Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull DAX updates from Dan Williams:
"The completion of Jan's DAX work for 4.10.
As I mentioned in the libnvdimm-for-4.10 pull request, these are some
final fixes for the DAX dirty-cacheline-tracking invalidation work
that was merged through the -mm, ext4, and xfs trees in -rc1. These
patches were prepared prior to the merge window, but we waited for
4.10-rc1 to have a stable merge base after all the prerequisites were
merged.
Quoting Jan on the overall changes in these patches:
"So I'd like all these 6 patches to go for rc2. The first three
patches fix invalidation of exceptional DAX entries (a bug which
is there for a long time) - without these patches data loss can
occur on power failure even though user called fsync(2). The other
three patches change locking of DAX faults so that ->iomap_begin()
is called in a more relaxed locking context and we are safe to
start a transaction there for ext4"
These have received a build success notification from the kbuild
robot, and pass the latest libnvdimm unit tests. There have not been
any -next releases since -rc1, so they have not appeared there"
* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
ext4: Simplify DAX fault path
dax: Call ->iomap_begin without entry lock during dax fault
dax: Finish fault completely when loading holes
dax: Avoid page invalidation races and unnecessary radix tree traversals
mm: Invalidate DAX radix tree entries only if appropriate
ext2: Return BH_New buffers for zeroed blocks
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index c75e5d6..a6eb7dc 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -12,7 +12,7 @@
kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
- 80211.xml sh.xml regulator.xml w1.xml \
+ sh.xml regulator.xml w1.xml \
writing_musb_glue_layer.xml iio.xml
ifeq ($(DOCBOOKS),)
diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt
index a445da0..3f76c0c 100644
--- a/Documentation/unaligned-memory-access.txt
+++ b/Documentation/unaligned-memory-access.txt
@@ -151,7 +151,7 @@
#else
const u16 *a = (const u16 *)addr1;
const u16 *b = (const u16 *)addr2;
- return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0;
+ return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0;
#endif
}
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
new file mode 100644
index 0000000..df411f3
--- /dev/null
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -0,0 +1,65 @@
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ .macro __uaccess_ttbr0_disable, tmp1
+ mrs \tmp1, ttbr1_el1 // swapper_pg_dir
+ add \tmp1, \tmp1, #SWAPPER_DIR_SIZE // reserved_ttbr0 at the end of swapper_pg_dir
+ msr ttbr0_el1, \tmp1 // set reserved TTBR0_EL1
+ isb
+ .endm
+
+ .macro __uaccess_ttbr0_enable, tmp1
+ get_thread_info \tmp1
+ ldr \tmp1, [\tmp1, #TSK_TI_TTBR0] // load saved TTBR0_EL1
+ msr ttbr0_el1, \tmp1 // set the non-PAN TTBR0_EL1
+ isb
+ .endm
+
+ .macro uaccess_ttbr0_disable, tmp1
+alternative_if_not ARM64_HAS_PAN
+ __uaccess_ttbr0_disable \tmp1
+alternative_else_nop_endif
+ .endm
+
+ .macro uaccess_ttbr0_enable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+ save_and_disable_irq \tmp2 // avoid preemption
+ __uaccess_ttbr0_enable \tmp1
+ restore_irq \tmp2
+alternative_else_nop_endif
+ .endm
+#else
+ .macro uaccess_ttbr0_disable, tmp1
+ .endm
+
+ .macro uaccess_ttbr0_enable, tmp1, tmp2
+ .endm
+#endif
+
+/*
+ * These macros are no-ops when UAO is present.
+ */
+ .macro uaccess_disable_not_uao, tmp1
+ uaccess_ttbr0_disable \tmp1
+alternative_if ARM64_ALT_PAN_NOT_UAO
+ SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+ .endm
+
+ .macro uaccess_enable_not_uao, tmp1, tmp2
+ uaccess_ttbr0_enable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+ SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+ .endm
+
+#endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index d26750c..46da3ea 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -22,8 +22,6 @@
#include <asm/kernel-pgtable.h>
#include <asm/sysreg.h>
-#ifndef __ASSEMBLY__
-
/*
* User space memory access functions
*/
@@ -424,66 +422,4 @@
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
-#else /* __ASSEMBLY__ */
-
-#include <asm/assembler.h>
-
-/*
- * User access enabling/disabling macros.
- */
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
- .macro __uaccess_ttbr0_disable, tmp1
- mrs \tmp1, ttbr1_el1 // swapper_pg_dir
- add \tmp1, \tmp1, #SWAPPER_DIR_SIZE // reserved_ttbr0 at the end of swapper_pg_dir
- msr ttbr0_el1, \tmp1 // set reserved TTBR0_EL1
- isb
- .endm
-
- .macro __uaccess_ttbr0_enable, tmp1
- get_thread_info \tmp1
- ldr \tmp1, [\tmp1, #TSK_TI_TTBR0] // load saved TTBR0_EL1
- msr ttbr0_el1, \tmp1 // set the non-PAN TTBR0_EL1
- isb
- .endm
-
- .macro uaccess_ttbr0_disable, tmp1
-alternative_if_not ARM64_HAS_PAN
- __uaccess_ttbr0_disable \tmp1
-alternative_else_nop_endif
- .endm
-
- .macro uaccess_ttbr0_enable, tmp1, tmp2
-alternative_if_not ARM64_HAS_PAN
- save_and_disable_irq \tmp2 // avoid preemption
- __uaccess_ttbr0_enable \tmp1
- restore_irq \tmp2
-alternative_else_nop_endif
- .endm
-#else
- .macro uaccess_ttbr0_disable, tmp1
- .endm
-
- .macro uaccess_ttbr0_enable, tmp1, tmp2
- .endm
-#endif
-
-/*
- * These macros are no-ops when UAO is present.
- */
- .macro uaccess_disable_not_uao, tmp1
- uaccess_ttbr0_disable \tmp1
-alternative_if ARM64_ALT_PAN_NOT_UAO
- SET_PSTATE_PAN(1)
-alternative_else_nop_endif
- .endm
-
- .macro uaccess_enable_not_uao, tmp1, tmp2
- uaccess_ttbr0_enable \tmp1, \tmp2
-alternative_if ARM64_ALT_PAN_NOT_UAO
- SET_PSTATE_PAN(0)
-alternative_else_nop_endif
- .endm
-
-#endif /* __ASSEMBLY__ */
-
#endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a7504f4..923841f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -31,7 +31,7 @@
#include <asm/memory.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
#include <asm/unistd.h>
/*
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index add4a13..e88fb99 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -17,7 +17,7 @@
*/
#include <linux/linkage.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
.text
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index fd6cd055..4b5d826 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -17,7 +17,7 @@
#include <linux/linkage.h>
#include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
/*
* Copy from user space to a kernel buffer (alignment handled by the hardware)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index d828540..47184c3 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -19,7 +19,7 @@
#include <linux/linkage.h>
#include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
/*
* Copy from user space to user space (alignment handled by the hardware)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 3e6ae26..351f076 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -17,7 +17,7 @@
#include <linux/linkage.h>
#include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
/*
* Copy to user space from a kernel buffer (alignment handled by the hardware)
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 17f422a..83c27b6e 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -23,7 +23,7 @@
#include <asm/assembler.h>
#include <asm/cpufeature.h>
#include <asm/alternative.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
/*
* flush_icache_range(start,end)
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 47cf3f9..947830a 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -49,7 +49,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
#include <xen/interface/xen.h>
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 68557f52..8540227 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -139,6 +139,19 @@
asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
}
+static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+ bool negative;
+ asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+ CC_SET(s)
+ : CC_OUT(s) (negative), ADDR
+ : "ir" ((char) ~(1 << nr)) : "memory");
+ return negative;
+}
+
+// Let everybody know we have it
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+
/*
* __clear_bit_unlock - Clears a bit in memory
* @nr: Bit to clear
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ffacfdc..a5fd137 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1182,6 +1182,9 @@
const char *name = get_name(bank, NULL);
int err = 0;
+ if (!dev)
+ return -ENODEV;
+
if (is_shared_bank(bank)) {
nb = node_to_amd_nb(amd_get_nb_id(cpu));
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f616ad7..44e888b 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1461,16 +1461,25 @@
for (i = 0; i < ctcount; i++) {
unsigned int dlen = COMP_BUF_SIZE;
int ilen = ctemplate[i].inlen;
+ void *input_vec;
+ input_vec = kmalloc(ilen, GFP_KERNEL);
+ if (!input_vec) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ memcpy(input_vec, ctemplate[i].input, ilen);
memset(output, 0, dlen);
init_completion(&result.completion);
- sg_init_one(&src, ctemplate[i].input, ilen);
+ sg_init_one(&src, input_vec, ilen);
sg_init_one(&dst, output, dlen);
req = acomp_request_alloc(tfm);
if (!req) {
pr_err("alg: acomp: request alloc failed for %s\n",
algo);
+ kfree(input_vec);
ret = -ENOMEM;
goto out;
}
@@ -1483,6 +1492,7 @@
if (ret) {
pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
i + 1, algo, -ret);
+ kfree(input_vec);
acomp_request_free(req);
goto out;
}
@@ -1491,6 +1501,7 @@
pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
i + 1, algo, req->dlen);
ret = -EINVAL;
+ kfree(input_vec);
acomp_request_free(req);
goto out;
}
@@ -1500,26 +1511,37 @@
i + 1, algo);
hexdump(output, req->dlen);
ret = -EINVAL;
+ kfree(input_vec);
acomp_request_free(req);
goto out;
}
+ kfree(input_vec);
acomp_request_free(req);
}
for (i = 0; i < dtcount; i++) {
unsigned int dlen = COMP_BUF_SIZE;
int ilen = dtemplate[i].inlen;
+ void *input_vec;
+ input_vec = kmalloc(ilen, GFP_KERNEL);
+ if (!input_vec) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ memcpy(input_vec, dtemplate[i].input, ilen);
memset(output, 0, dlen);
init_completion(&result.completion);
- sg_init_one(&src, dtemplate[i].input, ilen);
+ sg_init_one(&src, input_vec, ilen);
sg_init_one(&dst, output, dlen);
req = acomp_request_alloc(tfm);
if (!req) {
pr_err("alg: acomp: request alloc failed for %s\n",
algo);
+ kfree(input_vec);
ret = -ENOMEM;
goto out;
}
@@ -1532,6 +1554,7 @@
if (ret) {
pr_err("alg: acomp: decompression failed on test %d for %s: ret=%d\n",
i + 1, algo, -ret);
+ kfree(input_vec);
acomp_request_free(req);
goto out;
}
@@ -1540,6 +1563,7 @@
pr_err("alg: acomp: Decompression test %d failed for %s: output len = %d\n",
i + 1, algo, req->dlen);
ret = -EINVAL;
+ kfree(input_vec);
acomp_request_free(req);
goto out;
}
@@ -1549,10 +1573,12 @@
i + 1, algo);
hexdump(output, req->dlen);
ret = -EINVAL;
+ kfree(input_vec);
acomp_request_free(req);
goto out;
}
+ kfree(input_vec);
acomp_request_free(req);
}
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index a768da7..b7872f6 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -273,7 +273,8 @@
#define CESA_TDMA_SRC_IN_SRAM BIT(30)
#define CESA_TDMA_END_OF_REQ BIT(29)
#define CESA_TDMA_BREAK_CHAIN BIT(28)
-#define CESA_TDMA_TYPE_MSK GENMASK(27, 0)
+#define CESA_TDMA_SET_STATE BIT(27)
+#define CESA_TDMA_TYPE_MSK GENMASK(26, 0)
#define CESA_TDMA_DUMMY 0
#define CESA_TDMA_DATA 1
#define CESA_TDMA_OP 2
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 317cf02..77c0fb9 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -280,13 +280,32 @@
sreq->offset = 0;
}
+static void mv_cesa_ahash_dma_step(struct ahash_request *req)
+{
+ struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+ struct mv_cesa_req *base = &creq->base;
+
+ /* We must explicitly set the digest state. */
+ if (base->chain.first->flags & CESA_TDMA_SET_STATE) {
+ struct mv_cesa_engine *engine = base->engine;
+ int i;
+
+ /* Set the hash state in the IVDIG regs. */
+ for (i = 0; i < ARRAY_SIZE(creq->state); i++)
+ writel_relaxed(creq->state[i], engine->regs +
+ CESA_IVDIG(i));
+ }
+
+ mv_cesa_dma_step(base);
+}
+
static void mv_cesa_ahash_step(struct crypto_async_request *req)
{
struct ahash_request *ahashreq = ahash_request_cast(req);
struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
- mv_cesa_dma_step(&creq->base);
+ mv_cesa_ahash_dma_step(ahashreq);
else
mv_cesa_ahash_std_step(ahashreq);
}
@@ -584,12 +603,16 @@
struct mv_cesa_ahash_dma_iter iter;
struct mv_cesa_op_ctx *op = NULL;
unsigned int frag_len;
+ bool set_state = false;
int ret;
u32 type;
basereq->chain.first = NULL;
basereq->chain.last = NULL;
+ if (!mv_cesa_mac_op_is_first_frag(&creq->op_tmpl))
+ set_state = true;
+
if (creq->src_nents) {
ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
DMA_TO_DEVICE);
@@ -683,6 +706,15 @@
if (type != CESA_TDMA_RESULT)
basereq->chain.last->flags |= CESA_TDMA_BREAK_CHAIN;
+ if (set_state) {
+ /*
+ * Put the CESA_TDMA_SET_STATE flag on the first tdma desc to
+ * let the step logic know that the IVDIG registers should be
+ * explicitly set before launching a TDMA chain.
+ */
+ basereq->chain.first->flags |= CESA_TDMA_SET_STATE;
+ }
+
return 0;
err_free_tdma:
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
index 4416b88..c76375f 100644
--- a/drivers/crypto/marvell/tdma.c
+++ b/drivers/crypto/marvell/tdma.c
@@ -109,7 +109,14 @@
last->next = dreq->chain.first;
engine->chain.last = dreq->chain.last;
- if (!(last->flags & CESA_TDMA_BREAK_CHAIN))
+ /*
+ * Break the DMA chain if the CESA_TDMA_BREAK_CHAIN is set on
+ * the last element of the current chain, or if the request
+ * being queued needs the IV regs to be set before lauching
+ * the request.
+ */
+ if (!(last->flags & CESA_TDMA_BREAK_CHAIN) &&
+ !(dreq->chain.first->flags & CESA_TDMA_SET_STATE))
last->next_dma = dreq->chain.first->cur_dma;
}
}
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index cbeea91..8037426 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -900,10 +900,10 @@
DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR,
&lp->rx_dma_regs->dmasm);
- korina_free_ring(dev);
-
napi_disable(&lp->napi);
+ korina_free_ring(dev);
+
if (korina_init(dev) < 0) {
printk(KERN_ERR "%s: cannot restart device\n", dev->name);
return;
@@ -1064,12 +1064,12 @@
tmp = tmp | DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR;
writel(tmp, &lp->rx_dma_regs->dmasm);
- korina_free_ring(dev);
-
napi_disable(&lp->napi);
cancel_work_sync(&lp->restart_task);
+ korina_free_ring(dev);
+
free_irq(lp->rx_irq, dev);
free_irq(lp->tx_irq, dev);
free_irq(lp->ovr_irq, dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index bcd9553..edbe200 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1638,7 +1638,8 @@
/* Configure tx cq's and rings */
for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
- u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up : 1;
+ u8 num_tx_rings_p_up = t == TX ?
+ priv->num_tx_rings_p_up : priv->tx_ring_num[t];
for (i = 0; i < priv->tx_ring_num[t]; i++) {
/* Configure cq */
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f9b97f5..44389c9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -326,6 +326,7 @@
static const struct pci_device_id rtl8169_pci_tbl[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8129), 0, 0, RTL_CFG_0 },
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8136), 0, 0, RTL_CFG_2 },
+ { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8161), 0, 0, RTL_CFG_1 },
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8167), 0, 0, RTL_CFG_0 },
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8168), 0, 0, RTL_CFG_1 },
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8169), 0, 0, RTL_CFG_0 },
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index fda01f7..b0344c2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -116,7 +116,7 @@
unsigned int mii_address = priv->hw->mii.addr;
unsigned int mii_data = priv->hw->mii.data;
- u32 value = MII_WRITE | MII_BUSY;
+ u32 value = MII_BUSY;
value |= (phyaddr << priv->hw->mii.addr_shift)
& priv->hw->mii.addr_mask;
@@ -126,6 +126,8 @@
& priv->hw->mii.clk_csr_mask;
if (priv->plat->has_gmac4)
value |= MII_GMAC4_WRITE;
+ else
+ value |= MII_WRITE;
/* Wait until any existing MII operation is complete */
if (stmmac_mdio_busy_wait(priv->ioaddr, mii_address))
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 031093e..dbfbb33 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -99,6 +99,11 @@
int count;
};
+struct ipvl_skb_cb {
+ bool tx_pkt;
+};
+#define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0]))
+
static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
{
return rcu_dereference(d->rx_handler_data);
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index b4e9907..83ce74a 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -198,7 +198,7 @@
unsigned int mac_hash;
int ret;
u8 pkt_type;
- bool hlocal, dlocal;
+ bool tx_pkt;
__skb_queue_head_init(&list);
@@ -207,8 +207,11 @@
spin_unlock_bh(&port->backlog.lock);
while ((skb = __skb_dequeue(&list)) != NULL) {
+ struct net_device *dev = skb->dev;
+ bool consumed = false;
+
ethh = eth_hdr(skb);
- hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
+ tx_pkt = IPVL_SKB_CB(skb)->tx_pkt;
mac_hash = ipvlan_mac_hash(ethh->h_dest);
if (ether_addr_equal(ethh->h_dest, port->dev->broadcast))
@@ -216,41 +219,45 @@
else
pkt_type = PACKET_MULTICAST;
- dlocal = false;
rcu_read_lock();
list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
- if (hlocal && (ipvlan->dev == skb->dev)) {
- dlocal = true;
+ if (tx_pkt && (ipvlan->dev == skb->dev))
continue;
- }
if (!test_bit(mac_hash, ipvlan->mac_filters))
continue;
-
+ if (!(ipvlan->dev->flags & IFF_UP))
+ continue;
ret = NET_RX_DROP;
len = skb->len + ETH_HLEN;
nskb = skb_clone(skb, GFP_ATOMIC);
- if (!nskb)
- goto acct;
-
- nskb->pkt_type = pkt_type;
- nskb->dev = ipvlan->dev;
- if (hlocal)
- ret = dev_forward_skb(ipvlan->dev, nskb);
- else
- ret = netif_rx(nskb);
-acct:
+ local_bh_disable();
+ if (nskb) {
+ consumed = true;
+ nskb->pkt_type = pkt_type;
+ nskb->dev = ipvlan->dev;
+ if (tx_pkt)
+ ret = dev_forward_skb(ipvlan->dev, nskb);
+ else
+ ret = netif_rx(nskb);
+ }
ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+ local_bh_enable();
}
rcu_read_unlock();
- if (dlocal) {
+ if (tx_pkt) {
/* If the packet originated here, send it out. */
skb->dev = port->dev;
skb->pkt_type = pkt_type;
dev_queue_xmit(skb);
} else {
- kfree_skb(skb);
+ if (consumed)
+ consume_skb(skb);
+ else
+ kfree_skb(skb);
}
+ if (dev)
+ dev_put(dev);
}
}
@@ -470,15 +477,24 @@
}
static void ipvlan_multicast_enqueue(struct ipvl_port *port,
- struct sk_buff *skb)
+ struct sk_buff *skb, bool tx_pkt)
{
if (skb->protocol == htons(ETH_P_PAUSE)) {
kfree_skb(skb);
return;
}
+ /* Record that the deferred packet is from TX or RX path. By
+ * looking at mac-addresses on packet will lead to erronus decisions.
+ * (This would be true for a loopback-mode on master device or a
+ * hair-pin mode of the switch.)
+ */
+ IPVL_SKB_CB(skb)->tx_pkt = tx_pkt;
+
spin_lock(&port->backlog.lock);
if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+ if (skb->dev)
+ dev_hold(skb->dev);
__skb_queue_tail(&port->backlog, skb);
spin_unlock(&port->backlog.lock);
schedule_work(&port->wq);
@@ -537,7 +553,7 @@
} else if (is_multicast_ether_addr(eth->h_dest)) {
ipvlan_skb_crossing_ns(skb, NULL);
- ipvlan_multicast_enqueue(ipvlan->port, skb);
+ ipvlan_multicast_enqueue(ipvlan->port, skb, true);
return NET_XMIT_SUCCESS;
}
@@ -634,7 +650,7 @@
*/
if (nskb) {
ipvlan_skb_crossing_ns(nskb, NULL);
- ipvlan_multicast_enqueue(port, nskb);
+ ipvlan_multicast_enqueue(port, nskb, false);
}
}
} else {
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 693ec5b..8b0f993 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -135,6 +135,7 @@
static void ipvlan_port_destroy(struct net_device *dev)
{
struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+ struct sk_buff *skb;
dev->priv_flags &= ~IFF_IPVLAN_MASTER;
if (port->mode == IPVLAN_MODE_L3S) {
@@ -144,7 +145,11 @@
}
netdev_rx_handler_unregister(dev);
cancel_work_sync(&port->wq);
- __skb_queue_purge(&port->backlog);
+ while ((skb = __skb_dequeue(&port->backlog)) != NULL) {
+ if (skb->dev)
+ dev_put(skb->dev);
+ kfree_skb(skb);
+ }
kfree(port);
}
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7023142..a0934e6 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -610,7 +610,6 @@
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len);
void bpf_warn_invalid_xdp_action(u32 act);
-void bpf_warn_invalid_xdp_buffer(void);
#ifdef CONFIG_BPF_JIT
extern int bpf_jit_enable;
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c56b398..6b5818d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -73,13 +73,13 @@
*/
enum pageflags {
PG_locked, /* Page is locked. Don't touch. */
- PG_waiters, /* Page has waiters, check its waitqueue */
PG_error,
PG_referenced,
PG_uptodate,
PG_dirty,
PG_lru,
PG_active,
+ PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
PG_slab,
PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/
PG_arch_1,
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index f0cf5a1..0378e88 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -110,6 +110,7 @@
int sysctl_tcp_orphan_retries;
int sysctl_tcp_fin_timeout;
unsigned int sysctl_tcp_notsent_lowat;
+ int sysctl_tcp_tw_reuse;
int sysctl_igmp_max_memberships;
int sysctl_igmp_max_msf;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 207147b..6061963 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -252,7 +252,6 @@
extern int sysctl_tcp_rmem[3];
extern int sysctl_tcp_app_win;
extern int sysctl_tcp_adv_win_scale;
-extern int sysctl_tcp_tw_reuse;
extern int sysctl_tcp_frto;
extern int sysctl_tcp_low_latency;
extern int sysctl_tcp_nometrics_save;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 042fd7e..f75c4d0 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1471,6 +1471,7 @@
bool multi_instance)
{
int cpu, ret = 0;
+ bool dynstate;
if (cpuhp_cb_check(state) || !name)
return -EINVAL;
@@ -1480,6 +1481,12 @@
ret = cpuhp_store_callbacks(state, name, startup, teardown,
multi_instance);
+ dynstate = state == CPUHP_AP_ONLINE_DYN;
+ if (ret > 0 && dynstate) {
+ state = ret;
+ ret = 0;
+ }
+
if (ret || !invoke || !startup)
goto out;
@@ -1508,7 +1515,7 @@
* If the requested state is CPUHP_AP_ONLINE_DYN, return the
* dynamically allocated state in case of success.
*/
- if (!ret && state == CPUHP_AP_ONLINE_DYN)
+ if (!ret && dynstate)
return state;
return ret;
}
diff --git a/mm/filemap.c b/mm/filemap.c
index 82f26cd..d0e4d10 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -912,6 +912,29 @@
}
EXPORT_SYMBOL_GPL(add_page_wait_queue);
+#ifndef clear_bit_unlock_is_negative_byte
+
+/*
+ * PG_waiters is the high bit in the same byte as PG_lock.
+ *
+ * On x86 (and on many other architectures), we can clear PG_lock and
+ * test the sign bit at the same time. But if the architecture does
+ * not support that special operation, we just do this all by hand
+ * instead.
+ *
+ * The read of PG_waiters has to be after (or concurrently with) PG_locked
+ * being cleared, but a memory barrier should be unneccssary since it is
+ * in the same byte as PG_locked.
+ */
+static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
+{
+ clear_bit_unlock(nr, mem);
+ /* smp_mb__after_atomic(); */
+ return test_bit(PG_waiters, mem);
+}
+
+#endif
+
/**
* unlock_page - unlock a locked page
* @page: the page
@@ -921,16 +944,19 @@
* mechanism between PageLocked pages and PageWriteback pages is shared.
* But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
*
- * The mb is necessary to enforce ordering between the clear_bit and the read
- * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
+ * Note that this depends on PG_waiters being the sign bit in the byte
+ * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
+ * clear the PG_locked bit and test PG_waiters at the same time fairly
+ * portably (architectures that do LL/SC can test any bit, while x86 can
+ * test the sign bit).
*/
void unlock_page(struct page *page)
{
+ BUILD_BUG_ON(PG_waiters != 7);
page = compound_head(page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
- clear_bit_unlock(PG_locked, &page->flags);
- smp_mb__after_atomic();
- wake_up_page(page, PG_locked);
+ if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
+ wake_up_page_bit(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);
diff --git a/net/core/filter.c b/net/core/filter.c
index e6c412b..1969b3f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2972,12 +2972,6 @@
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
-void bpf_warn_invalid_xdp_buffer(void)
-{
- WARN_ONCE(1, "Illegal XDP buffer encountered, expect throughput degradation\n");
-}
-EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_buffer);
-
static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
struct bpf_insn *insn_buf,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 80bc36b..22cbd61 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -433,13 +433,6 @@
.extra2 = &tcp_adv_win_scale_max,
},
{
- .procname = "tcp_tw_reuse",
- .data = &sysctl_tcp_tw_reuse,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_frto",
.data = &sysctl_tcp_frto,
.maxlen = sizeof(int),
@@ -960,6 +953,13 @@
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "tcp_tw_reuse",
+ .data = &init_net.ipv4.sysctl_tcp_tw_reuse,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
#ifdef CONFIG_IP_ROUTE_MULTIPATH
{
.procname = "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30d81f5..fe9da4f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,7 +84,6 @@
#include <crypto/hash.h>
#include <linux/scatterlist.h>
-int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
#ifdef CONFIG_TCP_MD5SIG
@@ -120,7 +119,7 @@
and use initial timestamp retrieved from peer table.
*/
if (tcptw->tw_ts_recent_stamp &&
- (!twp || (sysctl_tcp_tw_reuse &&
+ (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
if (tp->write_seq == 0)
@@ -2456,6 +2455,7 @@
net->ipv4.sysctl_tcp_orphan_retries = 0;
net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+ net->ipv4.sysctl_tcp_tw_reuse = 0;
return 0;
fail:
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 2d4c4d3..9c62b63 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -606,7 +606,6 @@
rcu_assign_pointer(flow->sf_acts, acts);
packet->priority = flow->key.phy.priority;
packet->mark = flow->key.phy.skb_mark;
- packet->protocol = flow->key.eth.type;
rcu_read_lock();
dp = get_dp_rcu(net, ovs_header->dp_ifindex);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 08aa926..2c0a00f 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -312,7 +312,8 @@
* Returns 0 if it encounters a non-vlan or incomplete packet.
* Returns 1 after successfully parsing vlan tag.
*/
-static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
+static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
+ bool untag_vlan)
{
struct vlan_head *vh = (struct vlan_head *)skb->data;
@@ -330,7 +331,20 @@
key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT);
key_vh->tpid = vh->tpid;
- __skb_pull(skb, sizeof(struct vlan_head));
+ if (unlikely(untag_vlan)) {
+ int offset = skb->data - skb_mac_header(skb);
+ u16 tci;
+ int err;
+
+ __skb_push(skb, offset);
+ err = __skb_vlan_pop(skb, &tci);
+ __skb_pull(skb, offset);
+ if (err)
+ return err;
+ __vlan_hwaccel_put_tag(skb, key_vh->tpid, tci);
+ } else {
+ __skb_pull(skb, sizeof(struct vlan_head));
+ }
return 1;
}
@@ -351,13 +365,13 @@
key->eth.vlan.tpid = skb->vlan_proto;
} else {
/* Parse outer vlan tag in the non-accelerated case. */
- res = parse_vlan_tag(skb, &key->eth.vlan);
+ res = parse_vlan_tag(skb, &key->eth.vlan, true);
if (res <= 0)
return res;
}
/* Parse inner vlan tag. */
- res = parse_vlan_tag(skb, &key->eth.cvlan);
+ res = parse_vlan_tag(skb, &key->eth.cvlan, false);
if (res <= 0)
return res;
@@ -800,29 +814,15 @@
if (err)
return err;
- if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
- /* key_extract assumes that skb->protocol is set-up for
- * layer 3 packets which is the case for other callers,
- * in particular packets recieved from the network stack.
- * Here the correct value can be set from the metadata
- * extracted above.
- */
- skb->protocol = key->eth.type;
- } else {
- struct ethhdr *eth;
+ /* key_extract assumes that skb->protocol is set-up for
+ * layer 3 packets which is the case for other callers,
+ * in particular packets received from the network stack.
+ * Here the correct value can be set from the metadata
+ * extracted above.
+ * For L2 packet key eth type would be zero. skb protocol
+ * would be set to correct value later during key-extact.
+ */
- skb_reset_mac_header(skb);
- eth = eth_hdr(skb);
-
- /* Normally, setting the skb 'protocol' field would be
- * handled by a call to eth_type_trans(), but it assumes
- * there's a sending device, which we may not have.
- */
- if (eth_proto_is_802_3(eth->h_proto))
- skb->protocol = eth->h_proto;
- else
- skb->protocol = htons(ETH_P_802_2);
- }
-
+ skb->protocol = key->eth.type;
return key_extract(skb, key);
}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3fbba79..1ecdf80 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -148,13 +148,15 @@
unsigned long cl;
unsigned long fh;
int err;
- int tp_created = 0;
+ int tp_created;
if ((n->nlmsg_type != RTM_GETTFILTER) &&
!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
replay:
+ tp_created = 0;
+
err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
if (err < 0)
return err;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 333c5da..800caaa 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -441,15 +441,19 @@
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
if (TIPC_SKB_CB(skb)->bytes_read) {
kfree_skb(skb);
- } else {
- if (!tipc_sk_type_connectionless(sk) &&
- sk->sk_state != TIPC_DISCONNECTING) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
- tipc_sk_respond(sk, skb, error);
+ continue;
}
+ if (!tipc_sk_type_connectionless(sk) &&
+ sk->sk_state != TIPC_DISCONNECTING) {
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ }
+ tipc_sk_respond(sk, skb, error);
}
+
+ if (tipc_sk_type_connectionless(sk))
+ return;
+
if (sk->sk_state != TIPC_DISCONNECTING) {
skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
@@ -457,10 +461,8 @@
tsk->portid, error);
if (skb)
tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
- if (!tipc_sk_type_connectionless(sk)) {
- tipc_node_remove_conn(net, dnode, tsk->portid);
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- }
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
}
}
