops(info.ops);
+
+ module_put(owner);
err1:
return ERR_PTR(err);
}
@@ -2458,7 +2481,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
static void nf_tables_rule_release(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE);
nf_tables_rule_destroy(ctx, rule);
}
@@ -3562,19 +3585,15 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
static void nft_set_destroy(struct nft_set *set)
{
+ if (WARN_ON(set->use > 0))
+ return;
+
set->ops->destroy(set);
module_put(to_set_type(set->ops)->owner);
kfree(set->name);
kvfree(set);
}
-static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
-{
- list_del_rcu(&set->list);
- nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC);
- nft_set_destroy(set);
-}
-
static int nf_tables_delset(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
@@ -3609,7 +3628,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk,
NL_SET_BAD_ATTR(extack, attr);
return PTR_ERR(set);
}
- if (!list_empty(&set->bindings) ||
+ if (set->use ||
(nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) {
NL_SET_BAD_ATTR(extack, attr);
return -EBUSY;
@@ -3639,6 +3658,9 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *i;
struct nft_set_iter iter;
+ if (set->use == UINT_MAX)
+ return -EOVERFLOW;
+
if (!list_empty(&set->bindings) && nft_set_is_anonymous(set))
return -EBUSY;
@@ -3665,21 +3687,53 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
bind:
binding->chain = ctx->chain;
list_add_tail_rcu(&binding->list, &set->bindings);
+ nft_set_trans_bind(ctx, set);
+ set->use++;
+
return 0;
}
EXPORT_SYMBOL_GPL(nf_tables_bind_set);
void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding)
+ struct nft_set_binding *binding, bool event)
{
list_del_rcu(&binding->list);
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set))
- nf_tables_set_destroy(ctx, set);
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) {
+ list_del_rcu(&set->list);
+ if (event)
+ nf_tables_set_notify(ctx, set, NFT_MSG_DELSET,
+ GFP_KERNEL);
+ }
}
EXPORT_SYMBOL_GPL(nf_tables_unbind_set);
+void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
+ struct nft_set_binding *binding,
+ enum nft_trans_phase phase)
+{
+ switch (phase) {
+ case NFT_TRANS_PREPARE:
+ set->use--;
+ return;
+ case NFT_TRANS_ABORT:
+ case NFT_TRANS_RELEASE:
+ set->use--;
+ /* fall through */
+ default:
+ nf_tables_unbind_set(ctx, set, binding,
+ phase == NFT_TRANS_COMMIT);
+ }
+}
+EXPORT_SYMBOL_GPL(nf_tables_deactivate_set);
+
+void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set)
+{
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set))
+ nft_set_destroy(set);
+}
+EXPORT_SYMBOL_GPL(nf_tables_destroy_set);
+
const struct nft_set_ext_type nft_set_ext_types[] = {
[NFT_SET_EXT_KEY] = {
.align = __alignof__(u32),
@@ -6429,6 +6483,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nf_tables_rule_notify(&trans->ctx,
nft_trans_rule(trans),
NFT_MSG_DELRULE);
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_COMMIT);
break;
case NFT_MSG_NEWSET:
nft_clear(net, nft_trans_set(trans));
@@ -6577,7 +6634,9 @@ static int __nf_tables_abort(struct net *net)
case NFT_MSG_NEWRULE:
trans->ctx.chain->use--;
list_del_rcu(&nft_trans_rule(trans)->list);
- nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans));
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_ABORT);
break;
case NFT_MSG_DELRULE:
trans->ctx.chain->use++;
@@ -6587,6 +6646,10 @@ static int __nf_tables_abort(struct net *net)
break;
case NFT_MSG_NEWSET:
trans->ctx.table->use--;
+ if (nft_trans_set(trans)->bound) {
+ nft_trans_destroy(trans);
+ break;
+ }
list_del_rcu(&nft_trans_set(trans)->list);
break;
case NFT_MSG_DELSET:
@@ -6595,8 +6658,11 @@ static int __nf_tables_abort(struct net *net)
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSETELEM:
+ if (nft_trans_elem_set(trans)->bound) {
+ nft_trans_destroy(trans);
+ break;
+ }
te = (struct nft_trans_elem *)trans->data;
-
te->set->ops->remove(net, te->set, &te->elem);
atomic_dec(&te->set->nelems);
break;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 38da1f5436b4..1245e02239d9 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -23,19 +23,6 @@
#include <linux/netfilter_arp/arp_tables.h>
#include <net/netfilter/nf_tables.h>
-struct nft_xt {
- struct list_head head;
- struct nft_expr_ops ops;
- unsigned int refcnt;
-
- /* Unlike other expressions, ops doesn't have static storage duration.
- * nft core assumes they do. We use kfree_rcu so that nft core can
- * can check expr->ops->size even after nft_compat->destroy() frees
- * the nft_xt struct that holds the ops structure.
- */
- struct rcu_head rcu_head;
-};
-
/* Used for matches where *info is larger than X byte */
#define NFT_MATCH_LARGE_THRESH 192
@@ -43,17 +30,6 @@ struct nft_xt_match_priv {
void *info;
};
-static bool nft_xt_put(struct nft_xt *xt)
-{
- if (--xt->refcnt == 0) {
- list_del(&xt->head);
- kfree_rcu(xt, rcu_head);
- return true;
- }
-
- return false;
-}
-
static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx,
const char *tablename)
{
@@ -248,7 +224,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
struct xt_target *target = expr->ops->data;
struct xt_tgchk_param par;
size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO]));
- struct nft_xt *nft_xt;
u16 proto = 0;
bool inv = false;
union nft_entry e = {};
@@ -272,8 +247,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
if (!target->target)
return -EINVAL;
- nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
return 0;
}
@@ -292,8 +265,8 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
if (par.target->destroy != NULL)
par.target->destroy(&par);
- if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
- module_put(me);
+ module_put(me);
+ kfree(expr->ops);
}
static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -447,7 +420,6 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
struct xt_match *match = expr->ops->data;
struct xt_mtchk_param par;
size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO]));
- struct nft_xt *nft_xt;
u16 proto = 0;
bool inv = false;
union nft_entry e = {};
@@ -463,13 +435,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
- ret = xt_check_match(&par, size, proto, inv);
- if (ret < 0)
- return ret;
-
- nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
- return 0;
+ return xt_check_match(&par, size, proto, inv);
}
static int
@@ -512,8 +478,8 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
if (par.match->destroy != NULL)
par.match->destroy(&par);
- if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
- module_put(me);
+ module_put(me);
+ kfree(expr->ops);
}
static void
@@ -715,22 +681,13 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = {
.cb = nfnl_nft_compat_cb,
};
-static LIST_HEAD(nft_match_list);
-
static struct nft_expr_type nft_match_type;
-static bool nft_match_cmp(const struct xt_match *match,
- const char *name, u32 rev, u32 family)
-{
- return strcmp(match->name, name) == 0 && match->revision == rev &&
- (match->family == NFPROTO_UNSPEC || match->family == family);
-}
-
static const struct nft_expr_ops *
nft_match_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
- struct nft_xt *nft_match;
+ struct nft_expr_ops *ops;
struct xt_match *match;
unsigned int matchsize;
char *mt_name;
@@ -746,14 +703,6 @@ nft_match_select_ops(const struct nft_ctx *ctx,
rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV]));
family = ctx->family;
- /* Re-use the existing match if it's already loaded. */
- list_for_each_entry(nft_match, &nft_match_list, head) {
- struct xt_match *match = nft_match->ops.data;
-
- if (nft_match_cmp(match, mt_name, rev, family))
- return &nft_match->ops;
- }
-
match = xt_request_find_match(family, mt_name, rev);
if (IS_ERR(match))
return ERR_PTR(-ENOENT);
@@ -763,66 +712,62 @@ nft_match_select_ops(const struct nft_ctx *ctx,
goto err;
}
- /* This is the first time we use this match, allocate operations */
- nft_match = kzalloc(sizeof(struct nft_xt), GFP_KERNEL);
- if (nft_match == NULL) {
+ ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
+ if (!ops) {
err = -ENOMEM;
goto err;
}
- nft_match->refcnt = 0;
- nft_match->ops.type = &nft_match_type;
- nft_match->ops.eval = nft_match_eval;
- nft_match->ops.init = nft_match_init;
- nft_match->ops.destroy = nft_match_destroy;
- nft_match->ops.dump = nft_match_dump;
- nft_match->ops.validate = nft_match_validate;
- nft_match->ops.data = match;
+ ops->type = &nft_match_type;
+ ops->eval = nft_match_eval;
+ ops->init = nft_match_init;
+ ops->destroy = nft_match_destroy;
+ ops->dump = nft_match_dump;
+ ops->validate = nft_match_validate;
+ ops->data = match;
matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
if (matchsize > NFT_MATCH_LARGE_THRESH) {
matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv));
- nft_match->ops.eval = nft_match_large_eval;
- nft_match->ops.init = nft_match_large_init;
- nft_match->ops.destroy = nft_match_large_destroy;
- nft_match->ops.dump = nft_match_large_dump;
+ ops->eval = nft_match_large_eval;
+ ops->init = nft_match_large_init;
+ ops->destroy = nft_match_large_destroy;
+ ops->dump = nft_match_large_dump;
}
- nft_match->ops.size = matchsize;
-
- list_add(&nft_match->head, &nft_match_list);
+ ops->size = matchsize;
- return &nft_match->ops;
+ return ops;
err:
module_put(match->me);
return ERR_PTR(err);
}
+static void nft_match_release_ops(const struct nft_expr_ops *ops)
+{
+ struct xt_match *match = ops->data;
+
+ module_put(match->me);
+ kfree(ops);
+}
+
static struct nft_expr_type nft_match_type __read_mostly = {
.name = "match",
.select_ops = nft_match_select_ops,
+ .release_ops = nft_match_release_ops,
.policy = nft_match_policy,
.maxattr = NFTA_MATCH_MAX,
.owner = THIS_MODULE,
};
-static LIST_HEAD(nft_target_list);
-
static struct nft_expr_type nft_target_type;
-static bool nft_target_cmp(const struct xt_target *tg,
- const char *name, u32 rev, u32 family)
-{
- return strcmp(tg->name, name) == 0 && tg->revision == rev &&
- (tg->family == NFPROTO_UNSPEC || tg->family == family);
-}
-
static const struct nft_expr_ops *
nft_target_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
- struct nft_xt *nft_target;
+ struct nft_expr_ops *ops;
struct xt_target *target;
char *tg_name;
u32 rev, family;
@@ -842,17 +787,6 @@ nft_target_select_ops(const struct nft_ctx *ctx,
strcmp(tg_name, "standard") == 0)
return ERR_PTR(-EINVAL);
- /* Re-use the existing target if it's already loaded. */
- list_for_each_entry(nft_target, &nft_target_list, head) {
- struct xt_target *target = nft_target->ops.data;
-
- if (!target->target)
- continue;
-
- if (nft_target_cmp(target, tg_name, rev, family))
- return &nft_target->ops;
- }
-
target = xt_request_find_target(family, tg_name, rev);
if (IS_ERR(target))
return ERR_PTR(-ENOENT);
@@ -867,38 +801,43 @@ nft_target_select_ops(const struct nft_ctx *ctx,
goto err;
}
- /* This is the first time we use this target, allocate operations */
- nft_target = kzalloc(sizeof(struct nft_xt), GFP_KERNEL);
- if (nft_target == NULL) {
+ ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
+ if (!ops) {
err = -ENOMEM;
goto err;
}
- nft_target->refcnt = 0;
- nft_target->ops.type = &nft_target_type;
- nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
- nft_target->ops.init = nft_target_init;
- nft_target->ops.destroy = nft_target_destroy;
- nft_target->ops.dump = nft_target_dump;
- nft_target->ops.validate = nft_target_validate;
- nft_target->ops.data = target;
+ ops->type = &nft_target_type;
+ ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
+ ops->init = nft_target_init;
+ ops->destroy = nft_target_destroy;
+ ops->dump = nft_target_dump;
+ ops->validate = nft_target_validate;
+ ops->data = target;
if (family == NFPROTO_BRIDGE)
- nft_target->ops.eval = nft_target_eval_bridge;
+ ops->eval = nft_target_eval_bridge;
else
- nft_target->ops.eval = nft_target_eval_xt;
-
- list_add(&nft_target->head, &nft_target_list);
+ ops->eval = nft_target_eval_xt;
- return &nft_target->ops;
+ return ops;
err:
module_put(target->me);
return ERR_PTR(err);
}
+static void nft_target_release_ops(const struct nft_expr_ops *ops)
+{
+ struct xt_target *target = ops->data;
+
+ module_put(target->me);
+ kfree(ops);
+}
+
static struct nft_expr_type nft_target_type __read_mostly = {
.name = "target",
.select_ops = nft_target_select_ops,
+ .release_ops = nft_target_release_ops,
.policy = nft_target_policy,
.maxattr = NFTA_TARGET_MAX,
.owner = THIS_MODULE,
@@ -923,7 +862,6 @@ static int __init nft_compat_module_init(void)
}
return ret;
-
err_target:
nft_unregister_expr(&nft_target_type);
err_match:
@@ -933,32 +871,6 @@ static int __init nft_compat_module_init(void)
static void __exit nft_compat_module_exit(void)
{
- struct nft_xt *xt, *next;
-
- /* list should be empty here, it can be non-empty only in case there
- * was an error that caused nft_xt expr to not be initialized fully
- * and noone else requested the same expression later.
- *
- * In this case, the lists contain 0-refcount entries that still
- * hold module reference.
- */
- list_for_each_entry_safe(xt, next, &nft_target_list, head) {
- struct xt_target *target = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(target->me);
- kfree(xt);
- }
-
- list_for_each_entry_safe(xt, next, &nft_match_list, head) {
- struct xt_match *match = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(match->me);
- kfree(xt);
- }
nfnetlink_subsys_unregister(&nfnl_compat_subsys);
nft_unregister_expr(&nft_target_type);
nft_unregister_expr(&nft_match_type);
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 6e91a37d57f2..eb7f9a5f2aeb 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -235,14 +235,32 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
return err;
}
+static void nft_dynset_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
+{
+ struct nft_dynset *priv = nft_expr_priv(expr);
+
+ nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase);
+}
+
+static void nft_dynset_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_dynset *priv = nft_expr_priv(expr);
+
+ priv->set->use++;
+}
+
static void nft_dynset_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr)
{
struct nft_dynset *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
if (priv->expr != NULL)
nft_expr_destroy(ctx, priv->expr);
+
+ nf_tables_destroy_set(ctx, priv->set);
}
static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -279,6 +297,8 @@ static const struct nft_expr_ops nft_dynset_ops = {
.eval = nft_dynset_eval,
.init = nft_dynset_init,
.destroy = nft_dynset_destroy,
+ .activate = nft_dynset_activate,
+ .deactivate = nft_dynset_deactivate,
.dump = nft_dynset_dump,
};
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 0777a93211e2..3f6d1d2a6281 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx,
}
static void nft_immediate_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+ if (phase == NFT_TRANS_COMMIT)
+ return;
+
return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg));
}
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index ad13e8643599..161c3451a747 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -121,12 +121,29 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
return 0;
}
+static void nft_lookup_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
+{
+ struct nft_lookup *priv = nft_expr_priv(expr);
+
+ nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase);
+}
+
+static void nft_lookup_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_lookup *priv = nft_expr_priv(expr);
+
+ priv->set->use++;
+}
+
static void nft_lookup_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr)
{
struct nft_lookup *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ nf_tables_destroy_set(ctx, priv->set);
}
static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -209,6 +226,8 @@ static const struct nft_expr_ops nft_lookup_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
.eval = nft_lookup_eval,
.init = nft_lookup_init,
+ .activate = nft_lookup_activate,
+ .deactivate = nft_lookup_deactivate,
.destroy = nft_lookup_destroy,
.dump = nft_lookup_dump,
.validate = nft_lookup_validate,
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index cdf348f751ec..bf92a40dd1b2 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -64,21 +64,34 @@ static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static void nft_objref_destroy(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+static void nft_objref_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_object *obj = nft_objref_priv(expr);
+ if (phase == NFT_TRANS_COMMIT)
+ return;
+
obj->use--;
}
+static void nft_objref_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_object *obj = nft_objref_priv(expr);
+
+ obj->use++;
+}
+
static struct nft_expr_type nft_objref_type;
static const struct nft_expr_ops nft_objref_ops = {
.type = &nft_objref_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_object *)),
.eval = nft_objref_eval,
.init = nft_objref_init,
- .destroy = nft_objref_destroy,
+ .activate = nft_objref_activate,
+ .deactivate = nft_objref_deactivate,
.dump = nft_objref_dump,
};
@@ -155,12 +168,29 @@ static int nft_objref_map_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
+static void nft_objref_map_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
+{
+ struct nft_objref_map *priv = nft_expr_priv(expr);
+
+ nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase);
+}
+
+static void nft_objref_map_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_objref_map *priv = nft_expr_priv(expr);
+
+ priv->set->use++;
+}
+
static void nft_objref_map_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr)
{
struct nft_objref_map *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ nf_tables_destroy_set(ctx, priv->set);
}
static struct nft_expr_type nft_objref_type;
@@ -169,6 +199,8 @@ static const struct nft_expr_ops nft_objref_map_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)),
.eval = nft_objref_map_eval,
.init = nft_objref_map_init,
+ .activate = nft_objref_map_activate,
+ .deactivate = nft_objref_map_deactivate,
.destroy = nft_objref_map_destroy,
.dump = nft_objref_map_dump,
};
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 1d3144d19903..71ffd1a6dc7c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1392,18 +1392,22 @@ static int __init nr_proto_init(void)
int i;
int rc = proto_register(&nr_proto, 0);
- if (rc != 0)
- goto out;
+ if (rc)
+ return rc;
if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n");
- return -1;
+ pr_err("NET/ROM: %s - nr_ndevs parameter too large\n",
+ __func__);
+ rc = -EINVAL;
+ goto unregister_proto;
}
dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL);
- if (dev_nr == NULL) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n");
- return -1;
+ if (!dev_nr) {
+ pr_err("NET/ROM: %s - unable to allocate device array\n",
+ __func__);
+ rc = -ENOMEM;
+ goto unregister_proto;
}
for (i = 0; i < nr_ndevs; i++) {
@@ -1413,13 +1417,13 @@ static int __init nr_proto_init(void)
sprintf(name, "nr%d", i);
dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup);
if (!dev) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n");
+ rc = -ENOMEM;
goto fail;
}
dev->base_addr = i;
- if (register_netdev(dev)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n");
+ rc = register_netdev(dev);
+ if (rc) {
free_netdev(dev);
goto fail;
}
@@ -1427,36 +1431,64 @@ static int __init nr_proto_init(void)
dev_nr[i] = dev;
}
- if (sock_register(&nr_family_ops)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n");
+ rc = sock_register(&nr_family_ops);
+ if (rc)
goto fail;
- }
- register_netdevice_notifier(&nr_dev_notifier);
+ rc = register_netdevice_notifier(&nr_dev_notifier);
+ if (rc)
+ goto out_sock;
ax25_register_pid(&nr_pid);
ax25_linkfail_register(&nr_linkfail_notifier);
#ifdef CONFIG_SYSCTL
- nr_register_sysctl();
+ rc = nr_register_sysctl();
+ if (rc)
+ goto out_sysctl;
#endif
nr_loopback_init();
- proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops);
- proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops);
- proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops);
-out:
- return rc;
+ rc = -ENOMEM;
+ if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops))
+ goto proc_remove1;
+ if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net,
+ &nr_neigh_seqops))
+ goto proc_remove2;
+ if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net,
+ &nr_node_seqops))
+ goto proc_remove3;
+
+ return 0;
+
+proc_remove3:
+ remove_proc_entry("nr_neigh", init_net.proc_net);
+proc_remove2:
+ remove_proc_entry("nr", init_net.proc_net);
+proc_remove1:
+
+ nr_loopback_clear();
+ nr_rt_free();
+
+#ifdef CONFIG_SYSCTL
+ nr_unregister_sysctl();
+out_sysctl:
+#endif
+ ax25_linkfail_release(&nr_linkfail_notifier);
+ ax25_protocol_release(AX25_P_NETROM);
+ unregister_netdevice_notifier(&nr_dev_notifier);
+out_sock:
+ sock_unregister(PF_NETROM);
fail:
while (--i >= 0) {
unregister_netdev(dev_nr[i]);
free_netdev(dev_nr[i]);
}
kfree(dev_nr);
+unregister_proto:
proto_unregister(&nr_proto);
- rc = -1;
- goto out;
+ return rc;
}
module_init(nr_proto_init);
diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c
index 215ad22a9647..93d13f019981 100644
--- a/net/netrom/nr_loopback.c
+++ b/net/netrom/nr_loopback.c
@@ -70,7 +70,7 @@ static void nr_loopback_timer(struct timer_list *unused)
}
}
-void __exit nr_loopback_clear(void)
+void nr_loopback_clear(void)
{
del_timer_sync(&loopback_timer);
skb_queue_purge(&loopback_queue);
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 6485f593e2f0..b76aa668a94b 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -953,7 +953,7 @@ const struct seq_operations nr_neigh_seqops = {
/*
* Free all memory associated with the nodes and routes lists.
*/
-void __exit nr_rt_free(void)
+void nr_rt_free(void)
{
struct nr_neigh *s = NULL;
struct nr_node *t = NULL;
diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c
index ba1c368b3f18..771011b84270 100644
--- a/net/netrom/sysctl_net_netrom.c
+++ b/net/netrom/sysctl_net_netrom.c
@@ -146,9 +146,12 @@ static struct ctl_table nr_table[] = {
{ }
};
-void __init nr_register_sysctl(void)
+int __init nr_register_sysctl(void)
{
nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table);
+ if (!nr_table_header)
+ return -ENOMEM;
+ return 0;
}
void nr_unregister_sysctl(void)
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 65387e1e6964..cd7e01ea8144 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -506,6 +506,9 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
struct rds_sock *rs = rds_sk_to_rs(sk);
int ret = 0;
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
+
lock_sock(sk);
switch (uaddr->sa_family) {
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 17c9d9f0c848..0f4398e7f2a7 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -173,6 +173,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
/* We allow an RDS socket to be bound to either IPv4 or IPv6
* address.
*/
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
if (uaddr->sa_family == AF_INET) {
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index e0f70c4051b6..01e764f8f224 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
else
pool = rds_ibdev->mr_1m_pool;
+ if (atomic_read(&pool->dirty_count) >= pool->max_items / 10)
+ queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
+
+ /* Switch pools if one of the pool is reaching upper limit */
+ if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) {
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ pool = rds_ibdev->mr_1m_pool;
+ else
+ pool = rds_ibdev->mr_8k_pool;
+ }
+
ibmr = rds_ib_try_reuse_ibmr(pool);
if (ibmr)
return ibmr;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 63c8d107adcf..d664e9ade74d 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
struct rds_ib_mr *ibmr = NULL;
int iter = 0;
- if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10)
- queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
-
while (1) {
ibmr = rds_ib_reuse_mr(pool);
if (ibmr)
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 7af4f99c4a93..094a6621f8e8 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -16,6 +16,7 @@
#include <linux/init.h>
static struct sk_buff_head loopback_queue;
+#define ROSE_LOOPBACK_LIMIT 1000
static struct timer_list loopback_timer;
static void rose_set_loopback_timer(void);
@@ -35,29 +36,27 @@ static int rose_loopback_running(void)
int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh)
{
- struct sk_buff *skbn;
+ struct sk_buff *skbn = NULL;
- skbn = skb_clone(skb, GFP_ATOMIC);
+ if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT)
+ skbn = skb_clone(skb, GFP_ATOMIC);
- kfree_skb(skb);
-
- if (skbn != NULL) {
+ if (skbn) {
+ consume_skb(skb);
skb_queue_tail(&loopback_queue, skbn);
if (!rose_loopback_running())
rose_set_loopback_timer();
+ } else {
+ kfree_skb(skb);
}
return 1;
}
-
static void rose_set_loopback_timer(void)
{
- del_timer(&loopback_timer);
-
- loopback_timer.expires = jiffies + 10;
- add_timer(&loopback_timer);
+ mod_timer(&loopback_timer, jiffies + 10);
}
static void rose_loopback_timer(struct timer_list *unused)
@@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused)
struct sock *sk;
unsigned short frametype;
unsigned int lci_i, lci_o;
+ int count;
- while ((skb = skb_dequeue(&loopback_queue)) != NULL) {
+ for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) {
+ skb = skb_dequeue(&loopback_queue);
+ if (!skb)
+ return;
if (skb->len < ROSE_MIN_LEN) {
kfree_skb(skb);
continue;
@@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused)
kfree_skb(skb);
}
}
+ if (!skb_queue_empty(&loopback_queue))
+ mod_timer(&loopback_timer, jiffies + 1);
}
void __exit rose_loopback_clear(void)
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 570b49d2da42..d591f54cb91f 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1155,19 +1155,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
* handle data received on the local endpoint
* - may be called in interrupt context
*
- * The socket is locked by the caller and this prevents the socket from being
- * shut down and the local endpoint from going away, thus sk_user_data will not
- * be cleared until this function returns.
+ * [!] Note that as this is called from the encap_rcv hook, the socket is not
+ * held locked by the caller and nothing prevents sk_user_data on the UDP from
+ * being cleared in the middle of processing this function.
*
* Called with the RCU read lock held from the IP layer via UDP.
*/
int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
{
+ struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk);
struct rxrpc_connection *conn;
struct rxrpc_channel *chan;
struct rxrpc_call *call = NULL;
struct rxrpc_skb_priv *sp;
- struct rxrpc_local *local = udp_sk->sk_user_data;
struct rxrpc_peer *peer = NULL;
struct rxrpc_sock *rx = NULL;
unsigned int channel;
@@ -1175,6 +1175,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
_enter("%p", udp_sk);
+ if (unlikely(!local)) {
+ kfree_skb(skb);
+ return 0;
+ }
if (skb->tstamp == 0)
skb->tstamp = ktime_get_real();
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 0906e51d3cfb..10317dbdab5f 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -304,7 +304,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net,
ret = -ENOMEM;
sock_error:
mutex_unlock(&rxnet->local_mutex);
- kfree(local);
+ if (local)
+ call_rcu(&local->rcu, rxrpc_local_rcu);
_leave(" = %d", ret);
return ERR_PTR(ret);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index b6e8eccf2a52..214440c5b14e 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -54,6 +54,7 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail)
h->last_refresh = now;
}
+static inline int cache_is_valid(struct cache_head *h);
static void cache_fresh_locked(struct cache_head *head, time_t expiry,
struct cache_detail *detail);
static void cache_fresh_unlocked(struct cache_head *head,
@@ -100,6 +101,8 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
if (cache_is_expired(detail, tmp)) {
hlist_del_init(&tmp->cache_list);
detail->entries --;
+ if (cache_is_valid(tmp) == -EAGAIN)
+ set_bit(CACHE_NEGATIVE, &tmp->flags);
cache_fresh_locked(tmp, 0, detail);
freeme = tmp;
break;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 0b21187d74df..588d5aa14c41 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -267,8 +267,14 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
if (msg->rep_type)
tipc_tlv_init(msg->rep, msg->rep_type);
- if (cmd->header)
- (*cmd->header)(msg);
+ if (cmd->header) {
+ err = (*cmd->header)(msg);
+ if (err) {
+ kfree_skb(msg->rep);
+ msg->rep = NULL;
+ return err;
+ }
+ }
arg = nlmsg_new(0, GFP_KERNEL);
if (!arg) {
@@ -397,7 +403,12 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
if (!bearer)
return -EMSGSIZE;
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+ len = TLV_GET_DATA_LEN(msg->req);
+ len -= offsetof(struct tipc_bearer_config, name);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_BEARER_NAME);
if (!string_is_valid(b->name, len))
return -EINVAL;
@@ -766,7 +777,12 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd,
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+ len = TLV_GET_DATA_LEN(msg->req);
+ len -= offsetof(struct tipc_link_config, name);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_LINK_NAME);
if (!string_is_valid(lc->name, len))
return -EINVAL;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 961b07d4d41c..c9588b682db4 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -874,7 +874,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
goto release_netdev;
free_sw_resources:
+ up_read(&device_offload_lock);
tls_sw_free_resources_rx(sk);
+ down_read(&device_offload_lock);
release_ctx:
ctx->priv_ctx_rx = NULL;
release_netdev:
@@ -909,8 +911,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
}
out:
up_read(&device_offload_lock);
- kfree(tls_ctx->rx.rec_seq);
- kfree(tls_ctx->rx.iv);
tls_sw_release_resources_rx(sk);
}
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 450a6dbc5a88..ef8934fd8698 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -193,6 +193,9 @@ static void update_chksum(struct sk_buff *skb, int headln)
static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
{
+ struct sock *sk = skb->sk;
+ int delta;
+
skb_copy_header(nskb, skb);
skb_put(nskb, skb->len);
@@ -200,11 +203,15 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
update_chksum(nskb, headln);
nskb->destructor = skb->destructor;
- nskb->sk = skb->sk;
+ nskb->sk = sk;
skb->destructor = NULL;
skb->sk = NULL;
- refcount_add(nskb->truesize - skb->truesize,
- &nskb->sk->sk_wmem_alloc);
+
+ delta = nskb->truesize - skb->truesize;
+ if (likely(delta < 0))
+ WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+ else if (delta)
+ refcount_add(delta, &sk->sk_wmem_alloc);
}
/* This function may be called after the user socket is already
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index a091c03abcb2..25b3fb585777 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -290,11 +290,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
tls_sw_free_resources_tx(sk);
}
- if (ctx->rx_conf == TLS_SW) {
- kfree(ctx->rx.rec_seq);
- kfree(ctx->rx.iv);
+ if (ctx->rx_conf == TLS_SW)
tls_sw_free_resources_rx(sk);
- }
#ifdef CONFIG_TLS_DEVICE
if (ctx->rx_conf == TLS_HW)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index b9c6ecfbcfea..6848a8196711 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1118,6 +1118,9 @@ void tls_sw_release_resources_rx(struct sock *sk)
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+ kfree(tls_ctx->rx.rec_seq);
+ kfree(tls_ctx->rx.iv);
+
if (ctx->aead_recv) {
kfree_skb(ctx->recv_pkt);
ctx->recv_pkt = NULL;
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 3ae3a33da70b..602715fc9a75 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -662,6 +662,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
*/
static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
{
+ const struct virtio_transport *t;
+ struct virtio_vsock_pkt *reply;
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = le16_to_cpu(pkt->hdr.type),
@@ -672,15 +674,21 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
return 0;
- pkt = virtio_transport_alloc_pkt(&info, 0,
- le64_to_cpu(pkt->hdr.dst_cid),
- le32_to_cpu(pkt->hdr.dst_port),
- le64_to_cpu(pkt->hdr.src_cid),
- le32_to_cpu(pkt->hdr.src_port));
- if (!pkt)
+ reply = virtio_transport_alloc_pkt(&info, 0,
+ le64_to_cpu(pkt->hdr.dst_cid),
+ le32_to_cpu(pkt->hdr.dst_port),
+ le64_to_cpu(pkt->hdr.src_cid),
+ le32_to_cpu(pkt->hdr.src_port));
+ if (!reply)
return -ENOMEM;
- return virtio_transport_get_ops()->send_pkt(pkt);
+ t = virtio_transport_get_ops();
+ if (!t) {
+ virtio_transport_free_pkt(reply);
+ return -ENOTCONN;
+ }
+
+ return t->send_pkt(reply);
}
static void virtio_transport_wait_close(struct sock *sk, long timeout)
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 80f73810b21b..0436789e7cd8 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -7394,8 +7394,10 @@ static void ca0132_free(struct hda_codec *codec)
ca0132_exit_chip(codec);
snd_hda_power_down(codec);
- if (IS_ENABLED(CONFIG_PCI) && spec->mem_base)
+#ifdef CONFIG_PCI
+ if (spec->mem_base)
pci_iounmap(codec->bus->pci, spec->mem_base);
+#endif
kfree(spec->spec_init_verbs);
kfree(codec->spec);
}