Merge branch 'fixes' of git://git.armlinux.org.uk/~rmk/linux-arm
Pull ARM fixes from Russell King:
"Most of this update are fixes primarily discovered from testing on the
older StrongARM 1110 and PXA systems, as a result of recent interest
from several people in these platforms:
- Locomo interrupt handling incorrectly stores the handler data in
the chip's private data slot: when Locomo is combined with an
interrupt controller who's chip uses the chip private data, this
leads to an oops.
- SA1111 was missing a call to clk_disable() to clean up after a
failed probe.
- SA1111 and PCMCIA suspend/resume was broken:
The PCMCIA "ds" layer was using the legacy bus suspend/resume
methods, which the core PM code is no longer calling as a result of
device_pm_check_callbacks() introduced in commit aa8e54b559479
("PM / sleep: Go direct_complete if driver has no callbacks").
SA1111 was broken due to changes to PCMCIA which makes PCMCIA
suspend itself later than the SA1111 code expects, and resume
before the SA1111 code has initialised access to the pcmcia
sub-device.
- the default SA1111 interrupt mask polarity got messed up when it
was converted to use a dynamic interrupt base number for its
interrupts.
- fix platform_get_irq() error code propagation, which was causing
problems on platforms where the interrupt may not be available at
probe time in DT setups.
- fix the lack of clock to PCMCIA code on PXA platforms, which was
omitted in conversions of PXA to CCF.
- fix an oops in the PXA PCMCIA code caused by a previous commit not
realising that Lubbock is different from the rest of the PXA PCMCIA
drivers.
- ensure that SA1111 low-level PCMCIA drivers propagate their error
codes to the main probe function, rather than the driver silently
accepting a failure.
- fix the sa11xx debugfs reporting of timing information, which
always indicated zero due to the clock being a factor of 1000 out.
- fix the polarity of the status change signal reported from the
sockets.
Lastly, one ARM specific commit from Stefan Agner fixing the LPAE
cache attributes"
* 'fixes' of git://git.armlinux.org.uk/~rmk/linux-arm:
ARM: pxa/lubbock: add pcmcia clock
ARM: locomo: fix locomo irq handling
ARM: 8612/1: LPAE: initialize cache policy correctly
ARM: sa1111: fix missing clk_disable()
ARM: sa1111: fix pcmcia suspend/resume
ARM: sa1111: fix pcmcia interrupt mask polarity
ARM: sa1111: fix error code propagation in sa1111_probe()
pcmcia: lubbock: fix sockets configuration
pcmcia: sa1111: fix propagation of lowlevel board init return code
pcmcia: soc_common: fix SS_STSCHG polarity
pcmcia: sa11xx_base: add units to the timing information
pcmcia: sa11xx_base: fix reporting of timing information
pcmcia: ds: fix suspend/resume
diff --git a/MAINTAINERS b/MAINTAINERS
index 6781a3f..a5e1270 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2485,7 +2485,7 @@
BONDING DRIVER
M: Jay Vosburgh <j.vosburgh@gmail.com>
M: Veaceslav Falico <vfalico@gmail.com>
-M: Andy Gospodarek <gospo@cumulusnetworks.com>
+M: Andy Gospodarek <andy@greyhouse.net>
L: netdev@vger.kernel.org
W: http://sourceforge.net/projects/bonding/
S: Supported
@@ -3269,7 +3269,7 @@
F: drivers/net/wan/cosa*
CPMAC ETHERNET DRIVER
-M: Florian Fainelli <florian@openwrt.org>
+M: Florian Fainelli <f.fainelli@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/ti/cpmac.c
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index c419b43..466e42e 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -371,14 +371,6 @@
return __cu_len;
}
-extern inline long
-__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate)
-{
- if (__access_ok((unsigned long)validate, len, get_fs()))
- len = __copy_tofrom_user_nocheck(to, from, len);
- return len;
-}
-
#define __copy_to_user(to, from, n) \
({ \
__chk_user_ptr(to); \
@@ -393,17 +385,22 @@
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
-
extern inline long
copy_to_user(void __user *to, const void *from, long n)
{
- return __copy_tofrom_user((__force void *)to, from, n, to);
+ if (likely(__access_ok((unsigned long)to, n, get_fs())))
+ n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+ return n;
}
extern inline long
copy_from_user(void *to, const void __user *from, long n)
{
- return __copy_tofrom_user(to, (__force void *)from, n, from);
+ if (likely(__access_ok((unsigned long)from, n, get_fs())))
+ n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
+ else
+ memset(to, 0, n);
+ return n;
}
extern void __do_clear_user(void);
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index a78d567..41faf17 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -83,7 +83,10 @@
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
@@ -101,7 +104,11 @@
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
+ " mov %R1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 75f130e..c94b90d 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -158,8 +158,6 @@
{
int i;
- kvm_free_stage2_pgd(kvm);
-
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (kvm->vcpus[i]) {
kvm_arch_vcpu_free(kvm->vcpus[i]);
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 29d0b23..e9a5c0e 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1714,7 +1714,8 @@
kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
- hyp_idmap_start < kern_hyp_va(~0UL)) {
+ hyp_idmap_start < kern_hyp_va(~0UL) &&
+ hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
/*
* The idmap page is intersecting with the VA space,
* it is not safe to continue further.
@@ -1893,6 +1894,7 @@
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
+ kvm_free_stage2_pgd(kvm);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 3d2cef6..f193414 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -170,9 +170,6 @@
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
- /* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, cpu) = cpu;
-
info.mfn = virt_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
@@ -330,6 +327,7 @@
{
struct xen_add_to_physmap xatp;
struct shared_info *shared_info_page = NULL;
+ int cpu;
if (!xen_domain())
return 0;
@@ -380,7 +378,8 @@
return -ENOMEM;
/* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, 0) = 0;
+ for_each_possible_cpu(cpu)
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
index 68cf638..b1ec1fa 100644
--- a/arch/avr32/include/asm/uaccess.h
+++ b/arch/avr32/include/asm/uaccess.h
@@ -74,7 +74,7 @@
extern __kernel_size_t copy_to_user(void __user *to, const void *from,
__kernel_size_t n);
-extern __kernel_size_t copy_from_user(void *to, const void __user *from,
+extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
__kernel_size_t n);
static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
@@ -88,6 +88,15 @@
{
return __copy_user(to, (const void __force *)from, n);
}
+static inline __kernel_size_t copy_from_user(void *to,
+ const void __user *from,
+ __kernel_size_t n)
+{
+ size_t res = ___copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
+}
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
diff --git a/arch/avr32/kernel/avr32_ksyms.c b/arch/avr32/kernel/avr32_ksyms.c
index d93ead0..7c6cf14 100644
--- a/arch/avr32/kernel/avr32_ksyms.c
+++ b/arch/avr32/kernel/avr32_ksyms.c
@@ -36,7 +36,7 @@
/*
* Userspace access stuff.
*/
-EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(___copy_from_user);
EXPORT_SYMBOL(copy_to_user);
EXPORT_SYMBOL(__copy_user);
EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/avr32/lib/copy_user.S b/arch/avr32/lib/copy_user.S
index ea59c04..96a6de9 100644
--- a/arch/avr32/lib/copy_user.S
+++ b/arch/avr32/lib/copy_user.S
@@ -25,11 +25,11 @@
.align 1
.global copy_from_user
.type copy_from_user, @function
-copy_from_user:
+___copy_from_user:
branch_if_kernel r8, __copy_user
ret_if_privileged r8, r11, r10, r10
rjmp __copy_user
- .size copy_from_user, . - copy_from_user
+ .size ___copy_from_user, . - ___copy_from_user
.global copy_to_user
.type copy_to_user, @function
diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h
index 12f5d68..0a2a700 100644
--- a/arch/blackfin/include/asm/uaccess.h
+++ b/arch/blackfin/include/asm/uaccess.h
@@ -171,11 +171,12 @@
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n))) {
memcpy(to, (const void __force *)from, n);
- else
- return n;
- return 0;
+ return 0;
+ }
+ memset(to, 0, n);
+ return n;
}
static inline unsigned long __must_check
diff --git a/arch/cris/include/asm/uaccess.h b/arch/cris/include/asm/uaccess.h
index e3530d0..56c7d57 100644
--- a/arch/cris/include/asm/uaccess.h
+++ b/arch/cris/include/asm/uaccess.h
@@ -194,30 +194,6 @@
extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
extern unsigned long __do_clear_user(void __user *to, unsigned long n);
-static inline unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_user(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- return __copy_user_zeroing(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_clear_user(void __user *to, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __do_clear_user(to, n);
- return n;
-}
-
static inline long
__strncpy_from_user(char *dst, const char __user *src, long count)
{
@@ -282,7 +258,7 @@
else if (n == 24)
__asm_copy_from_user_24(to, from, ret);
else
- ret = __generic_copy_from_user(to, from, n);
+ ret = __copy_user_zeroing(to, from, n);
return ret;
}
@@ -333,7 +309,7 @@
else if (n == 24)
__asm_copy_to_user_24(to, from, ret);
else
- ret = __generic_copy_to_user(to, from, n);
+ ret = __copy_user(to, from, n);
return ret;
}
@@ -366,26 +342,43 @@
else if (n == 24)
__asm_clear_24(to, ret);
else
- ret = __generic_clear_user(to, n);
+ ret = __do_clear_user(to, n);
return ret;
}
-#define clear_user(to, n) \
- (__builtin_constant_p(n) ? \
- __constant_clear_user(to, n) : \
- __generic_clear_user(to, n))
+static inline size_t clear_user(void __user *to, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_clear_user(to, n);
+ else
+ return __do_clear_user(to, n);
+}
-#define copy_from_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_from_user(to, from, n) : \
- __generic_copy_from_user(to, from, n))
+static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_READ, from, n))) {
+ memset(to, 0, n);
+ return n;
+ }
+ if (__builtin_constant_p(n))
+ return __constant_copy_from_user(to, from, n);
+ else
+ return __copy_user_zeroing(to, from, n);
+}
-#define copy_to_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_to_user(to, from, n) : \
- __generic_copy_to_user(to, from, n))
+static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_copy_to_user(to, from, n);
+ else
+ return __copy_user(to, from, n);
+}
/* We let the __ versions of copy_from/to_user inline, because they're often
* used in fast paths and have only a small space overhead.
diff --git a/arch/frv/include/asm/uaccess.h b/arch/frv/include/asm/uaccess.h
index 3ac9a59..87d9e34 100644
--- a/arch/frv/include/asm/uaccess.h
+++ b/arch/frv/include/asm/uaccess.h
@@ -263,19 +263,25 @@
extern long __memset_user(void *dst, unsigned long count);
extern long __memcpy_user(void *dst, const void *src, unsigned long count);
-#define clear_user(dst,count) __memset_user(____force(dst), (count))
+#define __clear_user(dst,count) __memset_user(____force(dst), (count))
#define __copy_from_user_inatomic(to, from, n) __memcpy_user((to), ____force(from), (n))
#define __copy_to_user_inatomic(to, from, n) __memcpy_user(____force(to), (from), (n))
#else
-#define clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
+#define __clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
#define __copy_from_user_inatomic(to, from, n) (memcpy((to), ____force(from), (n)), 0)
#define __copy_to_user_inatomic(to, from, n) (memcpy(____force(to), (from), (n)), 0)
#endif
-#define __clear_user clear_user
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
+{
+ if (likely(__access_ok(to, n)))
+ n = __clear_user(to, n);
+ return n;
+}
static inline unsigned long __must_check
__copy_to_user(void __user *to, const void *from, unsigned long n)
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index f000a382..f61cfb2 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -103,7 +103,8 @@
{
long res = __strnlen_user(src, n);
- /* return from strnlen can't be zero -- that would be rubbish. */
+ if (unlikely(!res))
+ return -EFAULT;
if (res > n) {
copy_from_user(dst, src, n);
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 0472927..bfe1319 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -269,19 +269,16 @@
__cu_len; \
})
-#define copy_from_user(to, from, n) \
-({ \
- void *__cu_to = (to); \
- const void __user *__cu_from = (from); \
- long __cu_len = (n); \
- \
- __chk_user_ptr(__cu_from); \
- if (__access_ok(__cu_from, __cu_len, get_fs())) { \
- check_object_size(__cu_to, __cu_len, false); \
- __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \
- } \
- __cu_len; \
-})
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ check_object_size(to, n, false);
+ if (likely(__access_ok(from, n, get_fs())))
+ n = __copy_user((__force void __user *) to, from, n);
+ else
+ memset(to, 0, n);
+ return n;
+}
#define __copy_in_user(to, from, size) __copy_user((to), (from), (size))
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index cac7014..6f89821 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -219,7 +219,7 @@
#define __get_user_nocheck(x, ptr, size) \
({ \
long __gu_err = 0; \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
might_fault(); \
__get_user_size(__gu_val, (ptr), (size), __gu_err); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h
index 8282cbc..273e612 100644
--- a/arch/metag/include/asm/uaccess.h
+++ b/arch/metag/include/asm/uaccess.h
@@ -204,8 +204,9 @@
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n)))
return __copy_user_zeroing(to, from, n);
+ memset(to, 0, n);
return n;
}
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 331b0d3..8266767 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -227,7 +227,7 @@
#define __get_user(x, ptr) \
({ \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
/*unsigned long __gu_ptr = (unsigned long)(ptr);*/ \
long __gu_err; \
switch (sizeof(*(ptr))) { \
@@ -373,10 +373,13 @@
static inline long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
+ unsigned long res = n;
might_fault();
- if (access_ok(VERIFY_READ, from, n))
- return __copy_from_user(to, from, n);
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
#define __copy_to_user(to, from, n) \
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 11b965f..21a2aab 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -14,6 +14,7 @@
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/thread_info.h>
+#include <linux/string.h>
#include <asm/asm-eva.h>
/*
@@ -1170,6 +1171,8 @@
__cu_len = __invoke_copy_from_user(__cu_to, \
__cu_from, \
__cu_len); \
+ } else { \
+ memset(__cu_to, 0, __cu_len); \
} \
} \
__cu_len; \
diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 20f7bf6..d012e87 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -166,6 +166,7 @@
"2:\n" \
" .section .fixup,\"ax\"\n" \
"3:\n\t" \
+ " mov 0,%1\n" \
" mov %3,%0\n" \
" jmp 2b\n" \
" .previous\n" \
diff --git a/arch/mn10300/lib/usercopy.c b/arch/mn10300/lib/usercopy.c
index 7826e6c..ce8899e 100644
--- a/arch/mn10300/lib/usercopy.c
+++ b/arch/mn10300/lib/usercopy.c
@@ -9,7 +9,7 @@
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
unsigned long
__generic_copy_to_user(void *to, const void *from, unsigned long n)
@@ -24,6 +24,8 @@
{
if (access_ok(VERIFY_READ, from, n))
__copy_user_zeroing(to, from, n);
+ else
+ memset(to, 0, n);
return n;
}
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index caa51ff..0ab8232 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -102,9 +102,12 @@
static inline long copy_from_user(void *to, const void __user *from,
unsigned long n)
{
- if (!access_ok(VERIFY_READ, from, n))
- return n;
- return __copy_from_user(to, from, n);
+ unsigned long res = n;
+ if (access_ok(VERIFY_READ, from, n))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline long copy_to_user(void __user *to, const void *from,
@@ -139,7 +142,7 @@
#define __get_user_unknown(val, size, ptr, err) do { \
err = 0; \
- if (copy_from_user(&(val), ptr, size)) { \
+ if (__copy_from_user(&(val), ptr, size)) { \
err = -EFAULT; \
} \
} while (0)
@@ -166,7 +169,7 @@
({ \
long __gu_err = -EFAULT; \
const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
__get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\
(x) = (__force __typeof__(x))__gu_val; \
__gu_err; \
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index a6bd07c..cbad29b 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -273,28 +273,20 @@
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
+ unsigned long res = n;
- if (access_ok(VERIFY_READ, from, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ n = __copy_tofrom_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, to, n)))
+ n = __copy_tofrom_user(to, from, n);
return n;
}
@@ -303,13 +295,8 @@
static inline __must_check unsigned long
clear_user(void *addr, unsigned long size)
{
-
- if (access_ok(VERIFY_WRITE, addr, size))
- return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, addr, size)))
+ size = __clear_user(addr, size);
return size;
}
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index e915048..4828478 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -10,6 +10,7 @@
#include <asm-generic/uaccess-unaligned.h>
#include <linux/bug.h>
+#include <linux/string.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
@@ -221,7 +222,7 @@
unsigned long n)
{
int sz = __compiletime_object_size(to);
- int ret = -EFAULT;
+ unsigned long ret = n;
if (likely(sz == -1 || sz >= n))
ret = __copy_from_user(to, from, n);
@@ -230,6 +231,8 @@
else
__bad_copy_user();
+ if (unlikely(ret))
+ memset(to + (n - ret), 0, ret);
return ret;
}
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f1e3824..c266227 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -308,36 +308,21 @@
static inline unsigned long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_READ, from, n)) {
+ if (likely(access_ok(VERIFY_READ, from, n))) {
check_object_size(to, n, false);
return __copy_tofrom_user((__force void __user *)to, from, n);
}
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- check_object_size(to, n - over, false);
- return __copy_tofrom_user((__force void __user *)to, from,
- n - over) + over;
- }
+ memset(to, 0, n);
return n;
}
static inline unsigned long copy_to_user(void __user *to,
const void *from, unsigned long n)
{
- unsigned long over;
-
if (access_ok(VERIFY_WRITE, to, n)) {
check_object_size(from, n, true);
return __copy_tofrom_user(to, (__force void __user *)from, n);
}
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- check_object_size(from, n - over, true);
- return __copy_tofrom_user(to, (__force void __user *)from,
- n - over) + over;
- }
return n;
}
@@ -434,10 +419,6 @@
might_fault();
if (likely(access_ok(VERIFY_WRITE, addr, size)))
return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
return size;
}
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 95aefdb..52d7c87 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -266,28 +266,28 @@
__chk_user_ptr(ptr); \
switch (sizeof(*(ptr))) { \
case 1: { \
- unsigned char __x; \
+ unsigned char __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 2: { \
- unsigned short __x; \
+ unsigned short __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 4: { \
- unsigned int __x; \
+ unsigned int __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 8: { \
- unsigned long long __x; \
+ unsigned long long __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f142215..607ec91 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2231,9 +2231,10 @@
return -EINVAL;
current->thread.fpu.fpc = fpu->fpc;
if (MACHINE_HAS_VX)
- convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+ convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
+ (freg_t *) fpu->fprs);
else
- memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
+ memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
return 0;
}
@@ -2242,9 +2243,10 @@
/* make sure we have the latest values */
save_fpu_regs();
if (MACHINE_HAS_VX)
- convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp((freg_t *) fpu->fprs,
+ (__vector128 *) vcpu->run->s.regs.vrs);
else
- memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+ memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
fpu->fpc = current->thread.fpu.fpc;
return 0;
}
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index c106488..d8673e2 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -584,7 +584,7 @@
/* Validity 0x0044 will be checked by SIE */
if (rc)
goto unpin;
- scb_s->gvrd = hpa;
+ scb_s->riccbd = hpa;
}
return 0;
unpin:
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index 20a3591..01aec8c 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -163,7 +163,7 @@
__get_user_asm(val, "lw", ptr); \
break; \
case 8: \
- if ((copy_from_user((void *)&val, ptr, 8)) == 0) \
+ if (__copy_from_user((void *)&val, ptr, 8) == 0) \
__gu_err = 0; \
else \
__gu_err = -EFAULT; \
@@ -188,6 +188,8 @@
\
if (likely(access_ok(VERIFY_READ, __gu_ptr, size))) \
__get_user_common((x), size, __gu_ptr); \
+ else \
+ (x) = 0; \
\
__gu_err; \
})
@@ -201,6 +203,7 @@
"2:\n" \
".section .fixup,\"ax\"\n" \
"3:li %0, %4\n" \
+ "li %1, 0\n" \
"j 2b\n" \
".previous\n" \
".section __ex_table,\"a\"\n" \
@@ -298,35 +301,34 @@
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
+ unsigned long res = len;
- if (access_ok(VERIFY_READ, from, len))
- return __copy_tofrom_user(to, from, len);
+ if (likely(access_ok(VERIFY_READ, from, len)))
+ res = __copy_tofrom_user(to, from, len);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
- return len;
+ if (unlikely(res))
+ memset(to + (len - res), 0, res);
+
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
+ if (likely(access_ok(VERIFY_WRITE, to, len)))
+ len = __copy_tofrom_user(to, from, len);
- if (access_ok(VERIFY_WRITE, to, len))
- return __copy_tofrom_user(to, from, len);
-
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
return len;
}
-#define __copy_from_user(to, from, len) \
- __copy_tofrom_user((to), (from), (len))
+static inline unsigned long
+__copy_from_user(void *to, const void *from, unsigned long len)
+{
+ unsigned long left = __copy_tofrom_user(to, from, len);
+ if (unlikely(left))
+ memset(to + (len - left), 0, left);
+ return left;
+}
#define __copy_to_user(to, from, len) \
__copy_tofrom_user((to), (from), (len))
@@ -340,17 +342,17 @@
static inline unsigned long
__copy_from_user_inatomic(void *to, const void *from, unsigned long len)
{
- return __copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
-#define __copy_in_user(to, from, len) __copy_from_user(to, from, len)
+#define __copy_in_user(to, from, len) __copy_tofrom_user(to, from, len)
static inline unsigned long
copy_in_user(void *to, const void *from, unsigned long len)
{
if (access_ok(VERIFY_READ, from, len) &&
access_ok(VERFITY_WRITE, to, len))
- return copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
/*
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index a49635c..92ade79 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -151,7 +151,10 @@
__kernel_size_t __copy_size = (__kernel_size_t) n;
if (__copy_size && __access_ok(__copy_from, __copy_size))
- return __copy_user(to, from, __copy_size);
+ __copy_size = __copy_user(to, from, __copy_size);
+
+ if (unlikely(__copy_size))
+ memset(to + (n - __copy_size), 0, __copy_size);
return __copy_size;
}
diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h
index c01376c..ca5073d 100644
--- a/arch/sh/include/asm/uaccess_64.h
+++ b/arch/sh/include/asm/uaccess_64.h
@@ -24,6 +24,7 @@
#define __get_user_size(x,ptr,size,retval) \
do { \
retval = 0; \
+ x = 0; \
switch (size) { \
case 1: \
retval = __get_user_asm_b((void *)&x, \
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index e722c51..ea55f86 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -266,8 +266,10 @@
if (n && __access_ok((unsigned long) from, n)) {
check_object_size(to, n, false);
return __copy_user((__force void __user *) to, from, n);
- } else
+ } else {
+ memset(to, 0, n);
return n;
+ }
}
static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ff574da..94dd4a3 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1004,79 +1004,87 @@
return status;
}
+struct exit_boot_struct {
+ struct boot_params *boot_params;
+ struct efi_info *efi;
+ struct setup_data *e820ext;
+ __u32 e820ext_size;
+ bool is64;
+};
+
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv)
+{
+ static bool first = true;
+ const char *signature;
+ __u32 nr_desc;
+ efi_status_t status;
+ struct exit_boot_struct *p = priv;
+
+ if (first) {
+ nr_desc = *map->buff_size / *map->desc_size;
+ if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+ u32 nr_e820ext = nr_desc -
+ ARRAY_SIZE(p->boot_params->e820_map);
+
+ status = alloc_e820ext(nr_e820ext, &p->e820ext,
+ &p->e820ext_size);
+ if (status != EFI_SUCCESS)
+ return status;
+ }
+ first = false;
+ }
+
+ signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+ memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
+
+ p->efi->efi_systab = (unsigned long)sys_table_arg;
+ p->efi->efi_memdesc_size = *map->desc_size;
+ p->efi->efi_memdesc_version = *map->desc_ver;
+ p->efi->efi_memmap = (unsigned long)*map->map;
+ p->efi->efi_memmap_size = *map->map_size;
+
+#ifdef CONFIG_X86_64
+ p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+ p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
+#endif
+
+ return EFI_SUCCESS;
+}
+
static efi_status_t exit_boot(struct boot_params *boot_params,
void *handle, bool is64)
{
- struct efi_info *efi = &boot_params->efi_info;
- unsigned long map_sz, key, desc_size;
+ unsigned long map_sz, key, desc_size, buff_size;
efi_memory_desc_t *mem_map;
struct setup_data *e820ext;
- const char *signature;
__u32 e820ext_size;
- __u32 nr_desc, prev_nr_desc;
efi_status_t status;
__u32 desc_version;
- bool called_exit = false;
- u8 nr_entries;
- int i;
+ struct efi_boot_memmap map;
+ struct exit_boot_struct priv;
- nr_desc = 0;
- e820ext = NULL;
- e820ext_size = 0;
+ map.map = &mem_map;
+ map.map_size = &map_sz;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_version;
+ map.key_ptr = &key;
+ map.buff_size = &buff_size;
+ priv.boot_params = boot_params;
+ priv.efi = &boot_params->efi_info;
+ priv.e820ext = NULL;
+ priv.e820ext_size = 0;
+ priv.is64 = is64;
-get_map:
- status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
- &desc_version, &key);
-
+ /* Might as well exit boot services now */
+ status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+ exit_boot_func);
if (status != EFI_SUCCESS)
return status;
- prev_nr_desc = nr_desc;
- nr_desc = map_sz / desc_size;
- if (nr_desc > prev_nr_desc &&
- nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
- u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
-
- status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
- if (status != EFI_SUCCESS)
- goto free_mem_map;
-
- efi_call_early(free_pool, mem_map);
- goto get_map; /* Allocated memory, get map again */
- }
-
- signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
- memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
-
- efi->efi_systab = (unsigned long)sys_table;
- efi->efi_memdesc_size = desc_size;
- efi->efi_memdesc_version = desc_version;
- efi->efi_memmap = (unsigned long)mem_map;
- efi->efi_memmap_size = map_sz;
-
-#ifdef CONFIG_X86_64
- efi->efi_systab_hi = (unsigned long)sys_table >> 32;
- efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
-#endif
-
- /* Might as well exit boot services now */
- status = efi_call_early(exit_boot_services, handle, key);
- if (status != EFI_SUCCESS) {
- /*
- * ExitBootServices() will fail if any of the event
- * handlers change the memory map. In which case, we
- * must be prepared to retry, but only once so that
- * we're guaranteed to exit on repeated failures instead
- * of spinning forever.
- */
- if (called_exit)
- goto free_mem_map;
-
- called_exit = true;
- efi_call_early(free_pool, mem_map);
- goto get_map;
- }
-
+ e820ext = priv.e820ext;
+ e820ext_size = priv.e820ext_size;
/* Historic? */
boot_params->alt_mem_k = 32 * 1024;
@@ -1085,10 +1093,6 @@
return status;
return EFI_SUCCESS;
-
-free_mem_map:
- efi_call_early(free_pool, mem_map);
- return status;
}
/*
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index e6131d4..65577f0 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -29,6 +29,8 @@
#define COUNTER_SHIFT 16
+static HLIST_HEAD(uncore_unused_list);
+
struct amd_uncore {
int id;
int refcnt;
@@ -39,7 +41,7 @@
cpumask_t *active_mask;
struct pmu *pmu;
struct perf_event *events[MAX_COUNTERS];
- struct amd_uncore *free_when_cpu_online;
+ struct hlist_node node;
};
static struct amd_uncore * __percpu *amd_uncore_nb;
@@ -306,6 +308,7 @@
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
uncore_nb->pmu = &amd_nb_pmu;
+ uncore_nb->id = -1;
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
@@ -319,6 +322,7 @@
uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
uncore_l2->active_mask = &amd_l2_active_mask;
uncore_l2->pmu = &amd_l2_pmu;
+ uncore_l2->id = -1;
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
}
@@ -348,7 +352,7 @@
continue;
if (this->id == that->id) {
- that->free_when_cpu_online = this;
+ hlist_add_head(&this->node, &uncore_unused_list);
this = that;
break;
}
@@ -388,13 +392,23 @@
return 0;
}
+static void uncore_clean_online(void)
+{
+ struct amd_uncore *uncore;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
+ hlist_del(&uncore->node);
+ kfree(uncore);
+ }
+}
+
static void uncore_online(unsigned int cpu,
struct amd_uncore * __percpu *uncores)
{
struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
- kfree(uncore->free_when_cpu_online);
- uncore->free_when_cpu_online = NULL;
+ uncore_clean_online();
if (cpu == uncore->cpu)
cpumask_set_cpu(cpu, uncore->active_mask);
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 0a6e393..bdcd651 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -31,7 +31,17 @@
struct bts_ctx {
struct perf_output_handle handle;
struct debug_store ds_back;
- int started;
+ int state;
+};
+
+/* BTS context states: */
+enum {
+ /* no ongoing AUX transactions */
+ BTS_STATE_STOPPED = 0,
+ /* AUX transaction is on, BTS tracing is disabled */
+ BTS_STATE_INACTIVE,
+ /* AUX transaction is on, BTS tracing is running */
+ BTS_STATE_ACTIVE,
};
static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
@@ -204,6 +214,15 @@
static int
bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+/*
+ * Ordering PMU callbacks wrt themselves and the PMI is done by means
+ * of bts::state, which:
+ * - is set when bts::handle::event is valid, that is, between
+ * perf_aux_output_begin() and perf_aux_output_end();
+ * - is zero otherwise;
+ * - is ordered against bts::handle::event with a compiler barrier.
+ */
+
static void __bts_event_start(struct perf_event *event)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
@@ -221,10 +240,13 @@
/*
* local barrier to make sure that ds configuration made it
- * before we enable BTS
+ * before we enable BTS and bts::state goes ACTIVE
*/
wmb();
+ /* INACTIVE/STOPPED -> ACTIVE */
+ WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
+
intel_pmu_enable_bts(config);
}
@@ -251,9 +273,6 @@
__bts_event_start(event);
- /* PMI handler: this counter is running and likely generating PMIs */
- ACCESS_ONCE(bts->started) = 1;
-
return;
fail_end_stop:
@@ -263,30 +282,34 @@
event->hw.state = PERF_HES_STOPPED;
}
-static void __bts_event_stop(struct perf_event *event)
+static void __bts_event_stop(struct perf_event *event, int state)
{
+ struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+
+ /* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
+ WRITE_ONCE(bts->state, state);
+
/*
* No extra synchronization is mandated by the documentation to have
* BTS data stores globally visible.
*/
intel_pmu_disable_bts();
-
- if (event->hw.state & PERF_HES_STOPPED)
- return;
-
- ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
}
static void bts_event_stop(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
- struct bts_buffer *buf = perf_get_aux(&bts->handle);
+ struct bts_buffer *buf = NULL;
+ int state = READ_ONCE(bts->state);
- /* PMI handler: don't restart this counter */
- ACCESS_ONCE(bts->started) = 0;
+ if (state == BTS_STATE_ACTIVE)
+ __bts_event_stop(event, BTS_STATE_STOPPED);
- __bts_event_stop(event);
+ if (state != BTS_STATE_STOPPED)
+ buf = perf_get_aux(&bts->handle);
+
+ event->hw.state |= PERF_HES_STOPPED;
if (flags & PERF_EF_UPDATE) {
bts_update(bts);
@@ -296,6 +319,7 @@
bts->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
+
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
}
@@ -310,8 +334,20 @@
void intel_bts_enable_local(void)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ int state = READ_ONCE(bts->state);
- if (bts->handle.event && bts->started)
+ /*
+ * Here we transition from INACTIVE to ACTIVE;
+ * if we instead are STOPPED from the interrupt handler,
+ * stay that way. Can't be ACTIVE here though.
+ */
+ if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
+ return;
+
+ if (state == BTS_STATE_STOPPED)
+ return;
+
+ if (bts->handle.event)
__bts_event_start(bts->handle.event);
}
@@ -319,8 +355,15 @@
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ /*
+ * Here we transition from ACTIVE to INACTIVE;
+ * do nothing for STOPPED or INACTIVE.
+ */
+ if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
+ return;
+
if (bts->handle.event)
- __bts_event_stop(bts->handle.event);
+ __bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
}
static int
@@ -335,8 +378,6 @@
return 0;
head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
- if (WARN_ON_ONCE(head != local_read(&buf->head)))
- return -EINVAL;
phys = &buf->buf[buf->cur_buf];
space = phys->offset + phys->displacement + phys->size - head;
@@ -403,22 +444,37 @@
int intel_bts_interrupt(void)
{
+ struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
struct perf_event *event = bts->handle.event;
struct bts_buffer *buf;
s64 old_head;
- int err;
+ int err = -ENOSPC, handled = 0;
- if (!event || !bts->started)
- return 0;
+ /*
+ * The only surefire way of knowing if this NMI is ours is by checking
+ * the write ptr against the PMI threshold.
+ */
+ if (ds->bts_index >= ds->bts_interrupt_threshold)
+ handled = 1;
+
+ /*
+ * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
+ * so we can only be INACTIVE or STOPPED
+ */
+ if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
+ return handled;
buf = perf_get_aux(&bts->handle);
+ if (!buf)
+ return handled;
+
/*
* Skip snapshot counters: they don't use the interrupt, but
* there's no other way of telling, because the pointer will
* keep moving
*/
- if (!buf || buf->snapshot)
+ if (buf->snapshot)
return 0;
old_head = local_read(&buf->head);
@@ -426,18 +482,27 @@
/* no new data */
if (old_head == local_read(&buf->head))
- return 0;
+ return handled;
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
buf = perf_aux_output_begin(&bts->handle, event);
- if (!buf)
- return 1;
+ if (buf)
+ err = bts_buffer_reset(buf, &bts->handle);
- err = bts_buffer_reset(buf, &bts->handle);
- if (err)
- perf_aux_output_end(&bts->handle, 0, false);
+ if (err) {
+ WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
+
+ if (buf) {
+ /*
+ * BTS_STATE_STOPPED should be visible before
+ * cleared handle::event
+ */
+ barrier();
+ perf_aux_output_end(&bts->handle, 0, false);
+ }
+ }
return 1;
}
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 783c49d..8f82b02 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -458,6 +458,11 @@
static void init_mbm_sample(u32 rmid, u32 evt_type);
static void __intel_mbm_event_count(void *info);
+static bool is_cqm_event(int e)
+{
+ return (e == QOS_L3_OCCUP_EVENT_ID);
+}
+
static bool is_mbm_event(int e)
{
return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
@@ -1366,6 +1371,10 @@
(event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
return -EINVAL;
+ if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
+ (is_mbm_event(event->attr.config) && !mbm_enabled))
+ return -EINVAL;
+
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ce9f3f..9b983a4 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1274,18 +1274,18 @@
struct pebs_record_nhm *p = at;
u64 pebs_status;
- /* PEBS v3 has accurate status bits */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+ /* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&p->status,
- MAX_PEBS_EVENTS)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status,
+ x86_pmu.max_pebs_events)
counts[bit]++;
continue;
}
- pebs_status = p->status & cpuc->pebs_enabled;
- pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
/*
* On some CPUs the PEBS status can be zero when PEBS is
* racing with clearing of GLOBAL_STATUS.
@@ -1333,8 +1333,11 @@
continue;
event = cpuc->events[bit];
- WARN_ON_ONCE(!event);
- WARN_ON_ONCE(!event->attr.precise_ip);
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
/* log dropped samples number */
if (error[bit])
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index e3af86f..2131c4c 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -433,7 +433,11 @@
#define __get_user_asm_ex(x, addr, itype, rtype, ltype) \
asm volatile("1: mov"itype" %1,%"rtype"0\n" \
"2:\n" \
- _ASM_EXTABLE_EX(1b, 2b) \
+ ".section .fixup,\"ax\"\n" \
+ "3:xor"itype" %"rtype"0,%"rtype"0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE_EX(1b, 3b) \
: ltype(x) : "m" (__m(addr)))
#define __put_user_nocheck(x, ptr, size) \
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 50c95af..f3e9b2d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2093,7 +2093,6 @@
return -EINVAL;
}
- num_processors++;
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
@@ -2116,10 +2115,13 @@
pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
thiscpu, apicid);
+
disabled_cpus++;
return -ENOSPC;
}
+ num_processors++;
+
/*
* Validate version
*/
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b816971..620ab06 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -54,6 +54,7 @@
*/
static u8 *container;
static size_t container_size;
+static bool ucode_builtin;
static u32 ucode_new_rev;
static u8 amd_ucode_patch[PATCH_MAX_SIZE];
@@ -281,18 +282,22 @@
void __init load_ucode_amd_bsp(unsigned int family)
{
struct cpio_data cp;
+ bool *builtin;
void **data;
size_t *size;
#ifdef CONFIG_X86_32
data = (void **)__pa_nodebug(&ucode_cpio.data);
size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+ builtin = (bool *)__pa_nodebug(&ucode_builtin);
#else
data = &ucode_cpio.data;
size = &ucode_cpio.size;
+ builtin = &ucode_builtin;
#endif
- if (!load_builtin_amd_microcode(&cp, family))
+ *builtin = load_builtin_amd_microcode(&cp, family);
+ if (!*builtin)
cp = find_ucode_in_initrd();
if (!(cp.data && cp.size))
@@ -373,7 +378,8 @@
return;
/* Add CONFIG_RANDOMIZE_MEMORY offset. */
- cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+ if (!ucode_builtin)
+ cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
eax = cpuid_eax(0x00000001);
eq = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ);
@@ -439,7 +445,8 @@
container = cont_va;
/* Add CONFIG_RANDOMIZE_MEMORY offset. */
- container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+ if (!ucode_builtin)
+ container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
eax = cpuid_eax(0x00000001);
eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1d39bfb..3692249 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -289,6 +289,7 @@
put_cpu();
x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+ x86_platform.calibrate_cpu = kvm_get_tsc_khz;
x86_platform.get_wallclock = kvm_get_wallclock;
x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 5f42d03..c7220ba 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -109,6 +109,7 @@
{
bool new_val, old_val;
struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+ struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
union kvm_ioapic_redirect_entry *e;
e = &ioapic->redirtbl[RTC_GSI];
@@ -117,16 +118,17 @@
return;
new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
- old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ old_val = test_bit(vcpu->vcpu_id, dest_map->map);
if (new_val == old_val)
return;
if (new_val) {
- __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __set_bit(vcpu->vcpu_id, dest_map->map);
+ dest_map->vectors[vcpu->vcpu_id] = e->fields.vector;
ioapic->rtc_status.pending_eoi++;
} else {
- __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __clear_bit(vcpu->vcpu_id, dest_map->map);
ioapic->rtc_status.pending_eoi--;
rtc_status_pending_eoi_check_valid(ioapic);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 19f9f9e..699f872 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2743,16 +2743,16 @@
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (kvm_lapic_hv_timer_in_use(vcpu) &&
- kvm_x86_ops->set_hv_timer(vcpu,
- kvm_get_lapic_tscdeadline_msr(vcpu)))
- kvm_lapic_switch_to_sw_timer(vcpu);
if (check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_x86_ops->write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
+ if (kvm_lapic_hv_timer_in_use(vcpu) &&
+ kvm_x86_ops->set_hv_timer(vcpu,
+ kvm_get_lapic_tscdeadline_msr(vcpu)))
+ kvm_lapic_switch_to_sw_timer(vcpu);
/*
* On a host with synchronized TSC, there is no need to update
* kvmclock on vcpu->cpu migration
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 837ea36..6d52b94 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -553,15 +553,21 @@
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
/*
- * Broadwell EP Home Agent BARs erroneously return non-zero values when read.
+ * Device [8086:2fc0]
+ * Erratum HSE43
+ * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html
*
- * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
- * entry BDF2.
+ * Devices [8086:6f60,6fa0,6fc0]
+ * Erratum BDF2
+ * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
*/
-static void pci_bdwep_bar(struct pci_dev *dev)
+static void pci_invalid_bar(struct pci_dev *dev)
{
dev->non_compliant_bars = 1;
}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 77207b4..0c654e5 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -631,9 +631,14 @@
static int cryptd_hash_import(struct ahash_request *req, const void *in)
{
- struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct shash_desc *desc = cryptd_shash_desc(req);
- return crypto_shash_import(&rctx->desc, in);
+ desc->tfm = ctx->child;
+ desc->flags = req->base.flags;
+
+ return crypto_shash_import(desc, in);
}
static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-h3.c b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
index 9af35954..267f995 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
@@ -783,14 +783,14 @@
[RST_BUS_I2S1] = { 0x2d0, BIT(13) },
[RST_BUS_I2S2] = { 0x2d0, BIT(14) },
- [RST_BUS_I2C0] = { 0x2d4, BIT(0) },
- [RST_BUS_I2C1] = { 0x2d4, BIT(1) },
- [RST_BUS_I2C2] = { 0x2d4, BIT(2) },
- [RST_BUS_UART0] = { 0x2d4, BIT(16) },
- [RST_BUS_UART1] = { 0x2d4, BIT(17) },
- [RST_BUS_UART2] = { 0x2d4, BIT(18) },
- [RST_BUS_UART3] = { 0x2d4, BIT(19) },
- [RST_BUS_SCR] = { 0x2d4, BIT(20) },
+ [RST_BUS_I2C0] = { 0x2d8, BIT(0) },
+ [RST_BUS_I2C1] = { 0x2d8, BIT(1) },
+ [RST_BUS_I2C2] = { 0x2d8, BIT(2) },
+ [RST_BUS_UART0] = { 0x2d8, BIT(16) },
+ [RST_BUS_UART1] = { 0x2d8, BIT(17) },
+ [RST_BUS_UART2] = { 0x2d8, BIT(18) },
+ [RST_BUS_UART3] = { 0x2d8, BIT(19) },
+ [RST_BUS_SCR] = { 0x2d8, BIT(20) },
};
static const struct sunxi_ccu_desc sun8i_h3_ccu_desc = {
diff --git a/drivers/clk/sunxi-ng/ccu_nk.c b/drivers/clk/sunxi-ng/ccu_nk.c
index 4470ffc..d6fafb3 100644
--- a/drivers/clk/sunxi-ng/ccu_nk.c
+++ b/drivers/clk/sunxi-ng/ccu_nk.c
@@ -14,9 +14,9 @@
#include "ccu_gate.h"
#include "ccu_nk.h"
-void ccu_nk_find_best(unsigned long parent, unsigned long rate,
- unsigned int max_n, unsigned int max_k,
- unsigned int *n, unsigned int *k)
+static void ccu_nk_find_best(unsigned long parent, unsigned long rate,
+ unsigned int max_n, unsigned int max_k,
+ unsigned int *n, unsigned int *k)
{
unsigned long best_rate = 0;
unsigned int best_k = 0, best_n = 0;
diff --git a/drivers/clk/sunxi/clk-a10-pll2.c b/drivers/clk/sunxi/clk-a10-pll2.c
index 0ee1f36..d8eab90 100644
--- a/drivers/clk/sunxi/clk-a10-pll2.c
+++ b/drivers/clk/sunxi/clk-a10-pll2.c
@@ -73,7 +73,7 @@
SUN4I_PLL2_PRE_DIV_WIDTH,
CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
&sun4i_a10_pll2_lock);
- if (!prediv_clk) {
+ if (IS_ERR(prediv_clk)) {
pr_err("Couldn't register the prediv clock\n");
goto err_free_array;
}
@@ -106,7 +106,7 @@
&mult->hw, &clk_multiplier_ops,
&gate->hw, &clk_gate_ops,
CLK_SET_RATE_PARENT);
- if (!base_clk) {
+ if (IS_ERR(base_clk)) {
pr_err("Couldn't register the base multiplier clock\n");
goto err_free_multiplier;
}
diff --git a/drivers/clk/sunxi/clk-sun8i-mbus.c b/drivers/clk/sunxi/clk-sun8i-mbus.c
index 411d303..b200ebf 100644
--- a/drivers/clk/sunxi/clk-sun8i-mbus.c
+++ b/drivers/clk/sunxi/clk-sun8i-mbus.c
@@ -48,7 +48,7 @@
return;
reg = of_io_request_and_map(node, 0, of_node_full_name(node));
- if (!reg) {
+ if (IS_ERR(reg)) {
pr_err("Could not get registers for sun8i-mbus-clk\n");
goto err_free_parents;
}
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 5a2631a..7dd2e2d 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -657,9 +657,12 @@
}
if (subnode) {
- node = of_get_flat_dt_subnode_by_name(node, subnode);
- if (node < 0)
+ int err = of_get_flat_dt_subnode_by_name(node, subnode);
+
+ if (err < 0)
return 0;
+
+ node = err;
}
return __find_uefi_params(node, info, dt_params[i].params);
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 3bd127f9..aded106 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -41,6 +41,8 @@
#define EFI_ALLOC_ALIGN EFI_PAGE_SIZE
#endif
+#define EFI_MMAP_NR_SLACK_SLOTS 8
+
struct file_info {
efi_file_handle_t *handle;
u64 size;
@@ -63,49 +65,62 @@
}
}
+static inline bool mmap_has_headroom(unsigned long buff_size,
+ unsigned long map_size,
+ unsigned long desc_size)
+{
+ unsigned long slack = buff_size - map_size;
+
+ return slack / desc_size >= EFI_MMAP_NR_SLACK_SLOTS;
+}
+
efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
- efi_memory_desc_t **map,
- unsigned long *map_size,
- unsigned long *desc_size,
- u32 *desc_ver,
- unsigned long *key_ptr)
+ struct efi_boot_memmap *map)
{
efi_memory_desc_t *m = NULL;
efi_status_t status;
unsigned long key;
u32 desc_version;
- *map_size = sizeof(*m) * 32;
+ *map->desc_size = sizeof(*m);
+ *map->map_size = *map->desc_size * 32;
+ *map->buff_size = *map->map_size;
again:
- /*
- * Add an additional efi_memory_desc_t because we're doing an
- * allocation which may be in a new descriptor region.
- */
- *map_size += sizeof(*m);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- *map_size, (void **)&m);
+ *map->map_size, (void **)&m);
if (status != EFI_SUCCESS)
goto fail;
- *desc_size = 0;
+ *map->desc_size = 0;
key = 0;
- status = efi_call_early(get_memory_map, map_size, m,
- &key, desc_size, &desc_version);
- if (status == EFI_BUFFER_TOO_SMALL) {
+ status = efi_call_early(get_memory_map, map->map_size, m,
+ &key, map->desc_size, &desc_version);
+ if (status == EFI_BUFFER_TOO_SMALL ||
+ !mmap_has_headroom(*map->buff_size, *map->map_size,
+ *map->desc_size)) {
efi_call_early(free_pool, m);
+ /*
+ * Make sure there is some entries of headroom so that the
+ * buffer can be reused for a new map after allocations are
+ * no longer permitted. Its unlikely that the map will grow to
+ * exceed this headroom once we are ready to trigger
+ * ExitBootServices()
+ */
+ *map->map_size += *map->desc_size * EFI_MMAP_NR_SLACK_SLOTS;
+ *map->buff_size = *map->map_size;
goto again;
}
if (status != EFI_SUCCESS)
efi_call_early(free_pool, m);
- if (key_ptr && status == EFI_SUCCESS)
- *key_ptr = key;
- if (desc_ver && status == EFI_SUCCESS)
- *desc_ver = desc_version;
+ if (map->key_ptr && status == EFI_SUCCESS)
+ *map->key_ptr = key;
+ if (map->desc_ver && status == EFI_SUCCESS)
+ *map->desc_ver = desc_version;
fail:
- *map = m;
+ *map->map = m;
return status;
}
@@ -113,13 +128,20 @@
unsigned long get_dram_base(efi_system_table_t *sys_table_arg)
{
efi_status_t status;
- unsigned long map_size;
+ unsigned long map_size, buff_size;
unsigned long membase = EFI_ERROR;
struct efi_memory_map map;
efi_memory_desc_t *md;
+ struct efi_boot_memmap boot_map;
- status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map,
- &map_size, &map.desc_size, NULL, NULL);
+ boot_map.map = (efi_memory_desc_t **)&map.map;
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &map.desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
return membase;
@@ -144,15 +166,22 @@
unsigned long size, unsigned long align,
unsigned long *addr, unsigned long max)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
efi_memory_desc_t *map;
efi_status_t status;
unsigned long nr_pages;
u64 max_addr = 0;
int i;
+ struct efi_boot_memmap boot_map;
- status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
- NULL, NULL);
+ boot_map.map = ↦
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
goto fail;
@@ -230,14 +259,21 @@
unsigned long size, unsigned long align,
unsigned long *addr)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
efi_memory_desc_t *map;
efi_status_t status;
unsigned long nr_pages;
int i;
+ struct efi_boot_memmap boot_map;
- status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
- NULL, NULL);
+ boot_map.map = ↦
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
goto fail;
@@ -704,3 +740,76 @@
*cmd_line_len = options_bytes;
return (char *)cmdline_addr;
}
+
+/*
+ * Handle calling ExitBootServices according to the requirements set out by the
+ * spec. Obtains the current memory map, and returns that info after calling
+ * ExitBootServices. The client must specify a function to perform any
+ * processing of the memory map data prior to ExitBootServices. A client
+ * specific structure may be passed to the function via priv. The client
+ * function may be called multiple times.
+ */
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table_arg,
+ void *handle,
+ struct efi_boot_memmap *map,
+ void *priv,
+ efi_exit_boot_map_processing priv_func)
+{
+ efi_status_t status;
+
+ status = efi_get_memory_map(sys_table_arg, map);
+
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = priv_func(sys_table_arg, map, priv);
+ if (status != EFI_SUCCESS)
+ goto free_map;
+
+ status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+
+ if (status == EFI_INVALID_PARAMETER) {
+ /*
+ * The memory map changed between efi_get_memory_map() and
+ * exit_boot_services(). Per the UEFI Spec v2.6, Section 6.4:
+ * EFI_BOOT_SERVICES.ExitBootServices we need to get the
+ * updated map, and try again. The spec implies one retry
+ * should be sufficent, which is confirmed against the EDK2
+ * implementation. Per the spec, we can only invoke
+ * get_memory_map() and exit_boot_services() - we cannot alloc
+ * so efi_get_memory_map() cannot be used, and we must reuse
+ * the buffer. For all practical purposes, the headroom in the
+ * buffer should account for any changes in the map so the call
+ * to get_memory_map() is expected to succeed here.
+ */
+ *map->map_size = *map->buff_size;
+ status = efi_call_early(get_memory_map,
+ map->map_size,
+ *map->map,
+ map->key_ptr,
+ map->desc_size,
+ map->desc_ver);
+
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = priv_func(sys_table_arg, map, priv);
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+ }
+
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ return EFI_SUCCESS;
+
+free_map:
+ efi_call_early(free_pool, *map->map);
+fail:
+ return status;
+}
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index e58abfa..a6a9311 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -152,6 +152,27 @@
#define EFI_FDT_ALIGN EFI_PAGE_SIZE
#endif
+struct exit_boot_struct {
+ efi_memory_desc_t *runtime_map;
+ int *runtime_entry_count;
+};
+
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv)
+{
+ struct exit_boot_struct *p = priv;
+ /*
+ * Update the memory map with virtual addresses. The function will also
+ * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
+ * entries so that we can pass it straight to SetVirtualAddressMap()
+ */
+ efi_get_virtmap(*map->map, *map->map_size, *map->desc_size,
+ p->runtime_map, p->runtime_entry_count);
+
+ return EFI_SUCCESS;
+}
+
/*
* Allocate memory for a new FDT, then add EFI, commandline, and
* initrd related fields to the FDT. This routine increases the
@@ -175,13 +196,22 @@
unsigned long fdt_addr,
unsigned long fdt_size)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
u32 desc_ver;
unsigned long mmap_key;
efi_memory_desc_t *memory_map, *runtime_map;
unsigned long new_fdt_size;
efi_status_t status;
int runtime_entry_count = 0;
+ struct efi_boot_memmap map;
+ struct exit_boot_struct priv;
+
+ map.map = &runtime_map;
+ map.map_size = &map_size;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_ver;
+ map.key_ptr = &mmap_key;
+ map.buff_size = &buff_size;
/*
* Get a copy of the current memory map that we will use to prepare
@@ -189,8 +219,7 @@
* subsequent allocations adding entries, since they could not affect
* the number of EFI_MEMORY_RUNTIME regions.
*/
- status = efi_get_memory_map(sys_table, &runtime_map, &map_size,
- &desc_size, &desc_ver, &mmap_key);
+ status = efi_get_memory_map(sys_table, &map);
if (status != EFI_SUCCESS) {
pr_efi_err(sys_table, "Unable to retrieve UEFI memory map.\n");
return status;
@@ -199,6 +228,7 @@
pr_efi(sys_table,
"Exiting boot services and installing virtual address map...\n");
+ map.map = &memory_map;
/*
* Estimate size of new FDT, and allocate memory for it. We
* will allocate a bigger buffer if this ends up being too
@@ -218,8 +248,7 @@
* we can get the memory map key needed for
* exit_boot_services().
*/
- status = efi_get_memory_map(sys_table, &memory_map, &map_size,
- &desc_size, &desc_ver, &mmap_key);
+ status = efi_get_memory_map(sys_table, &map);
if (status != EFI_SUCCESS)
goto fail_free_new_fdt;
@@ -250,16 +279,11 @@
}
}
- /*
- * Update the memory map with virtual addresses. The function will also
- * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
- * entries so that we can pass it straight into SetVirtualAddressMap()
- */
- efi_get_virtmap(memory_map, map_size, desc_size, runtime_map,
- &runtime_entry_count);
-
- /* Now we are ready to exit_boot_services.*/
- status = sys_table->boottime->exit_boot_services(handle, mmap_key);
+ sys_table->boottime->free_pool(memory_map);
+ priv.runtime_map = runtime_map;
+ priv.runtime_entry_count = &runtime_entry_count;
+ status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+ exit_boot_func);
if (status == EFI_SUCCESS) {
efi_set_virtual_address_map_t *svam;
diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
index 53f6d3f..0c9f58c 100644
--- a/drivers/firmware/efi/libstub/random.c
+++ b/drivers/firmware/efi/libstub/random.c
@@ -73,12 +73,20 @@
unsigned long random_seed)
{
unsigned long map_size, desc_size, total_slots = 0, target_slot;
+ unsigned long buff_size;
efi_status_t status;
efi_memory_desc_t *memory_map;
int map_offset;
+ struct efi_boot_memmap map;
- status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size,
- &desc_size, NULL, NULL);
+ map.map = &memory_map;
+ map.map_size = &map_size;
+ map.desc_size = &desc_size;
+ map.desc_ver = NULL;
+ map.key_ptr = NULL;
+ map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &map);
if (status != EFI_SUCCESS)
return status;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index b6a953a..80f9889 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -333,6 +333,8 @@
spin_lock_irqsave(&ep->com.dev->lock, flags);
_remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid, 0);
+ if (idr_is_empty(&ep->com.dev->hwtid_idr))
+ wake_up(&ep->com.dev->wait);
spin_unlock_irqrestore(&ep->com.dev->lock, flags);
}
@@ -2117,8 +2119,10 @@
}
ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
n, pdev, rt_tos2priority(tos));
- if (!ep->l2t)
+ if (!ep->l2t) {
+ dev_put(pdev);
goto out;
+ }
ep->mtu = pdev->mtu;
ep->tx_chan = cxgb4_port_chan(pdev);
ep->smac_idx = cxgb4_tp_smt_idx(adapter_type,
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 071d733..3c4b212 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -872,9 +872,13 @@
static void c4iw_dealloc(struct uld_ctx *ctx)
{
c4iw_rdev_close(&ctx->dev->rdev);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->cqidr));
idr_destroy(&ctx->dev->cqidr);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->qpidr));
idr_destroy(&ctx->dev->qpidr);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->mmidr));
idr_destroy(&ctx->dev->mmidr);
+ wait_event(ctx->dev->wait, idr_is_empty(&ctx->dev->hwtid_idr));
idr_destroy(&ctx->dev->hwtid_idr);
idr_destroy(&ctx->dev->stid_idr);
idr_destroy(&ctx->dev->atid_idr);
@@ -992,6 +996,7 @@
mutex_init(&devp->rdev.stats.lock);
mutex_init(&devp->db_mutex);
INIT_LIST_HEAD(&devp->db_fc_list);
+ init_waitqueue_head(&devp->wait);
devp->avail_ird = devp->rdev.lldi.max_ird_adapter;
if (c4iw_debugfs_root) {
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index aa47e0a..4b83b84f 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -263,6 +263,7 @@
struct idr stid_idr;
struct list_head db_fc_list;
u32 avail_ird;
+ wait_queue_head_t wait;
};
static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 67642ba..915e84d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7610,16 +7610,12 @@
int md_setup_cluster(struct mddev *mddev, int nodes)
{
- int err;
-
- err = request_module("md-cluster");
- if (err) {
- pr_err("md-cluster module not found.\n");
- return -ENOENT;
- }
-
+ if (!md_cluster_ops)
+ request_module("md-cluster");
spin_lock(&pers_lock);
+ /* ensure module won't be unloaded */
if (!md_cluster_ops || !try_module_get(md_cluster_mod)) {
+ pr_err("can't find md-cluster module or get it's reference.\n");
spin_unlock(&pers_lock);
return -ENOENT;
}
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 51f76dd..1b1ab4a 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -96,7 +96,6 @@
spinlock_t no_space_stripes_lock;
bool need_cache_flush;
- bool in_teardown;
};
/*
@@ -704,31 +703,22 @@
mddev = log->rdev->mddev;
/*
- * This is to avoid a deadlock. r5l_quiesce holds reconfig_mutex and
- * wait for this thread to finish. This thread waits for
- * MD_CHANGE_PENDING clear, which is supposed to be done in
- * md_check_recovery(). md_check_recovery() tries to get
- * reconfig_mutex. Since r5l_quiesce already holds the mutex,
- * md_check_recovery() fails, so the PENDING never get cleared. The
- * in_teardown check workaround this issue.
+ * Discard could zero data, so before discard we must make sure
+ * superblock is updated to new log tail. Updating superblock (either
+ * directly call md_update_sb() or depend on md thread) must hold
+ * reconfig mutex. On the other hand, raid5_quiesce is called with
+ * reconfig_mutex hold. The first step of raid5_quiesce() is waitting
+ * for all IO finish, hence waitting for reclaim thread, while reclaim
+ * thread is calling this function and waitting for reconfig mutex. So
+ * there is a deadlock. We workaround this issue with a trylock.
+ * FIXME: we could miss discard if we can't take reconfig mutex
*/
- if (!log->in_teardown) {
- set_mask_bits(&mddev->flags, 0,
- BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
- md_wakeup_thread(mddev->thread);
- wait_event(mddev->sb_wait,
- !test_bit(MD_CHANGE_PENDING, &mddev->flags) ||
- log->in_teardown);
- /*
- * r5l_quiesce could run after in_teardown check and hold
- * mutex first. Superblock might get updated twice.
- */
- if (log->in_teardown)
- md_update_sb(mddev, 1);
- } else {
- WARN_ON(!mddev_is_locked(mddev));
- md_update_sb(mddev, 1);
- }
+ set_mask_bits(&mddev->flags, 0,
+ BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+ if (!mddev_trylock(mddev))
+ return;
+ md_update_sb(mddev, 1);
+ mddev_unlock(mddev);
/* discard IO error really doesn't matter, ignore it */
if (log->last_checkpoint < end) {
@@ -827,7 +817,6 @@
if (!log || state == 2)
return;
if (state == 0) {
- log->in_teardown = 0;
/*
* This is a special case for hotadd. In suspend, the array has
* no journal. In resume, journal is initialized as well as the
@@ -838,11 +827,6 @@
log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
log->rdev->mddev, "reclaim");
} else if (state == 1) {
- /*
- * at this point all stripes are finished, so io_unit is at
- * least in STRIPE_END state
- */
- log->in_teardown = 1;
/* make sure r5l_write_super_and_discard_space exits */
mddev = log->rdev->mddev;
wake_up(&mddev->sb_wait);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index da583bb..ee7fc37 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2423,10 +2423,10 @@
}
}
rdev_dec_pending(rdev, conf->mddev);
+ bio_reset(bi);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
- bio_reset(bi);
}
static void raid5_end_write_request(struct bio *bi)
@@ -2498,6 +2498,7 @@
if (sh->batch_head && bi->bi_error && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
+ bio_reset(bi);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
@@ -2505,7 +2506,6 @@
if (sh->batch_head && sh != sh->batch_head)
raid5_release_stripe(sh->batch_head);
- bio_reset(bi);
}
static void raid5_build_block(struct stripe_head *sh, int i, int previous)
@@ -6639,6 +6639,16 @@
}
conf->min_nr_stripes = NR_STRIPES;
+ if (mddev->reshape_position != MaxSector) {
+ int stripes = max_t(int,
+ ((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
+ ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+ conf->min_nr_stripes = max(NR_STRIPES, stripes);
+ if (conf->min_nr_stripes != NR_STRIPES)
+ printk(KERN_INFO
+ "md/raid:%s: force stripe size %d for reshape\n",
+ mdname(mddev), conf->min_nr_stripes);
+ }
memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 217e8da..9599ed6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1341,9 +1341,10 @@
slave_dev->name);
}
- /* already enslaved */
- if (slave_dev->flags & IFF_SLAVE) {
- netdev_dbg(bond_dev, "Error: Device was already enslaved\n");
+ /* already in-use? */
+ if (netdev_is_rx_handler_busy(slave_dev)) {
+ netdev_err(bond_dev,
+ "Error: Device is in use and cannot be enslaved\n");
return -EBUSY;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 97e8925..fa3386b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -772,6 +772,11 @@
(bp->common.bc_ver & 0xff00) >> 8,
(bp->common.bc_ver & 0xff));
+ if (pci_channel_offline(bp->pdev)) {
+ BNX2X_ERR("Cannot dump MCP info while in PCI error\n");
+ return;
+ }
+
val = REG_RD(bp, MCP_REG_MCPR_CPU_PROGRAM_COUNTER);
if (val == REG_RD(bp, MCP_REG_MCPR_CPU_PROGRAM_COUNTER))
BNX2X_ERR("%s" "MCP PC at 0x%x\n", lvl, val);
@@ -9415,10 +9420,16 @@
/* Release IRQs */
bnx2x_free_irq(bp);
- /* Reset the chip */
- rc = bnx2x_reset_hw(bp, reset_code);
- if (rc)
- BNX2X_ERR("HW_RESET failed\n");
+ /* Reset the chip, unless PCI function is offline. If we reach this
+ * point following a PCI error handling, it means device is really
+ * in a bad state and we're about to remove it, so reset the chip
+ * is not a good idea.
+ */
+ if (!pci_channel_offline(bp->pdev)) {
+ rc = bnx2x_reset_hw(bp, reset_code);
+ if (rc)
+ BNX2X_ERR("HW_RESET failed\n");
+ }
/* Report UNLOAD_DONE to MCP */
bnx2x_send_unload_done(bp, keep_link);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2cf7910..228c964 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -353,8 +353,8 @@
push_len = (length + sizeof(*tx_push) + 7) / 8;
if (push_len > 16) {
__iowrite64_copy(txr->tx_doorbell, tx_push_buf, 16);
- __iowrite64_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
- push_len - 16);
+ __iowrite32_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
+ (push_len - 16) << 1);
} else {
__iowrite64_copy(txr->tx_doorbell, tx_push_buf,
push_len);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 6592612..a2551bc 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14012,6 +14012,7 @@
if ((ec->rx_coalesce_usecs > MAX_RXCOL_TICKS) ||
(!ec->rx_coalesce_usecs) ||
(ec->tx_coalesce_usecs > MAX_TXCOL_TICKS) ||
+ (!ec->tx_coalesce_usecs) ||
(ec->rx_max_coalesced_frames > MAX_RXMAX_FRAMES) ||
(ec->tx_max_coalesced_frames > MAX_TXMAX_FRAMES) ||
(ec->rx_coalesce_usecs_irq > max_rxcoal_tick_int) ||
@@ -14022,16 +14023,6 @@
(ec->stats_block_coalesce_usecs < min_stat_coal_ticks))
return -EINVAL;
- /* No rx interrupts will be generated if both are zero */
- if ((ec->rx_coalesce_usecs == 0) &&
- (ec->rx_max_coalesced_frames == 0))
- return -EINVAL;
-
- /* No tx interrupts will be generated if both are zero */
- if ((ec->tx_coalesce_usecs == 0) &&
- (ec->tx_max_coalesced_frames == 0))
- return -EINVAL;
-
/* Only copy relevant parameters, ignore all others. */
tp->coal.rx_coalesce_usecs = ec->rx_coalesce_usecs;
tp->coal.tx_coalesce_usecs = ec->tx_coalesce_usecs;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 89c0cfa..d954a97b 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -1323,6 +1323,24 @@
return 0;
}
+static inline int macb_clear_csum(struct sk_buff *skb)
+{
+ /* no change for packets without checksum offloading */
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
+ /* make sure we can modify the header */
+ if (unlikely(skb_cow_head(skb, 0)))
+ return -1;
+
+ /* initialize checksum field
+ * This is required - at least for Zynq, which otherwise calculates
+ * wrong UDP header checksums for UDP packets with UDP data len <=2
+ */
+ *(__sum16 *)(skb_checksum_start(skb) + skb->csum_offset) = 0;
+ return 0;
+}
+
static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
u16 queue_index = skb_get_queue_mapping(skb);
@@ -1362,6 +1380,11 @@
return NETDEV_TX_BUSY;
}
+ if (macb_clear_csum(skb)) {
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
/* Map socket buffer for DMA transfer */
if (!macb_tx_map(bp, queue, skb)) {
dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 83025bb..e29815d 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -279,6 +279,7 @@
u8 sqs_id;
bool sqs_mode;
bool hw_tso;
+ bool t88;
/* Receive buffer alloc */
u32 rb_page_offset;
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 16ed203..85cc782 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -251,9 +251,14 @@
int lmac;
u64 lmac_cfg;
- /* Max value that can be set is 60 */
- if (size > 60)
- size = 60;
+ /* There is a issue in HW where-in while sending GSO sized
+ * pkts as part of TSO, if pkt len falls below this size
+ * NIC will zero PAD packet and also updates IP total length.
+ * Hence set this value to lessthan min pkt size of MAC+IP+TCP
+ * headers, BGX will do the padding to transmit 64 byte pkt.
+ */
+ if (size > 52)
+ size = 52;
for (lmac = 0; lmac < (MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX); lmac++) {
lmac_cfg = nic_reg_read(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3));
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index a19e73f..3240349 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -513,6 +513,7 @@
struct nicvf *nic = netdev_priv(netdev);
struct snd_queue *sq;
struct sq_hdr_subdesc *hdr;
+ struct sq_hdr_subdesc *tso_sqe;
sq = &nic->qs->sq[cqe_tx->sq_idx];
@@ -527,17 +528,21 @@
nicvf_check_cqe_tx_errs(nic, cq, cqe_tx);
skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
- /* For TSO offloaded packets only one SQE will have a valid SKB */
if (skb) {
+ /* Check for dummy descriptor used for HW TSO offload on 88xx */
+ if (hdr->dont_send) {
+ /* Get actual TSO descriptors and free them */
+ tso_sqe =
+ (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+ nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1);
+ }
nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
prefetch(skb);
dev_consume_skb_any(skb);
sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
} else {
- /* In case of HW TSO, HW sends a CQE for each segment of a TSO
- * packet instead of a single CQE for the whole TSO packet
- * transmitted. Each of this CQE points to the same SQE, so
- * avoid freeing same SQE multiple times.
+ /* In case of SW TSO on 88xx, only last segment will have
+ * a SKB attached, so just free SQEs here.
*/
if (!nic->hw_tso)
nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
@@ -1502,6 +1507,7 @@
struct net_device *netdev;
struct nicvf *nic;
int err, qcount;
+ u16 sdevid;
err = pci_enable_device(pdev);
if (err) {
@@ -1575,6 +1581,10 @@
if (!pass1_silicon(nic->pdev))
nic->hw_tso = true;
+ pci_read_config_word(nic->pdev, PCI_SUBSYSTEM_ID, &sdevid);
+ if (sdevid == 0xA134)
+ nic->t88 = true;
+
/* Check if this VF is in QS only mode */
if (nic->sqs_mode)
return 0;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 0ff8e60..dda3ea3 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -938,6 +938,8 @@
return num_edescs + sh->gso_segs;
}
+#define POST_CQE_DESC_COUNT 2
+
/* Get the number of SQ descriptors needed to xmit this skb */
static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb)
{
@@ -948,6 +950,10 @@
return subdesc_cnt;
}
+ /* Dummy descriptors to get TSO pkt completion notification */
+ if (nic->t88 && nic->hw_tso && skb_shinfo(skb)->gso_size)
+ subdesc_cnt += POST_CQE_DESC_COUNT;
+
if (skb_shinfo(skb)->nr_frags)
subdesc_cnt += skb_shinfo(skb)->nr_frags;
@@ -965,14 +971,21 @@
struct sq_hdr_subdesc *hdr;
hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
- sq->skbuff[qentry] = (u64)skb;
-
memset(hdr, 0, SND_QUEUE_DESC_SIZE);
hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
- /* Enable notification via CQE after processing SQE */
- hdr->post_cqe = 1;
- /* No of subdescriptors following this */
- hdr->subdesc_cnt = subdesc_cnt;
+
+ if (nic->t88 && nic->hw_tso && skb_shinfo(skb)->gso_size) {
+ /* post_cqe = 0, to avoid HW posting a CQE for every TSO
+ * segment transmitted on 88xx.
+ */
+ hdr->subdesc_cnt = subdesc_cnt - POST_CQE_DESC_COUNT;
+ } else {
+ sq->skbuff[qentry] = (u64)skb;
+ /* Enable notification via CQE after processing SQE */
+ hdr->post_cqe = 1;
+ /* No of subdescriptors following this */
+ hdr->subdesc_cnt = subdesc_cnt;
+ }
hdr->tot_len = len;
/* Offload checksum calculation to HW */
@@ -1023,6 +1036,37 @@
gather->addr = data;
}
+/* Add HDR + IMMEDIATE subdescriptors right after descriptors of a TSO
+ * packet so that a CQE is posted as a notifation for transmission of
+ * TSO packet.
+ */
+static inline void nicvf_sq_add_cqe_subdesc(struct snd_queue *sq, int qentry,
+ int tso_sqe, struct sk_buff *skb)
+{
+ struct sq_imm_subdesc *imm;
+ struct sq_hdr_subdesc *hdr;
+
+ sq->skbuff[qentry] = (u64)skb;
+
+ hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
+ memset(hdr, 0, SND_QUEUE_DESC_SIZE);
+ hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
+ /* Enable notification via CQE after processing SQE */
+ hdr->post_cqe = 1;
+ /* There is no packet to transmit here */
+ hdr->dont_send = 1;
+ hdr->subdesc_cnt = POST_CQE_DESC_COUNT - 1;
+ hdr->tot_len = 1;
+ /* Actual TSO header SQE index, needed for cleanup */
+ hdr->rsvd2 = tso_sqe;
+
+ qentry = nicvf_get_nxt_sqentry(sq, qentry);
+ imm = (struct sq_imm_subdesc *)GET_SQ_DESC(sq, qentry);
+ memset(imm, 0, SND_QUEUE_DESC_SIZE);
+ imm->subdesc_type = SQ_DESC_TYPE_IMMEDIATE;
+ imm->len = 1;
+}
+
/* Segment a TSO packet into 'gso_size' segments and append
* them to SQ for transfer
*/
@@ -1096,7 +1140,7 @@
int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb)
{
int i, size;
- int subdesc_cnt;
+ int subdesc_cnt, tso_sqe = 0;
int sq_num, qentry;
struct queue_set *qs;
struct snd_queue *sq;
@@ -1131,6 +1175,7 @@
/* Add SQ header subdesc */
nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1,
skb, skb->len);
+ tso_sqe = qentry;
/* Add SQ gather subdescs */
qentry = nicvf_get_nxt_sqentry(sq, qentry);
@@ -1154,6 +1199,11 @@
}
doorbell:
+ if (nic->t88 && skb_shinfo(skb)->gso_size) {
+ qentry = nicvf_get_nxt_sqentry(sq, qentry);
+ nicvf_sq_add_cqe_subdesc(sq, qentry, tso_sqe, skb);
+ }
+
/* make sure all memory stores are done before ringing doorbell */
smp_wmb();
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 828ed28..d0b3a1b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5113,9 +5113,13 @@
DCB_CAP_DCBX_VER_IEEE;
pf->flags |= I40E_FLAG_DCB_CAPABLE;
- /* Enable DCB tagging only when more than one TC */
+ /* Enable DCB tagging only when more than one TC
+ * or explicitly disable if only one TC
+ */
if (i40e_dcb_get_num_tc(&hw->local_dcbx_config) > 1)
pf->flags |= I40E_FLAG_DCB_ENABLED;
+ else
+ pf->flags &= ~I40E_FLAG_DCB_ENABLED;
dev_dbg(&pf->pdev->dev,
"DCBX offload is supported for this PF.\n");
}
@@ -5716,7 +5720,7 @@
u8 type;
/* Not DCB capable or capability disabled */
- if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+ if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
return ret;
/* Ignore if event is not for Nearest Bridge */
@@ -7896,6 +7900,7 @@
#endif
I40E_FLAG_RSS_ENABLED |
I40E_FLAG_DCB_CAPABLE |
+ I40E_FLAG_DCB_ENABLED |
I40E_FLAG_SRIOV_ENABLED |
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
@@ -10502,6 +10507,7 @@
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
I40E_FLAG_DCB_CAPABLE |
+ I40E_FLAG_DCB_ENABLED |
I40E_FLAG_SRIOV_ENABLED |
I40E_FLAG_VMDQ_ENABLED);
} else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED |
@@ -10525,7 +10531,8 @@
/* Not enough queues for all TCs */
if ((pf->flags & I40E_FLAG_DCB_CAPABLE) &&
(queues_left < I40E_MAX_TRAFFIC_CLASS)) {
- pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+ pf->flags &= ~(I40E_FLAG_DCB_CAPABLE |
+ I40E_FLAG_DCB_ENABLED);
dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n");
}
pf->num_lan_qps = max_t(int, pf->rss_size_max,
@@ -10922,7 +10929,7 @@
err = i40e_init_pf_dcb(pf);
if (err) {
dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err);
- pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+ pf->flags &= ~(I40E_FLAG_DCB_CAPABLE & I40E_FLAG_DCB_ENABLED);
/* Continue without DCB enabled */
}
#endif /* CONFIG_I40E_DCB */
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index f160954..d919915 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -50,6 +50,10 @@
MTK_ETHTOOL_STAT(rx_flow_control_packets),
};
+static const char * const mtk_clks_source_name[] = {
+ "ethif", "esw", "gp1", "gp2"
+};
+
void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg)
{
__raw_writel(val, eth->base + reg);
@@ -291,7 +295,7 @@
static int mtk_mdio_init(struct mtk_eth *eth)
{
struct device_node *mii_np;
- int err;
+ int ret;
mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus");
if (!mii_np) {
@@ -300,13 +304,13 @@
}
if (!of_device_is_available(mii_np)) {
- err = 0;
+ ret = -ENODEV;
goto err_put_node;
}
- eth->mii_bus = mdiobus_alloc();
+ eth->mii_bus = devm_mdiobus_alloc(eth->dev);
if (!eth->mii_bus) {
- err = -ENOMEM;
+ ret = -ENOMEM;
goto err_put_node;
}
@@ -317,19 +321,11 @@
eth->mii_bus->parent = eth->dev;
snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%s", mii_np->name);
- err = of_mdiobus_register(eth->mii_bus, mii_np);
- if (err)
- goto err_free_bus;
-
- return 0;
-
-err_free_bus:
- mdiobus_free(eth->mii_bus);
+ ret = of_mdiobus_register(eth->mii_bus, mii_np);
err_put_node:
of_node_put(mii_np);
- eth->mii_bus = NULL;
- return err;
+ return ret;
}
static void mtk_mdio_cleanup(struct mtk_eth *eth)
@@ -338,8 +334,6 @@
return;
mdiobus_unregister(eth->mii_bus);
- of_node_put(eth->mii_bus->dev.of_node);
- mdiobus_free(eth->mii_bus);
}
static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
@@ -588,14 +582,15 @@
dma_addr_t mapped_addr;
unsigned int nr_frags;
int i, n_desc = 1;
- u32 txd4 = 0;
+ u32 txd4 = 0, fport;
itxd = ring->next_free;
if (itxd == ring->last_free)
return -ENOMEM;
/* set the forward port */
- txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT;
+ fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT;
+ txd4 |= fport;
tx_buf = mtk_desc_to_tx_buf(ring, itxd);
memset(tx_buf, 0, sizeof(*tx_buf));
@@ -653,7 +648,7 @@
WRITE_ONCE(txd->txd3, (TX_DMA_SWC |
TX_DMA_PLEN0(frag_map_size) |
last_frag * TX_DMA_LS0));
- WRITE_ONCE(txd->txd4, 0);
+ WRITE_ONCE(txd->txd4, fport);
tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
tx_buf = mtk_desc_to_tx_buf(ring, txd);
@@ -865,7 +860,7 @@
/* receive data */
skb = build_skb(data, ring->frag_size);
if (unlikely(!skb)) {
- put_page(virt_to_head_page(new_data));
+ skb_free_frag(new_data);
netdev->stats.rx_dropped++;
goto release_desc;
}
@@ -1506,10 +1501,7 @@
struct mtk_eth *eth = mac->hw;
phy_disconnect(mac->phy_dev);
- mtk_mdio_cleanup(eth);
mtk_irq_disable(eth, ~0);
- free_irq(eth->irq[1], dev);
- free_irq(eth->irq[2], dev);
}
static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
@@ -1813,6 +1805,7 @@
if (!eth)
return -ENOMEM;
+ eth->dev = &pdev->dev;
eth->base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(eth->base))
return PTR_ERR(eth->base);
@@ -1847,21 +1840,21 @@
return -ENXIO;
}
}
+ for (i = 0; i < ARRAY_SIZE(eth->clks); i++) {
+ eth->clks[i] = devm_clk_get(eth->dev,
+ mtk_clks_source_name[i]);
+ if (IS_ERR(eth->clks[i])) {
+ if (PTR_ERR(eth->clks[i]) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+ return -ENODEV;
+ }
+ }
- eth->clk_ethif = devm_clk_get(&pdev->dev, "ethif");
- eth->clk_esw = devm_clk_get(&pdev->dev, "esw");
- eth->clk_gp1 = devm_clk_get(&pdev->dev, "gp1");
- eth->clk_gp2 = devm_clk_get(&pdev->dev, "gp2");
- if (IS_ERR(eth->clk_esw) || IS_ERR(eth->clk_gp1) ||
- IS_ERR(eth->clk_gp2) || IS_ERR(eth->clk_ethif))
- return -ENODEV;
+ clk_prepare_enable(eth->clks[MTK_CLK_ETHIF]);
+ clk_prepare_enable(eth->clks[MTK_CLK_ESW]);
+ clk_prepare_enable(eth->clks[MTK_CLK_GP1]);
+ clk_prepare_enable(eth->clks[MTK_CLK_GP2]);
- clk_prepare_enable(eth->clk_ethif);
- clk_prepare_enable(eth->clk_esw);
- clk_prepare_enable(eth->clk_gp1);
- clk_prepare_enable(eth->clk_gp2);
-
- eth->dev = &pdev->dev;
eth->msg_enable = netif_msg_init(mtk_msg_level, MTK_DEFAULT_MSG_ENABLE);
INIT_WORK(ð->pending_work, mtk_pending_work);
@@ -1903,15 +1896,24 @@
static int mtk_remove(struct platform_device *pdev)
{
struct mtk_eth *eth = platform_get_drvdata(pdev);
+ int i;
- clk_disable_unprepare(eth->clk_ethif);
- clk_disable_unprepare(eth->clk_esw);
- clk_disable_unprepare(eth->clk_gp1);
- clk_disable_unprepare(eth->clk_gp2);
+ /* stop all devices to make sure that dma is properly shut down */
+ for (i = 0; i < MTK_MAC_COUNT; i++) {
+ if (!eth->netdev[i])
+ continue;
+ mtk_stop(eth->netdev[i]);
+ }
+
+ clk_disable_unprepare(eth->clks[MTK_CLK_ETHIF]);
+ clk_disable_unprepare(eth->clks[MTK_CLK_ESW]);
+ clk_disable_unprepare(eth->clks[MTK_CLK_GP1]);
+ clk_disable_unprepare(eth->clks[MTK_CLK_GP2]);
netif_napi_del(ð->tx_napi);
netif_napi_del(ð->rx_napi);
mtk_cleanup(eth);
+ mtk_mdio_cleanup(eth);
platform_set_drvdata(pdev, NULL);
return 0;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index f82e3ac..6e1ade7 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -290,6 +290,17 @@
MTK_TX_FLAGS_PAGE0 = 0x02,
};
+/* This enum allows us to identify how the clock is defined on the array of the
+ * clock in the order
+ */
+enum mtk_clks_map {
+ MTK_CLK_ETHIF,
+ MTK_CLK_ESW,
+ MTK_CLK_GP1,
+ MTK_CLK_GP2,
+ MTK_CLK_MAX
+};
+
/* struct mtk_tx_buf - This struct holds the pointers to the memory pointed at
* by the TX descriptor s
* @skb: The SKB pointer of the packet being sent
@@ -370,10 +381,7 @@
* @scratch_ring: Newer SoCs need memory for a second HW managed TX ring
* @phy_scratch_ring: physical address of scratch_ring
* @scratch_head: The scratch memory that scratch_ring points to.
- * @clk_ethif: The ethif clock
- * @clk_esw: The switch clock
- * @clk_gp1: The gmac1 clock
- * @clk_gp2: The gmac2 clock
+ * @clks: clock array for all clocks required
* @mii_bus: If there is a bus we need to create an instance for it
* @pending_work: The workqueue used to reset the dma ring
*/
@@ -400,10 +408,8 @@
struct mtk_tx_dma *scratch_ring;
dma_addr_t phy_scratch_ring;
void *scratch_head;
- struct clk *clk_ethif;
- struct clk *clk_esw;
- struct clk *clk_gp1;
- struct clk *clk_gp2;
+ struct clk *clks[MTK_CLK_MAX];
+
struct mii_bus *mii_bus;
struct work_struct pending_work;
};
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index 99c6bbd..b04760a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -94,7 +94,7 @@
*cap = true;
break;
case DCB_CAP_ATTR_DCBX:
- *cap = priv->cee_params.dcbx_cap;
+ *cap = priv->dcbx_cap;
break;
case DCB_CAP_ATTR_PFC_TCS:
*cap = 1 << mlx4_max_tc(priv->mdev->dev);
@@ -111,14 +111,14 @@
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- return priv->cee_params.dcb_cfg.pfc_state;
+ return priv->cee_config.pfc_state;
}
static void mlx4_en_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- priv->cee_params.dcb_cfg.pfc_state = state;
+ priv->cee_config.pfc_state = state;
}
static void mlx4_en_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
@@ -126,7 +126,7 @@
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- *setting = priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc;
+ *setting = priv->cee_config.dcb_pfc[priority];
}
static void mlx4_en_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
@@ -134,8 +134,8 @@
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc = setting;
- priv->cee_params.dcb_cfg.pfc_state = true;
+ priv->cee_config.dcb_pfc[priority] = setting;
+ priv->cee_config.pfc_state = true;
}
static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
@@ -157,13 +157,11 @@
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
struct mlx4_en_dev *mdev = priv->mdev;
- struct mlx4_en_cee_config *dcb_cfg = &priv->cee_params.dcb_cfg;
- int err = 0;
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
- return -EINVAL;
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ return 1;
- if (dcb_cfg->pfc_state) {
+ if (priv->cee_config.pfc_state) {
int tc;
priv->prof->rx_pause = 0;
@@ -171,7 +169,7 @@
for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
u8 tc_mask = 1 << tc;
- switch (dcb_cfg->tc_config[tc].dcb_pfc) {
+ switch (priv->cee_config.dcb_pfc[tc]) {
case pfc_disabled:
priv->prof->tx_ppp &= ~tc_mask;
priv->prof->rx_ppp &= ~tc_mask;
@@ -199,15 +197,17 @@
en_dbg(DRV, priv, "Set pfc off\n");
}
- err = mlx4_SET_PORT_general(mdev->dev, priv->port,
- priv->rx_skb_size + ETH_FCS_LEN,
- priv->prof->tx_pause,
- priv->prof->tx_ppp,
- priv->prof->rx_pause,
- priv->prof->rx_ppp);
- if (err)
+ if (mlx4_SET_PORT_general(mdev->dev, priv->port,
+ priv->rx_skb_size + ETH_FCS_LEN,
+ priv->prof->tx_pause,
+ priv->prof->tx_ppp,
+ priv->prof->rx_pause,
+ priv->prof->rx_ppp)) {
en_err(priv, "Failed setting pause params\n");
- return err;
+ return 1;
+ }
+
+ return 0;
}
static u8 mlx4_en_dcbnl_get_state(struct net_device *dev)
@@ -225,7 +225,7 @@
struct mlx4_en_priv *priv = netdev_priv(dev);
int num_tcs = 0;
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
return 1;
if (!!(state) == !!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
@@ -238,7 +238,10 @@
priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
}
- return mlx4_en_setup_tc(dev, num_tcs);
+ if (mlx4_en_setup_tc(dev, num_tcs))
+ return 1;
+
+ return 0;
}
/* On success returns a non-zero 802.1p user priority bitmap
@@ -252,7 +255,7 @@
.selector = idtype,
.protocol = id,
};
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
return 0;
return dcb_getapp(netdev, &app);
@@ -264,7 +267,7 @@
struct mlx4_en_priv *priv = netdev_priv(netdev);
struct dcb_app app;
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
return -EINVAL;
memset(&app, 0, sizeof(struct dcb_app));
@@ -433,7 +436,7 @@
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- return priv->cee_params.dcbx_cap;
+ return priv->dcbx_cap;
}
static u8 mlx4_en_dcbnl_setdcbx(struct net_device *dev, u8 mode)
@@ -442,7 +445,7 @@
struct ieee_ets ets = {0};
struct ieee_pfc pfc = {0};
- if (mode == priv->cee_params.dcbx_cap)
+ if (mode == priv->dcbx_cap)
return 0;
if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
@@ -451,7 +454,7 @@
!(mode & DCB_CAP_DCBX_HOST))
goto err;
- priv->cee_params.dcbx_cap = mode;
+ priv->dcbx_cap = mode;
ets.ets_cap = IEEE_8021QAZ_MAX_TCS;
pfc.pfc_cap = IEEE_8021QAZ_MAX_TCS;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 4198e9b..fedb829 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -71,10 +71,11 @@
#ifdef CONFIG_MLX4_EN_DCB
if (!mlx4_is_slave(priv->mdev->dev)) {
if (up) {
- priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+ if (priv->dcbx_cap)
+ priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
} else {
priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
- priv->cee_params.dcb_cfg.pfc_state = false;
+ priv->cee_config.pfc_state = false;
}
}
#endif /* CONFIG_MLX4_EN_DCB */
@@ -3048,9 +3049,6 @@
struct mlx4_en_priv *priv;
int i;
int err;
-#ifdef CONFIG_MLX4_EN_DCB
- struct tc_configuration *tc;
-#endif
dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
MAX_TX_RINGS, MAX_RX_RINGS);
@@ -3117,16 +3115,13 @@
priv->msg_enable = MLX4_EN_MSG_LEVEL;
#ifdef CONFIG_MLX4_EN_DCB
if (!mlx4_is_slave(priv->mdev->dev)) {
- priv->cee_params.dcbx_cap = DCB_CAP_DCBX_VER_CEE |
- DCB_CAP_DCBX_HOST |
- DCB_CAP_DCBX_VER_IEEE;
+ priv->dcbx_cap = DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_HOST |
+ DCB_CAP_DCBX_VER_IEEE;
priv->flags |= MLX4_EN_DCB_ENABLED;
- priv->cee_params.dcb_cfg.pfc_state = false;
+ priv->cee_config.pfc_state = false;
- for (i = 0; i < MLX4_EN_NUM_UP; i++) {
- tc = &priv->cee_params.dcb_cfg.tc_config[i];
- tc->dcb_pfc = pfc_disabled;
- }
+ for (i = 0; i < MLX4_EN_NUM_UP; i++)
+ priv->cee_config.dcb_pfc[i] = pfc_disabled;
if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) {
dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 9df87ca..e2509bb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -818,7 +818,7 @@
real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
&inline_ok, &fragptr);
if (unlikely(!real_size))
- goto tx_drop;
+ goto tx_drop_count;
/* Align descriptor to TXBB size */
desc_size = ALIGN(real_size, TXBB_SIZE);
@@ -826,7 +826,7 @@
if (unlikely(nr_txbb > MAX_DESC_TXBBS)) {
if (netif_msg_tx_err(priv))
en_warn(priv, "Oversized header or SG list\n");
- goto tx_drop;
+ goto tx_drop_count;
}
bf_ok = ring->bf_enabled;
@@ -1071,9 +1071,10 @@
PCI_DMA_TODEVICE);
}
+tx_drop_count:
+ ring->tx_dropped++;
tx_drop:
dev_kfree_skb_any(skb);
- ring->tx_dropped++;
return NETDEV_TX_OK;
}
@@ -1106,7 +1107,7 @@
goto tx_drop;
if (mlx4_en_is_tx_ring_full(ring))
- goto tx_drop;
+ goto tx_drop_count;
/* fetch ring->cons far ahead before needing it to avoid stall */
ring_cons = READ_ONCE(ring->cons);
@@ -1176,7 +1177,8 @@
return NETDEV_TX_OK;
-tx_drop:
+tx_drop_count:
ring->tx_dropped++;
+tx_drop:
return NETDEV_TX_BUSY;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 2c2913d..9099dbd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -482,20 +482,10 @@
pfc_enabled_rx
};
-struct tc_configuration {
- enum dcb_pfc_type dcb_pfc;
-};
-
struct mlx4_en_cee_config {
bool pfc_state;
- struct tc_configuration tc_config[MLX4_EN_NUM_UP];
+ enum dcb_pfc_type dcb_pfc[MLX4_EN_NUM_UP];
};
-
-struct mlx4_en_cee_params {
- u8 dcbx_cap;
- struct mlx4_en_cee_config dcb_cfg;
-};
-
#endif
struct ethtool_flow_id {
@@ -624,7 +614,8 @@
struct ieee_ets ets;
u16 maxrate[IEEE_8021QAZ_MAX_TCS];
enum dcbnl_cndd_states cndd_state[IEEE_8021QAZ_MAX_TCS];
- struct mlx4_en_cee_params cee_params;
+ struct mlx4_en_cee_config cee_config;
+ u8 dcbx_cap;
#endif
#ifdef CONFIG_RFS_ACCEL
spinlock_t filters_lock;
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 3d2095e..c5b2064 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -52,7 +52,7 @@
#define MLX4_FLAG_V_IGNORE_FCS_MASK 0x2
#define MLX4_IGNORE_FCS_MASK 0x1
-#define MLNX4_TX_MAX_NUMBER 8
+#define MLX4_TC_MAX_NUMBER 8
void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table)
{
@@ -2022,7 +2022,7 @@
u8 num_tc = dev->caps.max_tc_eth;
if (!num_tc)
- num_tc = MLNX4_TX_MAX_NUMBER;
+ num_tc = MLX4_TC_MAX_NUMBER;
return num_tc;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index d0cf8fa..7a346bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -331,7 +331,7 @@
if (mlx5e_query_global_pause_combined(priv)) {
for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
- pport_per_prio_pfc_stats_desc, 0);
+ pport_per_prio_pfc_stats_desc, i);
}
}
@@ -659,9 +659,10 @@
static void ptys2ethtool_supported_link(unsigned long *supported_modes,
u32 eth_proto_cap)
{
+ unsigned long proto_cap = eth_proto_cap;
int proto;
- for_each_set_bit(proto, (unsigned long *)ð_proto_cap, MLX5E_LINK_MODES_NUMBER)
+ for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
bitmap_or(supported_modes, supported_modes,
ptys2ethtool_table[proto].supported,
__ETHTOOL_LINK_MODE_MASK_NBITS);
@@ -670,9 +671,10 @@
static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
u32 eth_proto_cap)
{
+ unsigned long proto_cap = eth_proto_cap;
int proto;
- for_each_set_bit(proto, (unsigned long *)ð_proto_cap, MLX5E_LINK_MODES_NUMBER)
+ for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
bitmap_or(advertising_modes, advertising_modes,
ptys2ethtool_table[proto].advertised,
__ETHTOOL_LINK_MODE_MASK_NBITS);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index b6f8ebb..e7c969d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -637,24 +637,32 @@
static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
u32 cqe_bcnt)
{
- struct ethhdr *eth = (struct ethhdr *)(skb->data);
- struct iphdr *ipv4 = (struct iphdr *)(skb->data + ETH_HLEN);
- struct ipv6hdr *ipv6 = (struct ipv6hdr *)(skb->data + ETH_HLEN);
+ struct ethhdr *eth = (struct ethhdr *)(skb->data);
+ struct iphdr *ipv4;
+ struct ipv6hdr *ipv6;
struct tcphdr *tcp;
+ int network_depth = 0;
+ __be16 proto;
+ u16 tot_len;
u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
int tcp_ack = ((CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA == l4_hdr_type) ||
(CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA == l4_hdr_type));
- u16 tot_len = cqe_bcnt - ETH_HLEN;
+ skb->mac_len = ETH_HLEN;
+ proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
- if (eth->h_proto == htons(ETH_P_IP)) {
- tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+ ipv4 = (struct iphdr *)(skb->data + network_depth);
+ ipv6 = (struct ipv6hdr *)(skb->data + network_depth);
+ tot_len = cqe_bcnt - network_depth;
+
+ if (proto == htons(ETH_P_IP)) {
+ tcp = (struct tcphdr *)(skb->data + network_depth +
sizeof(struct iphdr));
ipv6 = NULL;
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
} else {
- tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+ tcp = (struct tcphdr *)(skb->data + network_depth +
sizeof(struct ipv6hdr));
ipv4 = NULL;
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 988eca9..eb0e725 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -356,6 +356,7 @@
sq->stats.stopped++;
}
+ sq->stats.xmit_more += skb->xmit_more;
if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) {
int bf_sz = 0;
@@ -375,7 +376,6 @@
sq->stats.packets++;
sq->stats.bytes += num_bytes;
- sq->stats.xmit_more += skb->xmit_more;
return NETDEV_TX_OK;
dma_unmap_wqe_err:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 7291f2c..d48873b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -56,6 +56,7 @@
#include <generated/utsrelease.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_mirred.h>
+#include <net/netevent.h>
#include "spectrum.h"
#include "core.h"
@@ -2105,6 +2106,13 @@
dev->netdev_ops = &mlxsw_sp_port_netdev_ops;
dev->ethtool_ops = &mlxsw_sp_port_ethtool_ops;
+ err = mlxsw_sp_port_swid_set(mlxsw_sp_port, 0);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n",
+ mlxsw_sp_port->local_port);
+ goto err_port_swid_set;
+ }
+
err = mlxsw_sp_port_dev_addr_init(mlxsw_sp_port);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unable to init port mac address\n",
@@ -2130,13 +2138,6 @@
goto err_port_system_port_mapping_set;
}
- err = mlxsw_sp_port_swid_set(mlxsw_sp_port, 0);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n",
- mlxsw_sp_port->local_port);
- goto err_port_swid_set;
- }
-
err = mlxsw_sp_port_speed_by_width_set(mlxsw_sp_port, width);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to enable speeds\n",
@@ -2218,10 +2219,10 @@
err_port_admin_status_set:
err_port_mtu_set:
err_port_speed_by_width_set:
- mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
-err_port_swid_set:
err_port_system_port_mapping_set:
err_dev_addr_init:
+ mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
+err_port_swid_set:
free_percpu(mlxsw_sp_port->pcpu_stats);
err_alloc_stats:
kfree(mlxsw_sp_port->untagged_vlans);
@@ -4541,18 +4542,26 @@
.priority = 10, /* Must be called before FIB notifier block */
};
+static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = {
+ .notifier_call = mlxsw_sp_router_netevent_event,
+};
+
static int __init mlxsw_sp_module_init(void)
{
int err;
register_netdevice_notifier(&mlxsw_sp_netdevice_nb);
register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
+ register_netevent_notifier(&mlxsw_sp_router_netevent_nb);
+
err = mlxsw_core_driver_register(&mlxsw_sp_driver);
if (err)
goto err_core_driver_register;
return 0;
err_core_driver_register:
+ unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
+ unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb);
return err;
}
@@ -4560,6 +4569,7 @@
static void __exit mlxsw_sp_module_exit(void)
{
mlxsw_core_driver_unregister(&mlxsw_sp_driver);
+ unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index ab3feb8..ac48abe 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -587,6 +587,8 @@
struct neighbour *n);
void mlxsw_sp_router_neigh_destroy(struct net_device *dev,
struct neighbour *n);
+int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
+ unsigned long event, void *ptr);
int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count);
void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 917ddd1..3f5c51d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -107,6 +107,7 @@
}
struct mlxsw_sp_fib_key {
+ struct net_device *dev;
unsigned char addr[sizeof(struct in6_addr)];
unsigned char prefix_len;
};
@@ -123,7 +124,7 @@
struct rhash_head ht_node;
struct mlxsw_sp_fib_key key;
enum mlxsw_sp_fib_entry_type type;
- u8 added:1;
+ unsigned int ref_count;
u16 rif; /* used for action local */
struct mlxsw_sp_vr *vr;
struct list_head nexthop_group_node;
@@ -171,13 +172,15 @@
static struct mlxsw_sp_fib_entry *
mlxsw_sp_fib_entry_create(struct mlxsw_sp_fib *fib, const void *addr,
- size_t addr_len, unsigned char prefix_len)
+ size_t addr_len, unsigned char prefix_len,
+ struct net_device *dev)
{
struct mlxsw_sp_fib_entry *fib_entry;
fib_entry = kzalloc(sizeof(*fib_entry), GFP_KERNEL);
if (!fib_entry)
return NULL;
+ fib_entry->key.dev = dev;
memcpy(fib_entry->key.addr, addr, addr_len);
fib_entry->key.prefix_len = prefix_len;
return fib_entry;
@@ -190,10 +193,13 @@
static struct mlxsw_sp_fib_entry *
mlxsw_sp_fib_entry_lookup(struct mlxsw_sp_fib *fib, const void *addr,
- size_t addr_len, unsigned char prefix_len)
+ size_t addr_len, unsigned char prefix_len,
+ struct net_device *dev)
{
- struct mlxsw_sp_fib_key key = {{ 0 } };
+ struct mlxsw_sp_fib_key key;
+ memset(&key, 0, sizeof(key));
+ key.dev = dev;
memcpy(key.addr, addr, addr_len);
key.prefix_len = prefix_len;
return rhashtable_lookup_fast(&fib->ht, &key, mlxsw_sp_fib_ht_params);
@@ -938,8 +944,8 @@
mlxsw_sp_port_dev_put(mlxsw_sp_port);
}
-static int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
+int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
{
struct mlxsw_sp_neigh_entry *neigh_entry;
struct mlxsw_sp_port *mlxsw_sp_port;
@@ -1009,10 +1015,6 @@
return NOTIFY_DONE;
}
-static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = {
- .notifier_call = mlxsw_sp_router_netevent_event,
-};
-
static int mlxsw_sp_neigh_init(struct mlxsw_sp *mlxsw_sp)
{
int err;
@@ -1027,10 +1029,6 @@
*/
mlxsw_sp_router_neighs_update_interval_init(mlxsw_sp);
- err = register_netevent_notifier(&mlxsw_sp_router_netevent_nb);
- if (err)
- goto err_register_netevent_notifier;
-
/* Create the delayed works for the activity_update */
INIT_DELAYED_WORK(&mlxsw_sp->router.neighs_update.dw,
mlxsw_sp_router_neighs_update_work);
@@ -1039,17 +1037,12 @@
mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw, 0);
mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw, 0);
return 0;
-
-err_register_netevent_notifier:
- rhashtable_destroy(&mlxsw_sp->router.neigh_ht);
- return err;
}
static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp)
{
cancel_delayed_work_sync(&mlxsw_sp->router.neighs_update.dw);
cancel_delayed_work_sync(&mlxsw_sp->router.nexthop_probe_dw);
- unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
rhashtable_destroy(&mlxsw_sp->router.neigh_ht);
}
@@ -1524,7 +1517,14 @@
return err;
mlxsw_sp_lpm_init(mlxsw_sp);
mlxsw_sp_vrs_init(mlxsw_sp);
- return mlxsw_sp_neigh_init(mlxsw_sp);
+ err = mlxsw_sp_neigh_init(mlxsw_sp);
+ if (err)
+ goto err_neigh_init;
+ return 0;
+
+err_neigh_init:
+ __mlxsw_sp_router_fini(mlxsw_sp);
+ return err;
}
void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
@@ -1626,11 +1626,8 @@
static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry)
{
- enum mlxsw_reg_ralue_op op;
-
- op = !fib_entry->added ? MLXSW_REG_RALUE_OP_WRITE_WRITE :
- MLXSW_REG_RALUE_OP_WRITE_UPDATE;
- return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op);
+ return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry,
+ MLXSW_REG_RALUE_OP_WRITE_WRITE);
}
static int mlxsw_sp_fib_entry_del(struct mlxsw_sp *mlxsw_sp,
@@ -1695,6 +1692,79 @@
mlxsw_sp_nexthop_group_put(mlxsw_sp, fib_entry);
}
+static struct mlxsw_sp_fib_entry *
+mlxsw_sp_fib_entry_get(struct mlxsw_sp *mlxsw_sp,
+ const struct switchdev_obj_ipv4_fib *fib4)
+{
+ struct mlxsw_sp_fib_entry *fib_entry;
+ struct fib_info *fi = fib4->fi;
+ struct mlxsw_sp_vr *vr;
+ int err;
+
+ vr = mlxsw_sp_vr_get(mlxsw_sp, fib4->dst_len, fib4->tb_id,
+ MLXSW_SP_L3_PROTO_IPV4);
+ if (IS_ERR(vr))
+ return ERR_CAST(vr);
+
+ fib_entry = mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst,
+ sizeof(fib4->dst),
+ fib4->dst_len, fi->fib_dev);
+ if (fib_entry) {
+ /* Already exists, just take a reference */
+ fib_entry->ref_count++;
+ return fib_entry;
+ }
+ fib_entry = mlxsw_sp_fib_entry_create(vr->fib, &fib4->dst,
+ sizeof(fib4->dst),
+ fib4->dst_len, fi->fib_dev);
+ if (!fib_entry) {
+ err = -ENOMEM;
+ goto err_fib_entry_create;
+ }
+ fib_entry->vr = vr;
+ fib_entry->ref_count = 1;
+
+ err = mlxsw_sp_router_fib4_entry_init(mlxsw_sp, fib4, fib_entry);
+ if (err)
+ goto err_fib4_entry_init;
+
+ return fib_entry;
+
+err_fib4_entry_init:
+ mlxsw_sp_fib_entry_destroy(fib_entry);
+err_fib_entry_create:
+ mlxsw_sp_vr_put(mlxsw_sp, vr);
+
+ return ERR_PTR(err);
+}
+
+static struct mlxsw_sp_fib_entry *
+mlxsw_sp_fib_entry_find(struct mlxsw_sp *mlxsw_sp,
+ const struct switchdev_obj_ipv4_fib *fib4)
+{
+ struct mlxsw_sp_vr *vr;
+
+ vr = mlxsw_sp_vr_find(mlxsw_sp, fib4->tb_id, MLXSW_SP_L3_PROTO_IPV4);
+ if (!vr)
+ return NULL;
+
+ return mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst,
+ sizeof(fib4->dst), fib4->dst_len,
+ fib4->fi->fib_dev);
+}
+
+void mlxsw_sp_fib_entry_put(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
+{
+ struct mlxsw_sp_vr *vr = fib_entry->vr;
+
+ if (--fib_entry->ref_count == 0) {
+ mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
+ mlxsw_sp_fib_entry_destroy(fib_entry);
+ }
+ mlxsw_sp_vr_put(mlxsw_sp, vr);
+}
+
static int
mlxsw_sp_router_fib4_add_prepare(struct mlxsw_sp_port *mlxsw_sp_port,
const struct switchdev_obj_ipv4_fib *fib4,
@@ -1703,25 +1773,11 @@
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_router_fib4_add_info *info;
struct mlxsw_sp_fib_entry *fib_entry;
- struct mlxsw_sp_vr *vr;
int err;
- vr = mlxsw_sp_vr_get(mlxsw_sp, fib4->dst_len, fib4->tb_id,
- MLXSW_SP_L3_PROTO_IPV4);
- if (IS_ERR(vr))
- return PTR_ERR(vr);
-
- fib_entry = mlxsw_sp_fib_entry_create(vr->fib, &fib4->dst,
- sizeof(fib4->dst), fib4->dst_len);
- if (!fib_entry) {
- err = -ENOMEM;
- goto err_fib_entry_create;
- }
- fib_entry->vr = vr;
-
- err = mlxsw_sp_router_fib4_entry_init(mlxsw_sp, fib4, fib_entry);
- if (err)
- goto err_fib4_entry_init;
+ fib_entry = mlxsw_sp_fib_entry_get(mlxsw_sp, fib4);
+ if (IS_ERR(fib_entry))
+ return PTR_ERR(fib_entry);
info = kmalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
@@ -1736,11 +1792,7 @@
return 0;
err_alloc_info:
- mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
-err_fib4_entry_init:
- mlxsw_sp_fib_entry_destroy(fib_entry);
-err_fib_entry_create:
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+ mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
return err;
}
@@ -1759,11 +1811,14 @@
fib_entry = info->fib_entry;
kfree(info);
+ if (fib_entry->ref_count != 1)
+ return 0;
+
vr = fib_entry->vr;
- err = mlxsw_sp_fib_entry_insert(fib_entry->vr->fib, fib_entry);
+ err = mlxsw_sp_fib_entry_insert(vr->fib, fib_entry);
if (err)
goto err_fib_entry_insert;
- err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry);
+ err = mlxsw_sp_fib_entry_update(mlxsw_sp_port->mlxsw_sp, fib_entry);
if (err)
goto err_fib_entry_add;
return 0;
@@ -1771,9 +1826,7 @@
err_fib_entry_add:
mlxsw_sp_fib_entry_remove(vr->fib, fib_entry);
err_fib_entry_insert:
- mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
- mlxsw_sp_fib_entry_destroy(fib_entry);
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+ mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
return err;
}
@@ -1793,23 +1846,18 @@
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_fib_entry *fib_entry;
- struct mlxsw_sp_vr *vr;
- vr = mlxsw_sp_vr_find(mlxsw_sp, fib4->tb_id, MLXSW_SP_L3_PROTO_IPV4);
- if (!vr) {
- dev_warn(mlxsw_sp->bus_info->dev, "Failed to find virtual router for FIB4 entry being removed.\n");
- return -ENOENT;
- }
- fib_entry = mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst,
- sizeof(fib4->dst), fib4->dst_len);
+ fib_entry = mlxsw_sp_fib_entry_find(mlxsw_sp, fib4);
if (!fib_entry) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to find FIB4 entry being removed.\n");
return -ENOENT;
}
- mlxsw_sp_fib_entry_del(mlxsw_sp_port->mlxsw_sp, fib_entry);
- mlxsw_sp_fib_entry_remove(vr->fib, fib_entry);
- mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
- mlxsw_sp_fib_entry_destroy(fib_entry);
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+
+ if (fib_entry->ref_count == 1) {
+ mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry);
+ mlxsw_sp_fib_entry_remove(fib_entry->vr->fib, fib_entry);
+ }
+
+ mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index d1b59cd..7b654c51 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -167,8 +167,8 @@
}
static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port,
- u16 idx_begin, u16 idx_end, bool set,
- bool only_uc)
+ u16 idx_begin, u16 idx_end, bool uc_set,
+ bool bm_set)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
u16 local_port = mlxsw_sp_port->local_port;
@@ -187,28 +187,22 @@
return -ENOMEM;
mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, idx_begin,
- table_type, range, local_port, set);
+ table_type, range, local_port, uc_set);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
if (err)
goto buffer_out;
- /* Flooding control allows one to decide whether a given port will
- * flood unicast traffic for which there is no FDB entry.
- */
- if (only_uc)
- goto buffer_out;
-
mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, idx_begin,
- table_type, range, local_port, set);
+ table_type, range, local_port, bm_set);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
if (err)
goto err_flood_bm_set;
- else
- goto buffer_out;
+
+ goto buffer_out;
err_flood_bm_set:
mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, idx_begin,
- table_type, range, local_port, !set);
+ table_type, range, local_port, !uc_set);
mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
buffer_out:
kfree(sftr_pl);
@@ -257,8 +251,7 @@
* the start of the vFIDs range.
*/
vfid = mlxsw_sp_fid_to_vfid(fid);
- return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set,
- false);
+ return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set, set);
}
static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -460,6 +453,9 @@
{
struct mlxsw_sp_fid *f;
+ if (test_bit(fid, mlxsw_sp_port->active_vlans))
+ return 0;
+
f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid);
if (!f) {
f = mlxsw_sp_fid_create(mlxsw_sp_port->mlxsw_sp, fid);
@@ -517,7 +513,7 @@
}
err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end,
- true, false);
+ mlxsw_sp_port->uc_flood, true);
if (err)
goto err_port_flood_set;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 88678c1..252e492 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -41,7 +41,6 @@
* Chris Telfer <chris.telfer@netronome.com>
*/
-#include <linux/version.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -1441,10 +1440,6 @@
nfp_net_set_hash(nn->netdev, skb, rxd);
- /* Pad small frames to minimum */
- if (skb_put_padto(skb, 60))
- break;
-
/* Stats update */
u64_stats_update_begin(&r_vec->rx_sync);
r_vec->rx_pkts++;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 7d7933d0..4c98972 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -40,7 +40,6 @@
* Brad Petrus <brad.petrus@netronome.com>
*/
-#include <linux/version.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index 37abef0..f7062cb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -38,7 +38,6 @@
* Rolf Neugebauer <rolf.neugebauer@netronome.com>
*/
-#include <linux/version.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -134,7 +133,7 @@
}
nfp_net_get_fw_version(&fw_ver, ctrl_bar);
- if (fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) {
+ if (fw_ver.resv || fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) {
dev_err(&pdev->dev, "Unknown Firmware ABI %d.%d.%d.%d\n",
fw_ver.resv, fw_ver.class, fw_ver.major, fw_ver.minor);
err = -EINVAL;
@@ -142,9 +141,7 @@
}
/* Determine stride */
- if (nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0, 0) ||
- nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0, 1) ||
- nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0x12, 0x48)) {
+ if (nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0, 1)) {
stride = 2;
tx_bar_no = NFP_NET_Q0_BAR;
rx_bar_no = NFP_NET_Q1_BAR;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 226cb08..3656d2f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -19,6 +19,7 @@
#include "qed_dcbx.h"
#include "qed_hsi.h"
#include "qed_sp.h"
+#include "qed_sriov.h"
#ifdef CONFIG_DCB
#include <linux/qed/qed_eth_if.h>
#endif
@@ -945,6 +946,9 @@
struct qed_ptt *p_ptt;
int rc;
+ if (IS_VF(p_hwfn->cdev))
+ return -EINVAL;
+
p_ptt = qed_ptt_acquire(p_hwfn);
if (!p_ptt)
return -EBUSY;
@@ -984,6 +988,7 @@
if (p_params->pfc.prio[i])
pfc_map |= BIT(i);
+ *pfc &= ~DCBX_PFC_PRI_EN_BITMAP_MASK;
*pfc |= (pfc_map << DCBX_PFC_PRI_EN_BITMAP_SHIFT);
DP_VERBOSE(p_hwfn, QED_MSG_DCB, "pfc = 0x%x\n", *pfc);
@@ -1058,24 +1063,33 @@
for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) {
entry = &p_app->app_pri_tbl[i].entry;
+ *entry = 0;
if (ieee) {
- *entry &= ~DCBX_APP_SF_IEEE_MASK;
+ *entry &= ~(DCBX_APP_SF_IEEE_MASK | DCBX_APP_SF_MASK);
switch (p_params->app_entry[i].sf_ieee) {
case QED_DCBX_SF_IEEE_ETHTYPE:
*entry |= ((u32)DCBX_APP_SF_IEEE_ETHTYPE <<
DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_ETHTYPE <<
+ DCBX_APP_SF_SHIFT);
break;
case QED_DCBX_SF_IEEE_TCP_PORT:
*entry |= ((u32)DCBX_APP_SF_IEEE_TCP_PORT <<
DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_PORT <<
+ DCBX_APP_SF_SHIFT);
break;
case QED_DCBX_SF_IEEE_UDP_PORT:
*entry |= ((u32)DCBX_APP_SF_IEEE_UDP_PORT <<
DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_PORT <<
+ DCBX_APP_SF_SHIFT);
break;
case QED_DCBX_SF_IEEE_TCP_UDP_PORT:
*entry |= ((u32)DCBX_APP_SF_IEEE_TCP_UDP_PORT <<
DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_PORT <<
+ DCBX_APP_SF_SHIFT);
break;
}
} else {
@@ -1175,7 +1189,7 @@
return 0;
}
- dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+ dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL);
if (!dcbx_info) {
DP_ERR(p_hwfn, "Failed to allocate struct qed_dcbx_info\n");
return -ENOMEM;
@@ -1212,7 +1226,7 @@
{
struct qed_dcbx_get *dcbx_info;
- dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+ dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL);
if (!dcbx_info) {
DP_ERR(hwfn->cdev, "Failed to allocate memory for dcbx_info\n");
return NULL;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index a6eb6af..9544e4c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2520,7 +2520,8 @@
edev->ops->register_ops(cdev, &qede_ll_ops, edev);
#ifdef CONFIG_DCB
- qede_set_dcbnl_ops(edev->ndev);
+ if (!IS_VF(edev))
+ qede_set_dcbnl_ops(edev->ndev);
#endif
INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 799d58d..054e795 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -201,9 +201,14 @@
[ARSTR] = 0x0000,
[TSU_CTRST] = 0x0004,
+ [TSU_FWSLC] = 0x0038,
[TSU_VTAG0] = 0x0058,
[TSU_ADSBSY] = 0x0060,
[TSU_TEN] = 0x0064,
+ [TSU_POST1] = 0x0070,
+ [TSU_POST2] = 0x0074,
+ [TSU_POST3] = 0x0078,
+ [TSU_POST4] = 0x007c,
[TSU_ADRH0] = 0x0100,
[TXNLCR0] = 0x0080,
@@ -2786,6 +2791,8 @@
{
if (sh_eth_is_rz_fast_ether(mdp)) {
sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */
+ sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL,
+ TSU_FWSLC); /* Enable POST registers */
return;
}
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index e17671c..ea84654 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -470,7 +470,9 @@
#endif
#if ! SMC_CAN_USE_8BIT
+#undef SMC_inb
#define SMC_inb(ioaddr, reg) ({ BUG(); 0; })
+#undef SMC_outb
#define SMC_outb(x, ioaddr, reg) BUG()
#define SMC_insb(a, r, p, l) BUG()
#define SMC_outsb(a, r, p, l) BUG()
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index ca31345..4f8910b 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1099,15 +1099,8 @@
goto err_out_free_bus_2;
}
- if (smsc911x_mii_probe(dev) < 0) {
- SMSC_WARN(pdata, probe, "Error registering mii bus");
- goto err_out_unregister_bus_3;
- }
-
return 0;
-err_out_unregister_bus_3:
- mdiobus_unregister(pdata->mii_bus);
err_out_free_bus_2:
mdiobus_free(pdata->mii_bus);
err_out_1:
@@ -1514,23 +1507,90 @@
smsc911x_reg_write(pdata, INT_STS, 0xFFFFFFFF);
}
+static irqreturn_t smsc911x_irqhandler(int irq, void *dev_id)
+{
+ struct net_device *dev = dev_id;
+ struct smsc911x_data *pdata = netdev_priv(dev);
+ u32 intsts = smsc911x_reg_read(pdata, INT_STS);
+ u32 inten = smsc911x_reg_read(pdata, INT_EN);
+ int serviced = IRQ_NONE;
+ u32 temp;
+
+ if (unlikely(intsts & inten & INT_STS_SW_INT_)) {
+ temp = smsc911x_reg_read(pdata, INT_EN);
+ temp &= (~INT_EN_SW_INT_EN_);
+ smsc911x_reg_write(pdata, INT_EN, temp);
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_SW_INT_);
+ pdata->software_irq_signal = 1;
+ smp_wmb();
+ serviced = IRQ_HANDLED;
+ }
+
+ if (unlikely(intsts & inten & INT_STS_RXSTOP_INT_)) {
+ /* Called when there is a multicast update scheduled and
+ * it is now safe to complete the update */
+ SMSC_TRACE(pdata, intr, "RX Stop interrupt");
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_RXSTOP_INT_);
+ if (pdata->multicast_update_pending)
+ smsc911x_rx_multicast_update_workaround(pdata);
+ serviced = IRQ_HANDLED;
+ }
+
+ if (intsts & inten & INT_STS_TDFA_) {
+ temp = smsc911x_reg_read(pdata, FIFO_INT);
+ temp |= FIFO_INT_TX_AVAIL_LEVEL_;
+ smsc911x_reg_write(pdata, FIFO_INT, temp);
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_TDFA_);
+ netif_wake_queue(dev);
+ serviced = IRQ_HANDLED;
+ }
+
+ if (unlikely(intsts & inten & INT_STS_RXE_)) {
+ SMSC_TRACE(pdata, intr, "RX Error interrupt");
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_RXE_);
+ serviced = IRQ_HANDLED;
+ }
+
+ if (likely(intsts & inten & INT_STS_RSFL_)) {
+ if (likely(napi_schedule_prep(&pdata->napi))) {
+ /* Disable Rx interrupts */
+ temp = smsc911x_reg_read(pdata, INT_EN);
+ temp &= (~INT_EN_RSFL_EN_);
+ smsc911x_reg_write(pdata, INT_EN, temp);
+ /* Schedule a NAPI poll */
+ __napi_schedule(&pdata->napi);
+ } else {
+ SMSC_WARN(pdata, rx_err, "napi_schedule_prep failed");
+ }
+ serviced = IRQ_HANDLED;
+ }
+
+ return serviced;
+}
+
static int smsc911x_open(struct net_device *dev)
{
struct smsc911x_data *pdata = netdev_priv(dev);
unsigned int timeout;
unsigned int temp;
unsigned int intcfg;
+ int retval;
+ int irq_flags;
- /* if the phy is not yet registered, retry later*/
+ /* find and start the given phy */
if (!dev->phydev) {
- SMSC_WARN(pdata, hw, "phy_dev is NULL");
- return -EAGAIN;
+ retval = smsc911x_mii_probe(dev);
+ if (retval < 0) {
+ SMSC_WARN(pdata, probe, "Error starting phy");
+ goto out;
+ }
}
/* Reset the LAN911x */
- if (smsc911x_soft_reset(pdata)) {
+ retval = smsc911x_soft_reset(pdata);
+ if (retval) {
SMSC_WARN(pdata, hw, "soft reset failed");
- return -EIO;
+ goto mii_free_out;
}
smsc911x_reg_write(pdata, HW_CFG, 0x00050000);
@@ -1586,6 +1646,15 @@
pdata->software_irq_signal = 0;
smp_wmb();
+ irq_flags = irq_get_trigger_type(dev->irq);
+ retval = request_irq(dev->irq, smsc911x_irqhandler,
+ irq_flags | IRQF_SHARED, dev->name, dev);
+ if (retval) {
+ SMSC_WARN(pdata, probe,
+ "Unable to claim requested irq: %d", dev->irq);
+ goto mii_free_out;
+ }
+
temp = smsc911x_reg_read(pdata, INT_EN);
temp |= INT_EN_SW_INT_EN_;
smsc911x_reg_write(pdata, INT_EN, temp);
@@ -1600,7 +1669,8 @@
if (!pdata->software_irq_signal) {
netdev_warn(dev, "ISR failed signaling test (IRQ %d)\n",
dev->irq);
- return -ENODEV;
+ retval = -ENODEV;
+ goto irq_stop_out;
}
SMSC_TRACE(pdata, ifup, "IRQ handler passed test using IRQ %d",
dev->irq);
@@ -1646,6 +1716,14 @@
netif_start_queue(dev);
return 0;
+
+irq_stop_out:
+ free_irq(dev->irq, dev);
+mii_free_out:
+ phy_disconnect(dev->phydev);
+ dev->phydev = NULL;
+out:
+ return retval;
}
/* Entry point for stopping the interface */
@@ -1667,9 +1745,15 @@
dev->stats.rx_dropped += smsc911x_reg_read(pdata, RX_DROP);
smsc911x_tx_update_txcounters(dev);
+ free_irq(dev->irq, dev);
+
/* Bring the PHY down */
- if (dev->phydev)
+ if (dev->phydev) {
phy_stop(dev->phydev);
+ phy_disconnect(dev->phydev);
+ dev->phydev = NULL;
+ }
+ netif_carrier_off(dev);
SMSC_TRACE(pdata, ifdown, "Interface stopped");
return 0;
@@ -1811,67 +1895,6 @@
spin_unlock_irqrestore(&pdata->mac_lock, flags);
}
-static irqreturn_t smsc911x_irqhandler(int irq, void *dev_id)
-{
- struct net_device *dev = dev_id;
- struct smsc911x_data *pdata = netdev_priv(dev);
- u32 intsts = smsc911x_reg_read(pdata, INT_STS);
- u32 inten = smsc911x_reg_read(pdata, INT_EN);
- int serviced = IRQ_NONE;
- u32 temp;
-
- if (unlikely(intsts & inten & INT_STS_SW_INT_)) {
- temp = smsc911x_reg_read(pdata, INT_EN);
- temp &= (~INT_EN_SW_INT_EN_);
- smsc911x_reg_write(pdata, INT_EN, temp);
- smsc911x_reg_write(pdata, INT_STS, INT_STS_SW_INT_);
- pdata->software_irq_signal = 1;
- smp_wmb();
- serviced = IRQ_HANDLED;
- }
-
- if (unlikely(intsts & inten & INT_STS_RXSTOP_INT_)) {
- /* Called when there is a multicast update scheduled and
- * it is now safe to complete the update */
- SMSC_TRACE(pdata, intr, "RX Stop interrupt");
- smsc911x_reg_write(pdata, INT_STS, INT_STS_RXSTOP_INT_);
- if (pdata->multicast_update_pending)
- smsc911x_rx_multicast_update_workaround(pdata);
- serviced = IRQ_HANDLED;
- }
-
- if (intsts & inten & INT_STS_TDFA_) {
- temp = smsc911x_reg_read(pdata, FIFO_INT);
- temp |= FIFO_INT_TX_AVAIL_LEVEL_;
- smsc911x_reg_write(pdata, FIFO_INT, temp);
- smsc911x_reg_write(pdata, INT_STS, INT_STS_TDFA_);
- netif_wake_queue(dev);
- serviced = IRQ_HANDLED;
- }
-
- if (unlikely(intsts & inten & INT_STS_RXE_)) {
- SMSC_TRACE(pdata, intr, "RX Error interrupt");
- smsc911x_reg_write(pdata, INT_STS, INT_STS_RXE_);
- serviced = IRQ_HANDLED;
- }
-
- if (likely(intsts & inten & INT_STS_RSFL_)) {
- if (likely(napi_schedule_prep(&pdata->napi))) {
- /* Disable Rx interrupts */
- temp = smsc911x_reg_read(pdata, INT_EN);
- temp &= (~INT_EN_RSFL_EN_);
- smsc911x_reg_write(pdata, INT_EN, temp);
- /* Schedule a NAPI poll */
- __napi_schedule(&pdata->napi);
- } else {
- SMSC_WARN(pdata, rx_err, "napi_schedule_prep failed");
- }
- serviced = IRQ_HANDLED;
- }
-
- return serviced;
-}
-
#ifdef CONFIG_NET_POLL_CONTROLLER
static void smsc911x_poll_controller(struct net_device *dev)
{
@@ -2291,16 +2314,14 @@
pdata = netdev_priv(dev);
BUG_ON(!pdata);
BUG_ON(!pdata->ioaddr);
- BUG_ON(!dev->phydev);
+ WARN_ON(dev->phydev);
SMSC_TRACE(pdata, ifdown, "Stopping driver");
- phy_disconnect(dev->phydev);
mdiobus_unregister(pdata->mii_bus);
mdiobus_free(pdata->mii_bus);
unregister_netdev(dev);
- free_irq(dev->irq, dev);
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
"smsc911x-memory");
if (!res)
@@ -2385,8 +2406,7 @@
struct smsc911x_data *pdata;
struct smsc911x_platform_config *config = dev_get_platdata(&pdev->dev);
struct resource *res;
- unsigned int intcfg = 0;
- int res_size, irq, irq_flags;
+ int res_size, irq;
int retval;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
@@ -2425,7 +2445,6 @@
pdata = netdev_priv(dev);
dev->irq = irq;
- irq_flags = irq_get_trigger_type(irq);
pdata->ioaddr = ioremap_nocache(res->start, res_size);
pdata->dev = dev;
@@ -2472,41 +2491,21 @@
if (retval < 0)
goto out_disable_resources;
- /* configure irq polarity and type before connecting isr */
- if (pdata->config.irq_polarity == SMSC911X_IRQ_POLARITY_ACTIVE_HIGH)
- intcfg |= INT_CFG_IRQ_POL_;
-
- if (pdata->config.irq_type == SMSC911X_IRQ_TYPE_PUSH_PULL)
- intcfg |= INT_CFG_IRQ_TYPE_;
-
- smsc911x_reg_write(pdata, INT_CFG, intcfg);
-
- /* Ensure interrupts are globally disabled before connecting ISR */
- smsc911x_disable_irq_chip(dev);
-
- retval = request_irq(dev->irq, smsc911x_irqhandler,
- irq_flags | IRQF_SHARED, dev->name, dev);
- if (retval) {
- SMSC_WARN(pdata, probe,
- "Unable to claim requested irq: %d", dev->irq);
- goto out_disable_resources;
- }
-
netif_carrier_off(dev);
- retval = register_netdev(dev);
- if (retval) {
- SMSC_WARN(pdata, probe, "Error %i registering device", retval);
- goto out_free_irq;
- } else {
- SMSC_TRACE(pdata, probe,
- "Network interface: \"%s\"", dev->name);
- }
-
retval = smsc911x_mii_init(pdev, dev);
if (retval) {
SMSC_WARN(pdata, probe, "Error %i initialising mii", retval);
- goto out_unregister_netdev_5;
+ goto out_disable_resources;
+ }
+
+ retval = register_netdev(dev);
+ if (retval) {
+ SMSC_WARN(pdata, probe, "Error %i registering device", retval);
+ goto out_disable_resources;
+ } else {
+ SMSC_TRACE(pdata, probe,
+ "Network interface: \"%s\"", dev->name);
}
spin_lock_irq(&pdata->mac_lock);
@@ -2544,10 +2543,6 @@
return 0;
-out_unregister_netdev_5:
- unregister_netdev(dev);
-out_free_irq:
- free_irq(dev->irq, dev);
out_disable_resources:
pm_runtime_put(&pdev->dev);
pm_runtime_disable(&pdev->dev);
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 5a3941b..4490eba 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -1246,7 +1246,7 @@
lp->mii_bus->read = &dwceqos_mdio_read;
lp->mii_bus->write = &dwceqos_mdio_write;
lp->mii_bus->priv = lp;
- lp->mii_bus->parent = &lp->ndev->dev;
+ lp->mii_bus->parent = &lp->pdev->dev;
of_address_to_resource(lp->pdev->dev.of_node, 0, &res);
snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%.8llx",
@@ -2853,25 +2853,17 @@
ndev->features = ndev->hw_features;
- netif_napi_add(ndev, &lp->napi, dwceqos_rx_poll, NAPI_POLL_WEIGHT);
-
- ret = register_netdev(ndev);
- if (ret) {
- dev_err(&pdev->dev, "Cannot register net device, aborting.\n");
- goto err_out_clk_dis_aper;
- }
-
lp->phy_ref_clk = devm_clk_get(&pdev->dev, "phy_ref_clk");
if (IS_ERR(lp->phy_ref_clk)) {
dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
ret = PTR_ERR(lp->phy_ref_clk);
- goto err_out_unregister_netdev;
+ goto err_out_clk_dis_aper;
}
ret = clk_prepare_enable(lp->phy_ref_clk);
if (ret) {
dev_err(&pdev->dev, "Unable to enable device clock.\n");
- goto err_out_unregister_netdev;
+ goto err_out_clk_dis_aper;
}
lp->phy_node = of_parse_phandle(lp->pdev->dev.of_node,
@@ -2880,7 +2872,7 @@
ret = of_phy_register_fixed_link(lp->pdev->dev.of_node);
if (ret < 0) {
dev_err(&pdev->dev, "invalid fixed-link");
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
lp->phy_node = of_node_get(lp->pdev->dev.of_node);
@@ -2889,7 +2881,7 @@
ret = of_get_phy_mode(lp->pdev->dev.of_node);
if (ret < 0) {
dev_err(&lp->pdev->dev, "error in getting phy i/f\n");
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
lp->phy_interface = ret;
@@ -2897,14 +2889,14 @@
ret = dwceqos_mii_init(lp);
if (ret) {
dev_err(&lp->pdev->dev, "error in dwceqos_mii_init\n");
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
ret = dwceqos_mii_probe(ndev);
if (ret != 0) {
netdev_err(ndev, "mii_probe fail.\n");
ret = -ENXIO;
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
dwceqos_set_umac_addr(lp, lp->ndev->dev_addr, 0);
@@ -2922,7 +2914,7 @@
if (ret) {
dev_err(&lp->pdev->dev, "Unable to retrieve DT, error %d\n",
ret);
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
dev_info(&lp->pdev->dev, "pdev->id %d, baseaddr 0x%08lx, irq %d\n",
pdev->id, ndev->base_addr, ndev->irq);
@@ -2932,18 +2924,24 @@
if (ret) {
dev_err(&lp->pdev->dev, "Unable to request IRQ %d, error %d\n",
ndev->irq, ret);
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
if (netif_msg_probe(lp))
netdev_dbg(ndev, "net_local@%p\n", lp);
+ netif_napi_add(ndev, &lp->napi, dwceqos_rx_poll, NAPI_POLL_WEIGHT);
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot register net device, aborting.\n");
+ goto err_out_clk_dis_phy;
+ }
+
return 0;
-err_out_unregister_clk_notifier:
+err_out_clk_dis_phy:
clk_disable_unprepare(lp->phy_ref_clk);
-err_out_unregister_netdev:
- unregister_netdev(ndev);
err_out_clk_dis_aper:
clk_disable_unprepare(lp->apb_pclk);
err_out_free_netdev:
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 47a6434..b4863e4 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -303,6 +303,7 @@
config MDIO_XGENE
tristate "APM X-Gene SoC MDIO bus controller"
+ depends on ARCH_XGENE || COMPILE_TEST
help
This module provides a driver for the MDIO busses found in the
APM X-Gene SoC's.
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index c0dda6f..6e65832 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2782,14 +2782,15 @@
struct net_device *lowerdev = NULL;
if (conf->flags & VXLAN_F_GPE) {
- if (conf->flags & ~VXLAN_F_ALLOWED_GPE)
- return -EINVAL;
/* For now, allow GPE only together with COLLECT_METADATA.
* This can be relaxed later; in such case, the other side
* of the PtP link will have to be provided.
*/
- if (!(conf->flags & VXLAN_F_COLLECT_METADATA))
+ if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) ||
+ !(conf->flags & VXLAN_F_COLLECT_METADATA)) {
+ pr_info("unsupported combination of extensions\n");
return -EINVAL;
+ }
vxlan_raw_setup(dev);
} else {
@@ -2842,6 +2843,9 @@
dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
needed_headroom = lowerdev->hard_header_len;
+ } else if (vxlan_addr_multicast(&dst->remote_ip)) {
+ pr_info("multicast destination requires interface to be specified\n");
+ return -EINVAL;
}
if (conf->mtu) {
@@ -2874,8 +2878,10 @@
tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 &&
tmp->cfg.dst_port == vxlan->cfg.dst_port &&
(tmp->flags & VXLAN_F_RCV_FLAGS) ==
- (vxlan->flags & VXLAN_F_RCV_FLAGS))
- return -EEXIST;
+ (vxlan->flags & VXLAN_F_RCV_FLAGS)) {
+ pr_info("duplicate VNI %u\n", be32_to_cpu(conf->vni));
+ return -EEXIST;
+ }
}
dev->ethtool_ops = &vxlan_ethtool_ops;
@@ -2909,7 +2915,6 @@
struct nlattr *tb[], struct nlattr *data[])
{
struct vxlan_config conf;
- int err;
memset(&conf, 0, sizeof(conf));
@@ -3018,26 +3023,7 @@
if (tb[IFLA_MTU])
conf.mtu = nla_get_u32(tb[IFLA_MTU]);
- err = vxlan_dev_configure(src_net, dev, &conf);
- switch (err) {
- case -ENODEV:
- pr_info("ifindex %d does not exist\n", conf.remote_ifindex);
- break;
-
- case -EPERM:
- pr_info("IPv6 is disabled via sysctl\n");
- break;
-
- case -EEXIST:
- pr_info("duplicate VNI %u\n", be32_to_cpu(conf.vni));
- break;
-
- case -EINVAL:
- pr_info("unsupported combination of extensions\n");
- break;
- }
-
- return err;
+ return vxlan_dev_configure(src_net, dev, &conf);
}
static void vxlan_dellink(struct net_device *dev, struct list_head *head)
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 78db5d6..24c8d65 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -1525,7 +1525,7 @@
static int ath10k_htt_rx_handle_amsdu(struct ath10k_htt *htt)
{
struct ath10k *ar = htt->ar;
- static struct ieee80211_rx_status rx_status;
+ struct ieee80211_rx_status *rx_status = &htt->rx_status;
struct sk_buff_head amsdu;
int ret;
@@ -1549,11 +1549,11 @@
return ret;
}
- ath10k_htt_rx_h_ppdu(ar, &amsdu, &rx_status, 0xffff);
+ ath10k_htt_rx_h_ppdu(ar, &amsdu, rx_status, 0xffff);
ath10k_htt_rx_h_unchain(ar, &amsdu, ret > 0);
- ath10k_htt_rx_h_filter(ar, &amsdu, &rx_status);
- ath10k_htt_rx_h_mpdu(ar, &amsdu, &rx_status);
- ath10k_htt_rx_h_deliver(ar, &amsdu, &rx_status);
+ ath10k_htt_rx_h_filter(ar, &amsdu, rx_status);
+ ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status);
+ ath10k_htt_rx_h_deliver(ar, &amsdu, rx_status);
return 0;
}
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 9a22c47..07933c5 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -3162,7 +3162,6 @@
pci_hard_reset = ath10k_pci_qca988x_chip_reset;
break;
case QCA9887_1_0_DEVICE_ID:
- dev_warn(&pdev->dev, "QCA9887 support is still experimental, there are likely bugs. You have been warned.\n");
hw_rev = ATH10K_HW_QCA9887;
pci_ps = false;
pci_soft_reset = ath10k_pci_warm_reset;
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index d1d0c06..14b13f0 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -2482,6 +2482,8 @@
return -EINVAL;
}
+ ath9k_gpio_cap_init(ah);
+
if (AR_SREV_9485(ah) ||
AR_SREV_9285(ah) ||
AR_SREV_9330(ah) ||
@@ -2531,8 +2533,6 @@
else
pCap->hw_caps &= ~ATH9K_HW_CAP_HT;
- ath9k_gpio_cap_init(ah);
-
if (AR_SREV_9160_10_OR_LATER(ah) || AR_SREV_9100(ah))
pCap->rts_aggr_limit = ATH_AMPDU_LIMIT_MAX;
else
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index a394622..7cb65c3 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -718,9 +718,12 @@
if (!ath_complete_reset(sc, false))
ah->reset_power_on = false;
- if (ah->led_pin >= 0)
+ if (ah->led_pin >= 0) {
ath9k_hw_set_gpio(ah, ah->led_pin,
(ah->config.led_active_high) ? 1 : 0);
+ ath9k_hw_gpio_request_out(ah, ah->led_pin, NULL,
+ AR_GPIO_OUTPUT_MUX_AS_OUTPUT);
+ }
/*
* Reset key cache to sane defaults (all entries cleared) instead of
@@ -864,9 +867,11 @@
spin_lock_bh(&sc->sc_pcu_lock);
- if (ah->led_pin >= 0)
+ if (ah->led_pin >= 0) {
ath9k_hw_set_gpio(ah, ah->led_pin,
(ah->config.led_active_high) ? 0 : 1);
+ ath9k_hw_gpio_request_in(ah, ah->led_pin, NULL);
+ }
ath_prepare_reset(sc);
@@ -1154,6 +1159,7 @@
bool changed = (iter_data.primary_sta != ctx->primary_sta);
if (iter_data.primary_sta) {
+ iter_data.primary_beacon_vif = iter_data.primary_sta;
iter_data.beacons = true;
ath9k_set_assoc_state(sc, iter_data.primary_sta,
changed);
@@ -1563,13 +1569,13 @@
struct ath_common *common = ath9k_hw_common(sc->sc_ah);
int ret = 0;
- if (old_state == IEEE80211_STA_AUTH &&
- new_state == IEEE80211_STA_ASSOC) {
+ if (old_state == IEEE80211_STA_NOTEXIST &&
+ new_state == IEEE80211_STA_NONE) {
ret = ath9k_sta_add(hw, vif, sta);
ath_dbg(common, CONFIG,
"Add station: %pM\n", sta->addr);
- } else if (old_state == IEEE80211_STA_ASSOC &&
- new_state == IEEE80211_STA_AUTH) {
+ } else if (old_state == IEEE80211_STA_NONE &&
+ new_state == IEEE80211_STA_NOTEXIST) {
ret = ath9k_sta_remove(hw, vif, sta);
ath_dbg(common, CONFIG,
"Remove station: %pM\n", sta->addr);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 2628d5e..b8aec5e5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -4527,7 +4527,7 @@
(u8 *)&settings->beacon.head[ie_offset],
settings->beacon.head_len - ie_offset,
WLAN_EID_SSID);
- if (!ssid_ie)
+ if (!ssid_ie || ssid_ie->len > IEEE80211_MAX_SSID_LEN)
return -EINVAL;
memcpy(ssid_le.SSID, ssid_ie->data, ssid_ie->len);
@@ -5635,7 +5635,7 @@
ifevent->action, ifevent->flags, ifevent->ifidx,
ifevent->bsscfgidx);
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
event->action = ifevent->action;
vif = event->vif;
@@ -5643,7 +5643,7 @@
case BRCMF_E_IF_ADD:
/* waiting process may have timed out */
if (!cfg->vif_event.vif) {
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
return -EBADF;
}
@@ -5654,24 +5654,24 @@
ifp->ndev->ieee80211_ptr = &vif->wdev;
SET_NETDEV_DEV(ifp->ndev, wiphy_dev(cfg->wiphy));
}
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
wake_up(&event->vif_wq);
return 0;
case BRCMF_E_IF_DEL:
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
/* event may not be upon user request */
if (brcmf_cfg80211_vif_event_armed(cfg))
wake_up(&event->vif_wq);
return 0;
case BRCMF_E_IF_CHANGE:
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
wake_up(&event->vif_wq);
return 0;
default:
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
break;
}
return -EINVAL;
@@ -5792,7 +5792,7 @@
static void init_vif_event(struct brcmf_cfg80211_vif_event *event)
{
init_waitqueue_head(&event->vif_wq);
- mutex_init(&event->vif_event_lock);
+ spin_lock_init(&event->vif_event_lock);
}
static s32 brcmf_dongle_roam(struct brcmf_if *ifp)
@@ -6691,9 +6691,9 @@
{
u8 evt_action;
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
evt_action = event->action;
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
return evt_action == action;
}
@@ -6702,10 +6702,10 @@
{
struct brcmf_cfg80211_vif_event *event = &cfg->vif_event;
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
event->vif = vif;
event->action = 0;
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
}
bool brcmf_cfg80211_vif_event_armed(struct brcmf_cfg80211_info *cfg)
@@ -6713,9 +6713,9 @@
struct brcmf_cfg80211_vif_event *event = &cfg->vif_event;
bool armed;
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
armed = event->vif != NULL;
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
return armed;
}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
index 7d77f86..8889832 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
@@ -227,7 +227,7 @@
*/
struct brcmf_cfg80211_vif_event {
wait_queue_head_t vif_wq;
- struct mutex vif_event_lock;
+ spinlock_t vif_event_lock;
u8 action;
struct brcmf_cfg80211_vif *vif;
};
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index 8d16f02..65e8c87 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -743,7 +743,7 @@
* serious troublesome side effects. The p2p module will clean
* up the ifp if needed.
*/
- brcmf_p2p_ifp_removed(ifp);
+ brcmf_p2p_ifp_removed(ifp, rtnl_locked);
kfree(ifp);
}
}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index 66f942f..de19c7c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -2297,7 +2297,7 @@
return err;
}
-void brcmf_p2p_ifp_removed(struct brcmf_if *ifp)
+void brcmf_p2p_ifp_removed(struct brcmf_if *ifp, bool rtnl_locked)
{
struct brcmf_cfg80211_info *cfg;
struct brcmf_cfg80211_vif *vif;
@@ -2306,9 +2306,11 @@
vif = ifp->vif;
cfg = wdev_to_cfg(&vif->wdev);
cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif = NULL;
- rtnl_lock();
+ if (!rtnl_locked)
+ rtnl_lock();
cfg80211_unregister_wdev(&vif->wdev);
- rtnl_unlock();
+ if (!rtnl_locked)
+ rtnl_unlock();
brcmf_free_vif(vif);
}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h
index a3bd18c..8ce9447 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.h
@@ -155,7 +155,7 @@
int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev);
int brcmf_p2p_ifchange(struct brcmf_cfg80211_info *cfg,
enum brcmf_fil_p2p_if_types if_type);
-void brcmf_p2p_ifp_removed(struct brcmf_if *ifp);
+void brcmf_p2p_ifp_removed(struct brcmf_if *ifp, bool rtnl_locked);
int brcmf_p2p_start_device(struct wiphy *wiphy, struct wireless_dev *wdev);
void brcmf_p2p_stop_device(struct wiphy *wiphy, struct wireless_dev *wdev);
int brcmf_p2p_scan_prep(struct wiphy *wiphy,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c
index 1abcabb..46b52bf 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c
@@ -960,5 +960,6 @@
}
mvm->fw_dbg_conf = conf_id;
- return ret;
+
+ return 0;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.h
index f7dff76..e9f1be9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.h
@@ -105,7 +105,8 @@
{
u32 trig_vif = le32_to_cpu(trig->vif_type);
- return trig_vif == IWL_FW_DBG_CONF_VIF_ANY || vif->type == trig_vif;
+ return trig_vif == IWL_FW_DBG_CONF_VIF_ANY ||
+ ieee80211_vif_type_p2p(vif) == trig_vif;
}
static inline bool
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 6d60645..5dd77e3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -624,6 +624,7 @@
hw->wiphy->features |= NL80211_FEATURE_P2P_GO_CTWIN |
NL80211_FEATURE_LOW_PRIORITY_SCAN |
NL80211_FEATURE_P2P_GO_OPPPS |
+ NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE |
NL80211_FEATURE_DYNAMIC_SMPS |
NL80211_FEATURE_STATIC_SMPS |
NL80211_FEATURE_SUPPORTS_WMM_ADMISSION;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index b4fc86d..6a615bb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -467,6 +467,8 @@
static inline struct iwl_mvm_vif *
iwl_mvm_vif_from_mac80211(struct ieee80211_vif *vif)
{
+ if (!vif)
+ return NULL;
return (void *)vif->drv_priv;
}
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_aggr.c b/drivers/net/wireless/marvell/mwifiex/11n_aggr.c
index dc49c3d..c47d636 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_aggr.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_aggr.c
@@ -205,7 +205,8 @@
do {
/* Check if AMSDU can accommodate this MSDU */
- if (skb_tailroom(skb_aggr) < (skb_src->len + LLC_SNAP_LEN))
+ if ((skb_aggr->len + skb_src->len + LLC_SNAP_LEN) >
+ adapter->tx_buf_size)
break;
skb_src = skb_dequeue(&pra_list->skb_head);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8dcf5a9..60f7eab 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1693,7 +1693,12 @@
nvme_suspend_queue(dev->queues[i]);
if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
- nvme_suspend_queue(dev->queues[0]);
+ /* A device might become IO incapable very soon during
+ * probe, before the admin queue is configured. Thus,
+ * queue_count can be 0 here.
+ */
+ if (dev->queue_count)
+ nvme_suspend_queue(dev->queues[0]);
} else {
nvme_disable_io_queues(dev);
nvme_disable_admin_queue(dev, shutdown);
@@ -2112,6 +2117,8 @@
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+ { PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */
+ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ 0, }
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index ab545fb..c2c2c28 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -82,6 +82,8 @@
enum nvme_rdma_queue_flags {
NVME_RDMA_Q_CONNECTED = (1 << 0),
+ NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1),
+ NVME_RDMA_Q_DELETING = (1 << 2),
};
struct nvme_rdma_queue {
@@ -291,6 +293,7 @@
if (IS_ERR(req->mr)) {
ret = PTR_ERR(req->mr);
req->mr = NULL;
+ goto out;
}
req->mr->need_inval = false;
@@ -480,9 +483,14 @@
static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
{
- struct nvme_rdma_device *dev = queue->device;
- struct ib_device *ibdev = dev->dev;
+ struct nvme_rdma_device *dev;
+ struct ib_device *ibdev;
+ if (!test_and_clear_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags))
+ return;
+
+ dev = queue->device;
+ ibdev = dev->dev;
rdma_destroy_qp(queue->cm_id);
ib_free_cq(queue->ib_cq);
@@ -533,6 +541,7 @@
ret = -ENOMEM;
goto out_destroy_qp;
}
+ set_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags);
return 0;
@@ -552,6 +561,7 @@
queue = &ctrl->queues[idx];
queue->ctrl = ctrl;
+ queue->flags = 0;
init_completion(&queue->cm_done);
if (idx > 0)
@@ -590,6 +600,7 @@
return 0;
out_destroy_cm_id:
+ nvme_rdma_destroy_queue_ib(queue);
rdma_destroy_id(queue->cm_id);
return ret;
}
@@ -608,7 +619,7 @@
static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue)
{
- if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
+ if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags))
return;
nvme_rdma_stop_queue(queue);
nvme_rdma_free_queue(queue);
@@ -652,7 +663,7 @@
return 0;
out_free_queues:
- for (; i >= 1; i--)
+ for (i--; i >= 1; i--)
nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
return ret;
@@ -761,8 +772,13 @@
{
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, err_work);
+ int i;
nvme_stop_keep_alive(&ctrl->ctrl);
+
+ for (i = 0; i < ctrl->queue_count; i++)
+ clear_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[i].flags);
+
if (ctrl->queue_count > 1)
nvme_stop_queues(&ctrl->ctrl);
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
@@ -1305,58 +1321,6 @@
return ret;
}
-/**
- * nvme_rdma_device_unplug() - Handle RDMA device unplug
- * @queue: Queue that owns the cm_id that caught the event
- *
- * DEVICE_REMOVAL event notifies us that the RDMA device is about
- * to unplug so we should take care of destroying our RDMA resources.
- * This event will be generated for each allocated cm_id.
- *
- * In our case, the RDMA resources are managed per controller and not
- * only per queue. So the way we handle this is we trigger an implicit
- * controller deletion upon the first DEVICE_REMOVAL event we see, and
- * hold the event inflight until the controller deletion is completed.
- *
- * One exception that we need to handle is the destruction of the cm_id
- * that caught the event. Since we hold the callout until the controller
- * deletion is completed, we'll deadlock if the controller deletion will
- * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership
- * of destroying this queue before-hand, destroy the queue resources,
- * then queue the controller deletion which won't destroy this queue and
- * we destroy the cm_id implicitely by returning a non-zero rc to the callout.
- */
-static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue)
-{
- struct nvme_rdma_ctrl *ctrl = queue->ctrl;
- int ret = 0;
-
- /* Own the controller deletion */
- if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
- return 0;
-
- dev_warn(ctrl->ctrl.device,
- "Got rdma device removal event, deleting ctrl\n");
-
- /* Get rid of reconnect work if its running */
- cancel_delayed_work_sync(&ctrl->reconnect_work);
-
- /* Disable the queue so ctrl delete won't free it */
- if (test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) {
- /* Free this queue ourselves */
- nvme_rdma_stop_queue(queue);
- nvme_rdma_destroy_queue_ib(queue);
-
- /* Return non-zero so the cm_id will destroy implicitly */
- ret = 1;
- }
-
- /* Queue controller deletion */
- queue_work(nvme_rdma_wq, &ctrl->delete_work);
- flush_work(&ctrl->delete_work);
- return ret;
-}
-
static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *ev)
{
@@ -1398,8 +1362,8 @@
nvme_rdma_error_recovery(queue->ctrl);
break;
case RDMA_CM_EVENT_DEVICE_REMOVAL:
- /* return 1 means impliciy CM ID destroy */
- return nvme_rdma_device_unplug(queue);
+ /* device removal is handled via the ib_client API */
+ break;
default:
dev_err(queue->ctrl->ctrl.device,
"Unexpected RDMA CM event (%d)\n", ev->event);
@@ -1700,15 +1664,19 @@
static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
- int ret;
+ int ret = 0;
+ /*
+ * Keep a reference until all work is flushed since
+ * __nvme_rdma_del_ctrl can free the ctrl mem
+ */
+ if (!kref_get_unless_zero(&ctrl->ctrl.kref))
+ return -EBUSY;
ret = __nvme_rdma_del_ctrl(ctrl);
- if (ret)
- return ret;
-
- flush_work(&ctrl->delete_work);
-
- return 0;
+ if (!ret)
+ flush_work(&ctrl->delete_work);
+ nvme_put_ctrl(&ctrl->ctrl);
+ return ret;
}
static void nvme_rdma_remove_ctrl_work(struct work_struct *work)
@@ -2005,27 +1973,57 @@
.create_ctrl = nvme_rdma_create_ctrl,
};
+static void nvme_rdma_add_one(struct ib_device *ib_device)
+{
+}
+
+static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data)
+{
+ struct nvme_rdma_ctrl *ctrl;
+
+ /* Delete all controllers using this device */
+ mutex_lock(&nvme_rdma_ctrl_mutex);
+ list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) {
+ if (ctrl->device->dev != ib_device)
+ continue;
+ dev_info(ctrl->ctrl.device,
+ "Removing ctrl: NQN \"%s\", addr %pISp\n",
+ ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+ __nvme_rdma_del_ctrl(ctrl);
+ }
+ mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+ flush_workqueue(nvme_rdma_wq);
+}
+
+static struct ib_client nvme_rdma_ib_client = {
+ .name = "nvme_rdma",
+ .add = nvme_rdma_add_one,
+ .remove = nvme_rdma_remove_one
+};
+
static int __init nvme_rdma_init_module(void)
{
+ int ret;
+
nvme_rdma_wq = create_workqueue("nvme_rdma_wq");
if (!nvme_rdma_wq)
return -ENOMEM;
+ ret = ib_register_client(&nvme_rdma_ib_client);
+ if (ret) {
+ destroy_workqueue(nvme_rdma_wq);
+ return ret;
+ }
+
nvmf_register_transport(&nvme_rdma_transport);
return 0;
}
static void __exit nvme_rdma_cleanup_module(void)
{
- struct nvme_rdma_ctrl *ctrl;
-
nvmf_unregister_transport(&nvme_rdma_transport);
-
- mutex_lock(&nvme_rdma_ctrl_mutex);
- list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list)
- __nvme_rdma_del_ctrl(ctrl);
- mutex_unlock(&nvme_rdma_ctrl_mutex);
-
+ ib_unregister_client(&nvme_rdma_ib_client);
destroy_workqueue(nvme_rdma_wq);
}
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index d1ef7ac..f9357e0 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -40,6 +40,7 @@
list_del(&dev->bus_list);
up_write(&pci_bus_sem);
+ pci_bridge_d3_device_removed(dev);
pci_free_resources(dev);
put_device(&dev->dev);
}
@@ -96,8 +97,6 @@
dev->subordinate = NULL;
}
- pci_bridge_d3_device_removed(dev);
-
pci_destroy_dev(dev);
}
diff --git a/fs/aio.c b/fs/aio.c
index fb8e45b..4fe81d1 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -239,7 +239,12 @@
static const struct dentry_operations ops = {
.d_dname = simple_dname,
};
- return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC);
+ struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+ AIO_RING_MAGIC);
+
+ if (!IS_ERR(root))
+ root->d_sb->s_iflags |= SB_I_NOEXEC;
+ return root;
}
/* aio_setup
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 0f56deb..c415668 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -568,7 +568,7 @@
return thaw_super(sb);
}
-static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
+static int ioctl_file_dedupe_range(struct file *file, void __user *arg)
{
struct file_dedupe_range __user *argp = arg;
struct file_dedupe_range *same = NULL;
@@ -582,6 +582,10 @@
}
size = offsetof(struct file_dedupe_range __user, info[count]);
+ if (size > PAGE_SIZE) {
+ ret = -ENOMEM;
+ goto out;
+ }
same = memdup_user(argp, size);
if (IS_ERR(same)) {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7d62097..ca699dd 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -657,7 +657,10 @@
if (result <= 0)
goto out;
- written = generic_write_sync(iocb, result);
+ result = generic_write_sync(iocb, result);
+ if (result < 0)
+ goto out;
+ written = result;
iocb->ki_pos += written;
/* Return error values */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f5aecaa..a9dec32 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7570,12 +7570,20 @@
status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
trace_nfs4_create_session(clp, status);
+ switch (status) {
+ case -NFS4ERR_STALE_CLIENTID:
+ case -NFS4ERR_DELAY:
+ case -ETIMEDOUT:
+ case -EACCES:
+ case -EAGAIN:
+ goto out;
+ };
+
+ clp->cl_seqid++;
if (!status) {
/* Verify the session's negotiated channel_attrs values */
status = nfs4_verify_channel_attrs(&args, &res);
/* Increment the clientid slot sequence id */
- if (clp->cl_seqid == res.seqid)
- clp->cl_seqid++;
if (status)
goto out;
nfs4_update_session(session, &res);
@@ -8190,10 +8198,13 @@
dprintk("--> %s\n", __func__);
spin_lock(&lo->plh_inode->i_lock);
- pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
- be32_to_cpu(lrp->args.stateid.seqid));
- if (lrp->res.lrs_present && pnfs_layout_is_valid(lo))
+ if (lrp->res.lrs_present) {
+ pnfs_mark_matching_lsegs_invalid(lo, &freeme,
+ &lrp->args.range,
+ be32_to_cpu(lrp->args.stateid.seqid));
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+ } else
+ pnfs_mark_layout_stateid_invalid(lo, &freeme);
pnfs_clear_layoutreturn_waitbit(lo);
spin_unlock(&lo->plh_inode->i_lock);
nfs4_sequence_free_slot(&lrp->res.seq_res);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 6daf034..2c93a85 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -365,7 +365,8 @@
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
if (list_empty(&lo->plh_segs)) {
- set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ if (atomic_read(&lo->plh_outstanding) == 0)
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
@@ -768,17 +769,32 @@
pnfs_destroy_layouts_byclid(clp, false);
}
+static void
+pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
+{
+ lo->plh_return_iomode = 0;
+ lo->plh_return_seq = 0;
+ clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+}
+
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
bool update_barrier)
{
u32 oldseq, newseq, new_barrier = 0;
- bool invalid = !pnfs_layout_is_valid(lo);
oldseq = be32_to_cpu(lo->plh_stateid.seqid);
newseq = be32_to_cpu(new->seqid);
- if (invalid || pnfs_seqid_is_newer(newseq, oldseq)) {
+
+ if (!pnfs_layout_is_valid(lo)) {
+ nfs4_stateid_copy(&lo->plh_stateid, new);
+ lo->plh_barrier = newseq;
+ pnfs_clear_layoutreturn_info(lo);
+ clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ return;
+ }
+ if (pnfs_seqid_is_newer(newseq, oldseq)) {
nfs4_stateid_copy(&lo->plh_stateid, new);
/*
* Because of wraparound, we want to keep the barrier
@@ -790,7 +806,7 @@
new_barrier = be32_to_cpu(new->seqid);
else if (new_barrier == 0)
return;
- if (invalid || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+ if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
lo->plh_barrier = new_barrier;
}
@@ -886,19 +902,14 @@
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
}
-static void
-pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
-{
- lo->plh_return_iomode = 0;
- lo->plh_return_seq = 0;
- clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
-}
-
static bool
pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
nfs4_stateid *stateid,
enum pnfs_iomode *iomode)
{
+ /* Serialise LAYOUTGET/LAYOUTRETURN */
+ if (atomic_read(&lo->plh_outstanding) != 0)
+ return false;
if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return false;
pnfs_get_layout_hdr(lo);
@@ -1798,16 +1809,11 @@
*/
pnfs_mark_layout_stateid_invalid(lo, &free_me);
- nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
- lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
+ pnfs_set_layout_stateid(lo, &res->stateid, true);
}
pnfs_get_lseg(lseg);
pnfs_layout_insert_lseg(lo, lseg, &free_me);
- if (!pnfs_layout_is_valid(lo)) {
- pnfs_clear_layoutreturn_info(lo);
- clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- }
if (res->return_on_close)
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index 5dea1fb..6df9b07 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -231,14 +231,18 @@
might_fault(); \
access_ok(VERIFY_READ, __p, sizeof(*ptr)) ? \
__get_user((x), (__typeof__(*(ptr)) *)__p) : \
- -EFAULT; \
+ ((x) = (__typeof__(*(ptr)))0,-EFAULT); \
})
#ifndef __get_user_fn
static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
{
- size = __copy_from_user(x, ptr, size);
- return size ? -EFAULT : size;
+ size_t n = __copy_from_user(x, ptr, size);
+ if (unlikely(n)) {
+ memset(x + (size - n), 0, n);
+ return -EFAULT;
+ }
+ return 0;
}
#define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k)
@@ -258,11 +262,13 @@
static inline long copy_from_user(void *to,
const void __user * from, unsigned long n)
{
+ unsigned long res = n;
might_fault();
- if (access_ok(VERIFY_READ, from, n))
- return __copy_from_user(to, from, n);
- else
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline long copy_to_user(void __user *to,
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 436aa4e..6685698 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -527,13 +527,14 @@
* object's lifetime is managed by something other than RCU. That
* "something other" might be reference counting or simple immortality.
*
- * The seemingly unused size_t variable is to validate @p is indeed a pointer
- * type by making sure it can be dereferenced.
+ * The seemingly unused variable ___typecheck_p validates that @p is
+ * indeed a pointer type by using a pointer to typeof(*p) as the type.
+ * Taking a pointer to typeof(*p) again is needed in case p is void *.
*/
#define lockless_dereference(p) \
({ \
typeof(p) _________p1 = READ_ONCE(p); \
- size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \
+ typeof(*(p)) *___typecheck_p __maybe_unused; \
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
(_________p1); \
})
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7f5a582..0148a30 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -118,6 +118,15 @@
u32 imagesize;
} efi_capsule_header_t;
+struct efi_boot_memmap {
+ efi_memory_desc_t **map;
+ unsigned long *map_size;
+ unsigned long *desc_size;
+ u32 *desc_ver;
+ unsigned long *key_ptr;
+ unsigned long *buff_size;
+};
+
/*
* EFI capsule flags
*/
@@ -946,7 +955,7 @@
/* Iterate through an efi_memory_map */
#define for_each_efi_memory_desc_in_map(m, md) \
for ((md) = (m)->map; \
- ((void *)(md) + (m)->desc_size) <= (m)->map_end; \
+ (md) && ((void *)(md) + (m)->desc_size) <= (m)->map_end; \
(md) = (void *)(md) + (m)->desc_size)
/**
@@ -1371,11 +1380,7 @@
efi_loaded_image_t *image, int *cmd_line_len);
efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
- efi_memory_desc_t **map,
- unsigned long *map_size,
- unsigned long *desc_size,
- u32 *desc_ver,
- unsigned long *key_ptr);
+ struct efi_boot_memmap *map);
efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
unsigned long size, unsigned long align,
@@ -1457,4 +1462,14 @@
arch_efi_call_virt_teardown(); \
})
+typedef efi_status_t (*efi_exit_boot_map_processing)(
+ efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv);
+
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table,
+ void *handle,
+ struct efi_boot_memmap *map,
+ void *priv,
+ efi_exit_boot_map_processing priv_func);
#endif /* _LINUX_EFI_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 21bc455..d1f9a58 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -6710,9 +6710,10 @@
};
struct mlx5_ifc_ptys_reg_bits {
- u8 an_disable_cap[0x1];
+ u8 reserved_at_0[0x1];
u8 an_disable_admin[0x1];
- u8 reserved_at_2[0x6];
+ u8 an_disable_cap[0x1];
+ u8 reserved_at_3[0x5];
u8 local_port[0x8];
u8 reserved_at_10[0xd];
u8 proto_mask[0x3];
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3a788bf..e8d79d4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3267,6 +3267,7 @@
napi->skb = NULL;
}
+bool netdev_is_rx_handler_busy(struct net_device *dev);
int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data);
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 9b4c418..fd60ecc 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -52,7 +52,7 @@
struct sock sk;
struct unix_address *addr;
struct path path;
- struct mutex readlock;
+ struct mutex iolock, bindlock;
struct sock *peer;
struct list_head link;
atomic_long_t inflight;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 9c23f4d3..beb7610 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1102,6 +1102,7 @@
struct cfg80211_tid_stats pertid[IEEE80211_NUM_TIDS + 1];
};
+#if IS_ENABLED(CONFIG_CFG80211)
/**
* cfg80211_get_station - retrieve information about a given station
* @dev: the device where the station is supposed to be connected to
@@ -1114,6 +1115,14 @@
*/
int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,
struct station_info *sinfo);
+#else
+static inline int cfg80211_get_station(struct net_device *dev,
+ const u8 *mac_addr,
+ struct station_info *sinfo)
+{
+ return -ENOENT;
+}
+#endif
/**
* enum monitor_flags - monitor flags
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 4079fc1..7d4a72e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -111,6 +111,7 @@
unsigned char fib_scope;
unsigned char fib_type;
__be32 fib_prefsrc;
+ u32 fib_tb_id;
u32 fib_priority;
u32 *fib_metrics;
#define fib_mtu fib_metrics[RTAX_MTU-1]
@@ -319,7 +320,7 @@
/* Exported by fib_semantics.c */
int ip_fib_check_default(__be32 gw, struct net_device *dev);
int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
-int fib_sync_down_addr(struct net *net, __be32 local);
+int fib_sync_down_addr(struct net_device *dev, __be32 local);
int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
extern u32 fib_multipath_secret __read_mostly;
diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h
index d27588c..1139cde 100644
--- a/include/net/netfilter/nft_meta.h
+++ b/include/net/netfilter/nft_meta.h
@@ -36,4 +36,8 @@
void nft_meta_set_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr);
+int nft_meta_set_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data);
+
#endif
diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h
index 60fa153..02e28c5 100644
--- a/include/net/netfilter/nft_reject.h
+++ b/include/net/netfilter/nft_reject.h
@@ -8,6 +8,10 @@
extern const struct nla_policy nft_reject_policy[];
+int nft_reject_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data);
+
int nft_reject_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[]);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3cfabdf..a54f2c2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2496,11 +2496,11 @@
return 0;
}
-static int perf_event_restart(struct perf_event *event)
+static int perf_event_stop(struct perf_event *event, int restart)
{
struct stop_event_data sd = {
.event = event,
- .restart = 1,
+ .restart = restart,
};
int ret = 0;
@@ -3549,10 +3549,18 @@
.group = group,
.ret = 0,
};
- ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
- /* The event must have been read from an online CPU: */
- WARN_ON_ONCE(ret);
- ret = ret ? : data.ret;
+ /*
+ * Purposely ignore the smp_call_function_single() return
+ * value.
+ *
+ * If event->oncpu isn't a valid CPU it means the event got
+ * scheduled out and that will have updated the event count.
+ *
+ * Therefore, either way, we'll have an up-to-date event count
+ * after this.
+ */
+ (void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+ ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
unsigned long flags;
@@ -4837,6 +4845,19 @@
spin_unlock_irqrestore(&rb->event_lock, flags);
}
+ /*
+ * Avoid racing with perf_mmap_close(AUX): stop the event
+ * before swizzling the event::rb pointer; if it's getting
+ * unmapped, its aux_mmap_count will be 0 and it won't
+ * restart. See the comment in __perf_pmu_output_stop().
+ *
+ * Data will inevitably be lost when set_output is done in
+ * mid-air, but then again, whoever does it like this is
+ * not in for the data anyway.
+ */
+ if (has_aux(event))
+ perf_event_stop(event, 0);
+
rcu_assign_pointer(event->rb, rb);
if (old_rb) {
@@ -6112,7 +6133,7 @@
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
void perf_event_exec(void)
@@ -6156,7 +6177,13 @@
/*
* In case of inheritance, it will be the parent that links to the
- * ring-buffer, but it will be the child that's actually using it:
+ * ring-buffer, but it will be the child that's actually using it.
+ *
+ * We are using event::rb to determine if the event should be stopped,
+ * however this may race with ring_buffer_attach() (through set_output),
+ * which will make us skip the event that actually needs to be stopped.
+ * So ring_buffer_attach() has to stop an aux event before re-assigning
+ * its rb pointer.
*/
if (rcu_dereference(parent->rb) == rb)
ro->err = __perf_event_stop(&sd);
@@ -6670,7 +6697,7 @@
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
/*
@@ -7859,7 +7886,7 @@
mmput(mm);
restart:
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
/*
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index ae9b90d..257fa46 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -330,15 +330,22 @@
if (!rb)
return NULL;
- if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
+ if (!rb_has_aux(rb))
goto err;
/*
- * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
- * the aux buffer is in perf_mmap_close(), about to get freed.
+ * If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
+ * about to get freed, so we leave immediately.
+ *
+ * Checking rb::aux_mmap_count and rb::refcount has to be done in
+ * the same order, see perf_mmap_close. Otherwise we end up freeing
+ * aux pages in this path, which is a bug, because in_atomic().
*/
if (!atomic_read(&rb->aux_mmap_count))
- goto err_put;
+ goto err;
+
+ if (!atomic_inc_not_zero(&rb->aux_refcount))
+ goto err;
/*
* Nesting is not supported for AUX area, make sure nested
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2a906f2..44817c6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2016,6 +2016,28 @@
success = 1; /* we're going to change ->state */
cpu = task_cpu(p);
+ /*
+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
+ * in smp_cond_load_acquire() below.
+ *
+ * sched_ttwu_pending() try_to_wake_up()
+ * [S] p->on_rq = 1; [L] P->state
+ * UNLOCK rq->lock -----.
+ * \
+ * +--- RMB
+ * schedule() /
+ * LOCK rq->lock -----'
+ * UNLOCK rq->lock
+ *
+ * [task p]
+ * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ *
+ * Pairs with the UNLOCK+LOCK on rq->lock from the
+ * last wakeup of our task and the schedule that got our task
+ * current.
+ */
+ smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
goto stat;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 8e48620..abe11f0 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -80,13 +80,10 @@
BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
- if (dev->flags & IFF_NOARP)
+ if ((dev->flags & IFF_NOARP) ||
+ !pskb_may_pull(skb, arp_hdr_len(dev)))
return;
- if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
- dev->stats.tx_dropped++;
- return;
- }
parp = arp_hdr(skb);
if (parp->ar_pro != htons(ETH_P_IP) ||
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index a5423a1..c5fea93 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1138,7 +1138,7 @@
} else {
err = br_ip6_multicast_add_group(br, port,
&grec->grec_mca, vid);
- if (!err)
+ if (err)
break;
}
}
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index cceac5b..0833c25 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -368,6 +368,8 @@
match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0);
if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) {
+ if (!IS_ERR(match))
+ module_put(match->me);
request_module("ebt_%s", m->u.name);
match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0);
}
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index 4b901d9..ad47a92 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -86,6 +86,7 @@
.init = nft_meta_set_init,
.destroy = nft_meta_set_destroy,
.dump = nft_meta_set_dump,
+ .validate = nft_meta_set_validate,
};
static const struct nft_expr_ops *
diff --git a/net/core/dev.c b/net/core/dev.c
index dd6ce59..ea63120 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3975,6 +3975,22 @@
}
/**
+ * netdev_is_rx_handler_busy - check if receive handler is registered
+ * @dev: device to check
+ *
+ * Check if a receive handler is already registered for a given device.
+ * Return true if there one.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+bool netdev_is_rx_handler_busy(struct net_device *dev)
+{
+ ASSERT_RTNL();
+ return dev && rtnl_dereference(dev->rx_handler);
+}
+EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy);
+
+/**
* netdev_rx_handler_register - register receive handler
* @dev: device to register a handler for
* @rx_handler: receive handler to register
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 61ad43f..52742a0 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -680,11 +680,13 @@
void __skb_get_hash(struct sk_buff *skb)
{
struct flow_keys keys;
+ u32 hash;
__flow_hash_secret_init();
- __skb_set_sw_hash(skb, ___skb_get_hash(skb, &keys, hashrnd),
- flow_keys_have_l4(&keys));
+ hash = ___skb_get_hash(skb, &keys, hashrnd);
+
+ __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
}
EXPORT_SYMBOL(__skb_get_hash);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 415e117..062a67c 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2232,7 +2232,7 @@
};
static int __devinet_sysctl_register(struct net *net, char *dev_name,
- struct ipv4_devconf *p)
+ int ifindex, struct ipv4_devconf *p)
{
int i;
struct devinet_sysctl_table *t;
@@ -2255,6 +2255,8 @@
goto free;
p->sysctl = t;
+
+ inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
return 0;
free:
@@ -2286,7 +2288,7 @@
if (err)
return err;
err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name,
- &idev->cnf);
+ idev->dev->ifindex, &idev->cnf);
if (err)
neigh_sysctl_unregister(idev->arp_parms);
return err;
@@ -2347,11 +2349,12 @@
}
#ifdef CONFIG_SYSCTL
- err = __devinet_sysctl_register(net, "all", all);
+ err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all);
if (err < 0)
goto err_reg_all;
- err = __devinet_sysctl_register(net, "default", dflt);
+ err = __devinet_sysctl_register(net, "default",
+ NETCONFA_IFINDEX_DEFAULT, dflt);
if (err < 0)
goto err_reg_dflt;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index ef2ebeb..1b25daf 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -509,6 +509,7 @@
if (!dev)
return -ENODEV;
cfg->fc_oif = dev->ifindex;
+ cfg->fc_table = l3mdev_fib_table(dev);
if (colon) {
struct in_ifaddr *ifa;
struct in_device *in_dev = __in_dev_get_rtnl(dev);
@@ -1027,7 +1028,7 @@
* First of all, we scan fib_info list searching
* for stray nexthop entries, then ignite fib_flush.
*/
- if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local))
+ if (fib_sync_down_addr(dev, ifa->ifa_local))
fib_flush(dev_net(dev));
}
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 539fa26..e9f5622 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1057,6 +1057,7 @@
fi->fib_priority = cfg->fc_priority;
fi->fib_prefsrc = cfg->fc_prefsrc;
fi->fib_type = cfg->fc_type;
+ fi->fib_tb_id = cfg->fc_table;
fi->fib_nhs = nhs;
change_nexthops(fi) {
@@ -1337,18 +1338,21 @@
* referring to it.
* - device went down -> we must shutdown all nexthops going via it.
*/
-int fib_sync_down_addr(struct net *net, __be32 local)
+int fib_sync_down_addr(struct net_device *dev, __be32 local)
{
int ret = 0;
unsigned int hash = fib_laddr_hashfn(local);
struct hlist_head *head = &fib_info_laddrhash[hash];
+ struct net *net = dev_net(dev);
+ int tb_id = l3mdev_fib_table(dev);
struct fib_info *fi;
if (!fib_info_laddrhash || local == 0)
return 0;
hlist_for_each_entry(fi, head, fib_lhash) {
- if (!net_eq(fi->fib_net, net))
+ if (!net_eq(fi->fib_net, net) ||
+ fi->fib_tb_id != tb_id)
continue;
if (fi->fib_prefsrc == local) {
fi->fib_flags |= RTNH_F_DEAD;
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index c24f41c..2c2553b 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -46,6 +46,7 @@
.eval = nft_reject_ipv4_eval,
.init = nft_reject_init,
.dump = nft_reject_dump,
+ .validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_ipv4_type __read_mostly = {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 54d9f9b..4e777a3 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -150,6 +150,7 @@
tp->segs_in = 0;
tcp_segs_in(tp, skb);
__skb_pull(skb, tcp_hdrlen(skb));
+ sk_forced_mem_schedule(sk, skb->truesize);
skb_set_owner_r(skb, sk);
TCP_SKB_CB(skb)->seq++;
@@ -226,6 +227,7 @@
tcp_fastopen_add_skb(child, skb);
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt;
+ tp->rcv_wup = tp->rcv_nxt;
/* tcp_conn_request() is sending the SYNACK,
* and queues the child into listener accept queue.
*/
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 028eb04..9c5fc97 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -76,7 +76,7 @@
if (!tcp_is_cwnd_limited(sk))
return;
- if (tp->snd_cwnd <= tp->snd_ssthresh)
+ if (tcp_in_slow_start(tp))
tcp_slow_start(tp, acked);
else if (!yeah->doing_reno_now) {
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index b644a23..41f5b50 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -29,7 +29,7 @@
memset(fl4, 0, sizeof(*fl4));
fl4->daddr = daddr->a4;
fl4->flowi4_tos = tos;
- fl4->flowi4_oif = oif;
+ fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif);
if (saddr)
fl4->saddr = saddr->a4;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f418d2e..2f1f5d4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -778,7 +778,14 @@
}
if (p == &net->ipv6.devconf_all->forwarding) {
+ int old_dflt = net->ipv6.devconf_dflt->forwarding;
+
net->ipv6.devconf_dflt->forwarding = newf;
+ if ((!newf) ^ (!old_dflt))
+ inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ NETCONFA_IFINDEX_DEFAULT,
+ net->ipv6.devconf_dflt);
+
addrconf_forward_change(net, newf);
if ((!newf) ^ (!old))
inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
@@ -1941,6 +1948,7 @@
spin_unlock_bh(&ifp->lock);
addrconf_mod_dad_work(ifp, 0);
+ in6_ifa_put(ifp);
}
/* Join to solicited addr multicast group.
@@ -3850,6 +3858,7 @@
addrconf_dad_begin(ifp);
goto out;
} else if (action == DAD_ABORT) {
+ in6_ifa_hold(ifp);
addrconf_dad_stop(ifp, 1);
if (disable_ipv6)
addrconf_ifdown(idev->dev, 0);
@@ -6025,7 +6034,7 @@
static int __addrconf_sysctl_register(struct net *net, char *dev_name,
struct inet6_dev *idev, struct ipv6_devconf *p)
{
- int i;
+ int i, ifindex;
struct ctl_table *table;
char path[sizeof("net/ipv6/conf/") + IFNAMSIZ];
@@ -6045,6 +6054,13 @@
if (!p->sysctl_header)
goto free;
+ if (!strcmp(dev_name, "all"))
+ ifindex = NETCONFA_IFINDEX_ALL;
+ else if (!strcmp(dev_name, "default"))
+ ifindex = NETCONFA_IFINDEX_DEFAULT;
+ else
+ ifindex = idev->dev->ifindex;
+ inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
return 0;
free:
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 7b0481e..888543d 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1174,6 +1174,7 @@
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+ fl6.flowi6_proto = IPPROTO_IPIP;
dsfield = ipv4_get_dsfield(iph);
@@ -1233,6 +1234,7 @@
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+ fl6.flowi6_proto = IPPROTO_IPV6;
dsfield = ipv6_get_dsfield(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index 533cd57..92bda99 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -47,6 +47,7 @@
.eval = nft_reject_ipv6_eval,
.init = nft_reject_init,
.dump = nft_reject_dump,
+ .validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 0900352..0e983b6 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -126,8 +126,10 @@
rt = (struct rt6_info *) dst;
np = inet6_sk(sk);
- if (!np)
- return -EBADF;
+ if (!np) {
+ err = -EBADF;
+ goto dst_err_out;
+ }
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
@@ -163,6 +165,9 @@
}
release_sock(sk);
+dst_err_out:
+ dst_release(dst);
+
if (err)
return err;
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 0eaab1f..00a2d40 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -23,6 +23,7 @@
int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
{
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
return xfrm_input(skb, nexthdr, spi, 0);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 6cc9700..70a86ad 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -36,7 +36,7 @@
int err;
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_oif = oif;
+ fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif);
fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index cb39e05..4116932 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -13,6 +13,7 @@
#include <linux/socket.h>
#include <linux/uaccess.h>
#include <linux/workqueue.h>
+#include <linux/syscalls.h>
#include <net/kcm.h>
#include <net/netns/generic.h>
#include <net/sock.h>
@@ -2029,7 +2030,7 @@
if (copy_to_user((void __user *)arg, &info,
sizeof(info))) {
err = -EFAULT;
- sock_release(newsock);
+ sys_close(info.fd);
}
}
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1e40dac..a2ed3bd 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1855,6 +1855,9 @@
(void)l2tp_tunnel_delete(tunnel);
}
rcu_read_unlock_bh();
+
+ flush_workqueue(l2tp_wq);
+ rcu_barrier();
}
static struct pernet_operations l2tp_net_ops = {
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index b5d28f1..afca7d1 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -333,10 +333,11 @@
if (!uc.center_freq1)
return;
- /* proceed to downgrade the chandef until usable or the same */
+ /* proceed to downgrade the chandef until usable or the same as AP BW */
while (uc.width > max_width ||
- !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc,
- sdata->wdev.iftype))
+ (uc.width > sta->tdls_chandef.width &&
+ !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc,
+ sdata->wdev.iftype)))
ieee80211_chandef_downgrade(&uc);
if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) {
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
index 5eefe4a..75d696f 100644
--- a/net/netfilter/nf_tables_netdev.c
+++ b/net/netfilter/nf_tables_netdev.c
@@ -30,7 +30,6 @@
if (!iph)
return;
- iph = ip_hdr(skb);
if (iph->ihl < 5 || iph->version != 4)
return;
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 70eb2f6a..d44d89b 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -343,12 +343,12 @@
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const tb[])
{
- char *acct_name;
- struct nf_acct *cur;
+ struct nf_acct *cur, *tmp;
int ret = -ENOENT;
+ char *acct_name;
if (!tb[NFACCT_NAME]) {
- list_for_each_entry(cur, &net->nfnl_acct_list, head)
+ list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head)
nfnl_acct_try_del(cur);
return 0;
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 68216cd..139e086 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -98,31 +98,28 @@
break;
}
- l4proto = nf_ct_l4proto_find_get(l3num, l4num);
-
- /* This protocol is not supportted, skip. */
- if (l4proto->l4proto != l4num) {
- ret = -EOPNOTSUPP;
- goto err_proto_put;
- }
-
if (matching) {
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
/* You cannot replace one timeout policy by another of
* different kind, sorry.
*/
if (matching->l3num != l3num ||
- matching->l4proto->l4proto != l4num) {
- ret = -EINVAL;
- goto err_proto_put;
- }
+ matching->l4proto->l4proto != l4num)
+ return -EINVAL;
- ret = ctnl_timeout_parse_policy(&matching->data,
- l4proto, net,
- cda[CTA_TIMEOUT_DATA]);
- return ret;
+ return ctnl_timeout_parse_policy(&matching->data,
+ matching->l4proto, net,
+ cda[CTA_TIMEOUT_DATA]);
}
- ret = -EBUSY;
+
+ return -EBUSY;
+ }
+
+ l4proto = nf_ct_l4proto_find_get(l3num, l4num);
+
+ /* This protocol is not supportted, skip. */
+ if (l4proto->l4proto != l4num) {
+ ret = -EOPNOTSUPP;
goto err_proto_put;
}
@@ -305,7 +302,16 @@
const struct hlist_nulls_node *nn;
unsigned int last_hsize;
spinlock_t *lock;
- int i;
+ int i, cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_bh(&pcpu->lock);
+ hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode)
+ untimeout(h, timeout);
+ spin_unlock_bh(&pcpu->lock);
+ }
local_bh_disable();
restart:
@@ -350,12 +356,13 @@
const struct nlmsghdr *nlh,
const struct nlattr * const cda[])
{
- struct ctnl_timeout *cur;
+ struct ctnl_timeout *cur, *tmp;
int ret = -ENOENT;
char *name;
if (!cda[CTA_TIMEOUT_NAME]) {
- list_for_each_entry(cur, &net->nfct_timeout_list, head)
+ list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list,
+ head)
ctnl_timeout_try_del(net, cur);
return 0;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 2863f34..8a6bc76 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -291,10 +291,16 @@
}
EXPORT_SYMBOL_GPL(nft_meta_get_init);
-static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx)
+int nft_meta_set_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
{
+ struct nft_meta *priv = nft_expr_priv(expr);
unsigned int hooks;
+ if (priv->key != NFT_META_PKTTYPE)
+ return 0;
+
switch (ctx->afi->family) {
case NFPROTO_BRIDGE:
hooks = 1 << NF_BR_PRE_ROUTING;
@@ -308,6 +314,7 @@
return nft_chain_validate_hooks(ctx->chain, hooks);
}
+EXPORT_SYMBOL_GPL(nft_meta_set_validate);
int nft_meta_set_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
@@ -327,15 +334,16 @@
len = sizeof(u8);
break;
case NFT_META_PKTTYPE:
- err = nft_meta_set_init_pkttype(ctx);
- if (err)
- return err;
len = sizeof(u8);
break;
default:
return -EOPNOTSUPP;
}
+ err = nft_meta_set_validate(ctx, expr, NULL);
+ if (err < 0)
+ return err;
+
priv->sreg = nft_parse_register(tb[NFTA_META_SREG]);
err = nft_validate_register_load(priv->sreg, len);
if (err < 0)
@@ -407,6 +415,7 @@
.init = nft_meta_set_init,
.destroy = nft_meta_set_destroy,
.dump = nft_meta_set_dump,
+ .validate = nft_meta_set_validate,
};
static const struct nft_expr_ops *
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index 0522fc9..c64de3f7 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -26,11 +26,27 @@
};
EXPORT_SYMBOL_GPL(nft_reject_policy);
+int nft_reject_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ return nft_chain_validate_hooks(ctx->chain,
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_LOCAL_OUT));
+}
+EXPORT_SYMBOL_GPL(nft_reject_validate);
+
int nft_reject_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
+ int err;
+
+ err = nft_reject_validate(ctx, expr, NULL);
+ if (err < 0)
+ return err;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 759ca52..e79d9ca 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -66,7 +66,11 @@
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code;
+ int icmp_code, err;
+
+ err = nft_reject_validate(ctx, expr, NULL);
+ if (err < 0)
+ return err;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
@@ -124,6 +128,7 @@
.eval = nft_reject_inet_eval,
.init = nft_reject_inet_init,
.dump = nft_reject_inet_dump,
+ .validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_inet_type __read_mostly = {
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 1f1682b..31b7bc3 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -878,7 +878,7 @@
struct sctp_chunk *chunk,
u16 chunk_len)
{
- size_t psize, pmtu;
+ size_t psize, pmtu, maxsize;
sctp_xmit_t retval = SCTP_XMIT_OK;
psize = packet->size;
@@ -906,6 +906,17 @@
goto out;
}
+ /* Similarly, if this chunk was built before a PMTU
+ * reduction, we have to fragment it at IP level now. So
+ * if the packet already contains something, we need to
+ * flush.
+ */
+ maxsize = pmtu - packet->overhead;
+ if (packet->auth)
+ maxsize -= WORD_ROUND(packet->auth->skb->len);
+ if (chunk_len > maxsize)
+ retval = SCTP_XMIT_PMTU_FULL;
+
/* It is also okay to fragment if the chunk we are
* adding is a control chunk, but only if current packet
* is not a GSO one otherwise it causes fragmentation of
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 536d0be..799cce6 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -51,6 +51,7 @@
#include <linux/slab.h>
#include <linux/prefetch.h>
#include <linux/sunrpc/addr.h>
+#include <linux/sunrpc/svc_rdma.h>
#include <asm/bitops.h>
#include <linux/module.h> /* try_module_get()/module_put() */
@@ -923,7 +924,7 @@
}
INIT_LIST_HEAD(&buf->rb_recv_bufs);
- for (i = 0; i < buf->rb_max_requests; i++) {
+ for (i = 0; i < buf->rb_max_requests + RPCRDMA_MAX_BC_REQUESTS; i++) {
struct rpcrdma_rep *rep;
rep = rpcrdma_create_rep(r_xprt);
@@ -1018,6 +1019,7 @@
rep = rpcrdma_buffer_get_rep_locked(buf);
rpcrdma_destroy_rep(ia, rep);
}
+ buf->rb_send_count = 0;
spin_lock(&buf->rb_reqslock);
while (!list_empty(&buf->rb_allreqs)) {
@@ -1032,6 +1034,7 @@
spin_lock(&buf->rb_reqslock);
}
spin_unlock(&buf->rb_reqslock);
+ buf->rb_recv_count = 0;
rpcrdma_destroy_mrs(buf);
}
@@ -1074,8 +1077,27 @@
spin_unlock(&buf->rb_mwlock);
}
+static struct rpcrdma_rep *
+rpcrdma_buffer_get_rep(struct rpcrdma_buffer *buffers)
+{
+ /* If an RPC previously completed without a reply (say, a
+ * credential problem or a soft timeout occurs) then hold off
+ * on supplying more Receive buffers until the number of new
+ * pending RPCs catches up to the number of posted Receives.
+ */
+ if (unlikely(buffers->rb_send_count < buffers->rb_recv_count))
+ return NULL;
+
+ if (unlikely(list_empty(&buffers->rb_recv_bufs)))
+ return NULL;
+ buffers->rb_recv_count++;
+ return rpcrdma_buffer_get_rep_locked(buffers);
+}
+
/*
* Get a set of request/reply buffers.
+ *
+ * Reply buffer (if available) is attached to send buffer upon return.
*/
struct rpcrdma_req *
rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
@@ -1085,21 +1107,15 @@
spin_lock(&buffers->rb_lock);
if (list_empty(&buffers->rb_send_bufs))
goto out_reqbuf;
+ buffers->rb_send_count++;
req = rpcrdma_buffer_get_req_locked(buffers);
- if (list_empty(&buffers->rb_recv_bufs))
- goto out_repbuf;
- req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers);
+ req->rl_reply = rpcrdma_buffer_get_rep(buffers);
spin_unlock(&buffers->rb_lock);
return req;
out_reqbuf:
spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of request buffers (%p)\n", buffers);
- return NULL;
-out_repbuf:
- list_add(&req->rl_free, &buffers->rb_send_bufs);
- spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers);
+ pr_warn("RPC: %s: out of request buffers\n", __func__);
return NULL;
}
@@ -1117,9 +1133,12 @@
req->rl_reply = NULL;
spin_lock(&buffers->rb_lock);
+ buffers->rb_send_count--;
list_add_tail(&req->rl_free, &buffers->rb_send_bufs);
- if (rep)
+ if (rep) {
+ buffers->rb_recv_count--;
list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
+ }
spin_unlock(&buffers->rb_lock);
}
@@ -1133,8 +1152,7 @@
struct rpcrdma_buffer *buffers = req->rl_buffer;
spin_lock(&buffers->rb_lock);
- if (!list_empty(&buffers->rb_recv_bufs))
- req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers);
+ req->rl_reply = rpcrdma_buffer_get_rep(buffers);
spin_unlock(&buffers->rb_lock);
}
@@ -1148,6 +1166,7 @@
struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf;
spin_lock(&buffers->rb_lock);
+ buffers->rb_recv_count--;
list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
spin_unlock(&buffers->rb_lock);
}
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 670fad5..a71b0f5 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -321,6 +321,7 @@
char *rb_pool;
spinlock_t rb_lock; /* protect buf lists */
+ int rb_send_count, rb_recv_count;
struct list_head rb_send_bufs;
struct list_head rb_recv_bufs;
u32 rb_max_requests;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 8ede3bc..bf16883 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1074,7 +1074,7 @@
skb = skb_recv_datagram(sk, 0, 1, &err);
if (skb != NULL) {
xs_udp_data_read_skb(&transport->xprt, sk, skb);
- skb_free_datagram(sk, skb);
+ skb_free_datagram_locked(sk, skb);
continue;
}
if (!test_and_clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 6b626a6..a04fe9b 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -62,6 +62,8 @@
/**
* named_prepare_buf - allocate & initialize a publication message
+ *
+ * The buffer returned is of size INT_H_SIZE + payload size
*/
static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size,
u32 dest)
@@ -141,9 +143,9 @@
struct publication *publ;
struct sk_buff *skb = NULL;
struct distr_item *item = NULL;
- uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) *
- ITEM_SIZE;
- uint msg_rem = msg_dsz;
+ u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) /
+ ITEM_SIZE) * ITEM_SIZE;
+ u32 msg_rem = msg_dsz;
list_for_each_entry(publ, pls, local_list) {
/* Prepare next buffer: */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index f1dffe8..8309687 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -661,11 +661,11 @@
{
struct unix_sock *u = unix_sk(sk);
- if (mutex_lock_interruptible(&u->readlock))
+ if (mutex_lock_interruptible(&u->iolock))
return -EINTR;
sk->sk_peek_off = val;
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
return 0;
}
@@ -779,7 +779,8 @@
spin_lock_init(&u->lock);
atomic_long_set(&u->inflight, 0);
INIT_LIST_HEAD(&u->link);
- mutex_init(&u->readlock); /* single task reading lock */
+ mutex_init(&u->iolock); /* single task reading lock */
+ mutex_init(&u->bindlock); /* single task binding lock */
init_waitqueue_head(&u->peer_wait);
init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
unix_insert_socket(unix_sockets_unbound(sk), sk);
@@ -848,7 +849,7 @@
int err;
unsigned int retries = 0;
- err = mutex_lock_interruptible(&u->readlock);
+ err = mutex_lock_interruptible(&u->bindlock);
if (err)
return err;
@@ -895,7 +896,7 @@
spin_unlock(&unix_table_lock);
err = 0;
-out: mutex_unlock(&u->readlock);
+out: mutex_unlock(&u->bindlock);
return err;
}
@@ -954,20 +955,32 @@
return NULL;
}
-static int unix_mknod(struct dentry *dentry, const struct path *path, umode_t mode,
- struct path *res)
+static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
{
- int err;
+ struct dentry *dentry;
+ struct path path;
+ int err = 0;
+ /*
+ * Get the parent directory, calculate the hash for last
+ * component.
+ */
+ dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+ err = PTR_ERR(dentry);
+ if (IS_ERR(dentry))
+ return err;
- err = security_path_mknod(path, dentry, mode, 0);
+ /*
+ * All right, let's create it.
+ */
+ err = security_path_mknod(&path, dentry, mode, 0);
if (!err) {
- err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
+ err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
if (!err) {
- res->mnt = mntget(path->mnt);
+ res->mnt = mntget(path.mnt);
res->dentry = dget(dentry);
}
}
-
+ done_path_create(&path, dentry);
return err;
}
@@ -978,12 +991,10 @@
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
char *sun_path = sunaddr->sun_path;
- int err, name_err;
+ int err;
unsigned int hash;
struct unix_address *addr;
struct hlist_head *list;
- struct path path;
- struct dentry *dentry;
err = -EINVAL;
if (sunaddr->sun_family != AF_UNIX)
@@ -999,34 +1010,14 @@
goto out;
addr_len = err;
- name_err = 0;
- dentry = NULL;
- if (sun_path[0]) {
- /* Get the parent directory, calculate the hash for last
- * component.
- */
- dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-
- if (IS_ERR(dentry)) {
- /* delay report until after 'already bound' check */
- name_err = PTR_ERR(dentry);
- dentry = NULL;
- }
- }
-
- err = mutex_lock_interruptible(&u->readlock);
+ err = mutex_lock_interruptible(&u->bindlock);
if (err)
- goto out_path;
+ goto out;
err = -EINVAL;
if (u->addr)
goto out_up;
- if (name_err) {
- err = name_err == -EEXIST ? -EADDRINUSE : name_err;
- goto out_up;
- }
-
err = -ENOMEM;
addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
if (!addr)
@@ -1037,11 +1028,11 @@
addr->hash = hash ^ sk->sk_type;
atomic_set(&addr->refcnt, 1);
- if (dentry) {
- struct path u_path;
+ if (sun_path[0]) {
+ struct path path;
umode_t mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
- err = unix_mknod(dentry, &path, mode, &u_path);
+ err = unix_mknod(sun_path, mode, &path);
if (err) {
if (err == -EEXIST)
err = -EADDRINUSE;
@@ -1049,9 +1040,9 @@
goto out_up;
}
addr->hash = UNIX_HASH_SIZE;
- hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+ hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
spin_lock(&unix_table_lock);
- u->path = u_path;
+ u->path = path;
list = &unix_socket_table[hash];
} else {
spin_lock(&unix_table_lock);
@@ -1073,11 +1064,7 @@
out_unlock:
spin_unlock(&unix_table_lock);
out_up:
- mutex_unlock(&u->readlock);
-out_path:
- if (dentry)
- done_path_create(&path, dentry);
-
+ mutex_unlock(&u->bindlock);
out:
return err;
}
@@ -1969,17 +1956,17 @@
if (false) {
alloc_skb:
unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->readlock);
+ mutex_unlock(&unix_sk(other)->iolock);
newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
&err, 0);
if (!newskb)
goto err;
}
- /* we must acquire readlock as we modify already present
+ /* we must acquire iolock as we modify already present
* skbs in the sk_receive_queue and mess with skb->len
*/
- err = mutex_lock_interruptible(&unix_sk(other)->readlock);
+ err = mutex_lock_interruptible(&unix_sk(other)->iolock);
if (err) {
err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
goto err;
@@ -2046,7 +2033,7 @@
}
unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->readlock);
+ mutex_unlock(&unix_sk(other)->iolock);
other->sk_data_ready(other);
scm_destroy(&scm);
@@ -2055,7 +2042,7 @@
err_state_unlock:
unix_state_unlock(other);
err_unlock:
- mutex_unlock(&unix_sk(other)->readlock);
+ mutex_unlock(&unix_sk(other)->iolock);
err:
kfree_skb(newskb);
if (send_sigpipe && !(flags & MSG_NOSIGNAL))
@@ -2123,7 +2110,7 @@
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
skip = sk_peek_offset(sk, flags);
skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err,
@@ -2131,14 +2118,14 @@
if (skb)
break;
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
if (err != -EAGAIN)
break;
} while (timeo &&
!__skb_wait_for_more_packets(sk, &err, &timeo, last));
- if (!skb) { /* implies readlock unlocked */
+ if (!skb) { /* implies iolock unlocked */
unix_state_lock(sk);
/* Signal EOF on disconnected non-blocking SEQPACKET socket. */
if (sk->sk_type == SOCK_SEQPACKET && err == -EAGAIN &&
@@ -2203,7 +2190,7 @@
out_free:
skb_free_datagram(sk, skb);
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
out:
return err;
}
@@ -2298,7 +2285,7 @@
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
*/
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
if (flags & MSG_PEEK)
skip = sk_peek_offset(sk, flags);
@@ -2340,7 +2327,7 @@
break;
}
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
timeo = unix_stream_data_wait(sk, timeo, last,
last_len);
@@ -2351,7 +2338,7 @@
goto out;
}
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
goto redo;
unlock:
unix_state_unlock(sk);
@@ -2454,7 +2441,7 @@
}
} while (size);
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
if (state->msg)
scm_recv(sock, state->msg, &scm, flags);
else
@@ -2495,9 +2482,9 @@
int ret;
struct unix_sock *u = unix_sk(sk);
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
ret = splice_to_pipe(pipe, spd);
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
return ret;
}
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index dbb2738e..6250b1c 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -958,29 +958,8 @@
return private(dev, iwr, cmd, info, handler);
}
/* Old driver API : call driver ioctl handler */
- if (dev->netdev_ops->ndo_do_ioctl) {
-#ifdef CONFIG_COMPAT
- if (info->flags & IW_REQUEST_FLAG_COMPAT) {
- int ret = 0;
- struct iwreq iwr_lcl;
- struct compat_iw_point *iwp_compat = (void *) &iwr->u.data;
-
- memcpy(&iwr_lcl, iwr, sizeof(struct iwreq));
- iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer);
- iwr_lcl.u.data.length = iwp_compat->length;
- iwr_lcl.u.data.flags = iwp_compat->flags;
-
- ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd);
-
- iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer);
- iwp_compat->length = iwr_lcl.u.data.length;
- iwp_compat->flags = iwr_lcl.u.data.flags;
-
- return ret;
- } else
-#endif
- return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
- }
+ if (dev->netdev_ops->ndo_do_ioctl)
+ return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
return -EOPNOTSUPP;
}
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 1c4ad47..6e3f025 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -207,15 +207,15 @@
family = XFRM_SPI_SKB_CB(skb)->family;
/* if tunnel is present override skb->mark value with tunnel i_key */
- if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) {
- switch (family) {
- case AF_INET:
+ switch (family) {
+ case AF_INET:
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4)
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
- break;
- case AF_INET6:
+ break;
+ case AF_INET6:
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6)
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
- break;
- }
+ break;
}
/* Allocate new secpath or COW existing one. */
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b5e665b..45f9cf9 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -626,6 +626,10 @@
/* re-insert all policies by order of creation */
list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+ if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) {
+ /* skip socket policies */
+ continue;
+ }
newpos = NULL;
chain = policy_hash_bysel(net, &policy->selector,
policy->family,
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d516845..cb65d91 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -896,7 +896,8 @@
struct sock *sk = cb->skb->sk;
struct net *net = sock_net(sk);
- xfrm_state_walk_done(walk, net);
+ if (cb->args[0])
+ xfrm_state_walk_done(walk, net);
return 0;
}
@@ -921,8 +922,6 @@
u8 proto = 0;
int err;
- cb->args[0] = 1;
-
err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX,
xfrma_policy);
if (err < 0)
@@ -939,6 +938,7 @@
proto = nla_get_u8(attrs[XFRMA_PROTO]);
xfrm_state_walk_init(walk, proto, filter);
+ cb->args[0] = 1;
}
(void) xfrm_state_walk(net, walk, dump_one_state, &info);
@@ -2051,9 +2051,6 @@
if (up->hard) {
xfrm_policy_delete(xp, p->dir);
xfrm_audit_policy_delete(xp, 1, true);
- } else {
- // reset the timers here?
- WARN(1, "Don't know what to do with soft policy expire\n");
}
km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid);
@@ -2117,7 +2114,7 @@
err = verify_newpolicy_info(&ua->policy);
if (err)
- goto bad_policy;
+ goto free_state;
/* build an XP */
xp = xfrm_policy_construct(net, &ua->policy, attrs, &err);
@@ -2149,8 +2146,6 @@
return 0;
-bad_policy:
- WARN(1, "BAD policy passed\n");
free_state:
kfree(x);
nomem:
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index d9836c5..11c8d9b 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -3266,6 +3266,9 @@
}
}
+ /* If we exit via err(), this kills all the threads, restores tty. */
+ atexit(cleanup_devices);
+
/* We always have a console device, and it's always device 1. */
setup_console();
@@ -3369,9 +3372,6 @@
/* Ensure that we terminate if a device-servicing child dies. */
signal(SIGCHLD, kill_launcher);
- /* If we exit via err(), this kills all the threads, restores tty. */
- atexit(cleanup_devices);
-
/* If requested, chroot to a directory */
if (chroot_path) {
if (chroot(chroot_path) != 0)