Commit c4ba68b8691e4 backported from upstream to 4.14 stable was probably applied wrongly, and instead of calling sfp_register_socket in sfp_probe, the socket registering code was put into sfp_remove. This is obviously wrong.

The commit first appeared in 4.14.104. Fix it for the next 4.14 release.

Fixes: c4ba68b8691e4 ("net: sfp: do not probe SFP module before we're attached") Cc: stable stable@vger.kernel.org Cc: Russell King rmk+kernel@armlinux.org.uk Cc: David S. Miller davem@davemloft.net Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Sasha Levin sashal@kernel.org Signed-off-by: Marek Behún marek.behun@nic.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/sfp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index a1b68b19d912..5ab725a571a8 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -878,6 +878,10 @@ static int sfp_probe(struct platform_device *pdev) if (poll) mod_delayed_work(system_wq, &sfp->poll, poll_jiffies);

+ sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); + if (!sfp->sfp_bus) + return -ENOMEM; + return 0; }

@@ -887,10 +891,6 @@ static int sfp_remove(struct platform_device *pdev)

sfp_unregister_socket(sfp->sfp_bus);

- sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); - if (!sfp->sfp_bus) - return -ENOMEM; - return 0; }

[ Upstream commit 090edbe23ff57940fca7f57d9165ce57a826bd7a ]

x86_64's saved_context nonsensically used separate idt_limit and idt_base fields and then cast &idt_limit to struct desc_ptr *.

This was correct (with -fno-strict-aliasing), but it's confusing, served no purpose, and required #ifdeffery. Simplify this by using struct desc_ptr directly.

No change in functionality.

Tested-by: Jarkko Nikula jarkko.nikula@linux.intel.com Signed-off-by: Andy Lutomirski luto@kernel.org Acked-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Acked-by: Thomas Gleixner tglx@linutronix.de Cc: Borislav Petkov bpetkov@suse.de Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Pavel Machek pavel@ucw.cz Cc: Peter Zijlstra peterz@infradead.org Cc: Rafael J. Wysocki rjw@rjwysocki.net Cc: Zhang Rui rui.zhang@intel.com Link: http://lkml.kernel.org/r/967909ce38d341b01d45eff53e278e2728a3a93a.1513286253... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/suspend_64.h | 3 +-- arch/x86/power/cpu.c | 11 +---------- 2 files changed, 2 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 7306e911faee..600e9e0aea51 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -30,8 +30,7 @@ struct saved_context { u16 gdt_pad; /* Unused */ struct desc_ptr gdt_desc; u16 idt_pad; - u16 idt_limit; - unsigned long idt_base; + struct desc_ptr idt; u16 ldt; u16 tss; unsigned long tr; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index a51d2dfb57d1..cba2e2c3f89e 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -82,12 +82,8 @@ static void __save_processor_state(struct saved_context *ctxt) /* * descriptor tables */ -#ifdef CONFIG_X86_32 store_idt(&ctxt->idt); -#else -/* CONFIG_X86_64 */ - store_idt((struct desc_ptr *)&ctxt->idt_limit); -#endif + /* * We save it here, but restore it only in the hibernate case. * For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit @@ -221,12 +217,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) * now restore the descriptor tables to their proper values * ltr is done i fix_processor_context(). */ -#ifdef CONFIG_X86_32 load_idt(&ctxt->idt); -#else -/* CONFIG_X86_64 */ - load_idt((const struct desc_ptr *)&ctxt->idt_limit); -#endif

#ifdef CONFIG_X86_64 /*

[ Upstream commit 896c80bef4d3b357814a476663158aaf669d0fb3 ]

x86_64 restores system call MSRs in fix_processor_context(), and x86_32 restored them along with segment registers. The 64-bit variant makes more sense, so move the 32-bit code to match the 64-bit code.

No side effects are expected to runtime behavior.

Tested-by: Jarkko Nikula jarkko.nikula@linux.intel.com Signed-off-by: Andy Lutomirski luto@kernel.org Acked-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Acked-by: Thomas Gleixner tglx@linutronix.de Cc: Borislav Petkov bpetkov@suse.de Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Pavel Machek pavel@ucw.cz Cc: Peter Zijlstra peterz@infradead.org Cc: Rafael J. Wysocki rjw@rjwysocki.net Cc: Zhang Rui rui.zhang@intel.com Link: http://lkml.kernel.org/r/65158f8d7ee64dd6bbc6c1c83b3b34aaa854e3ae.1513286253... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/power/cpu.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index cba2e2c3f89e..8e1668470b23 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -176,6 +176,9 @@ static void fix_processor_context(void) write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS);

syscall_init(); /* This sets MSR_*STAR and related */ +#else + if (boot_cpu_has(X86_FEATURE_SEP)) + enable_sep_cpu(); #endif load_TR_desc(); /* This does ltr */ load_mm_ldt(current->active_mm); /* This does lldt */ @@ -239,12 +242,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) loadsegment(fs, ctxt->fs); loadsegment(gs, ctxt->gs); loadsegment(ss, ctxt->ss); - - /* - * sysenter MSRs - */ - if (boot_cpu_has(X86_FEATURE_SEP)) - enable_sep_cpu(); #else /* CONFIG_X86_64 */ asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));

[ Upstream commit 663a50ceac75c2208d2ad95365bc8382fd42f44d ]

shadow mm's pin count got increased in workload preparation phase, which is after workload scanning. it will get decreased in complete_current_workload() anyway after workload completion. Sometimes, if a workload meets a scanning error, its shadow mm pin count will not get increased but will get decreased in the end. This patch lets shadow mm's pin count not go below 0.

Fixes: 2707e4446688 ("drm/i915/gvt: vGPU graphics memory virtualization") Cc: zhenyuw@linux.intel.com Cc: stable@vger.kernel.org #4.14+ Signed-off-by: Yan Zhao yan.y.zhao@intel.com Signed-off-by: Zhenyu Wang zhenyuw@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/i915/gvt/gtt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index dadacbe558ab..1a1f7eb46d1e 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1629,7 +1629,7 @@ void intel_vgpu_unpin_mm(struct intel_vgpu_mm *mm) if (WARN_ON(mm->type != INTEL_GVT_MM_PPGTT)) return;

- atomic_dec(&mm->pincount); + atomic_dec_if_positive(&mm->pincount); }

/**

commit ad15006cc78459d059af56729c4d9bed7c7fd860 upstream.

This causes an issue when trying to build with `make LD=ld.lld` if ld.lld and the rest of your cross tools aren't in the same directory (ex. /usr/local/bin) (as is the case for Android's build system), as the GCC_TOOLCHAIN_DIR then gets set based on `which $(LD)` which will point where LLVM tools are, not GCC/binutils tools are located.

Instead, select the GCC_TOOLCHAIN_DIR based on another tool provided by binutils for which LLVM does not provide a substitute for, such as elfedit.

Fixes: 785f11aa595b ("kbuild: Add better clang cross build support") Link: https://github.com/ClangBuiltLinux/linux/issues/341 Suggested-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Nathan Chancellor natechancellor@gmail.com Tested-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile index da223c660c9a..85753250984c 100644 --- a/Makefile +++ b/Makefile @@ -480,7 +480,7 @@ endif ifeq ($(cc-name),clang) ifneq ($(CROSS_COMPILE),) CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) -GCC_TOOLCHAIN_DIR := $(dir $(shell which $(LD))) +GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) endif

[ Upstream commit 5f074f3e192f10c9fade898b9b3b8812e3d83342 ]

A recent optimization in Clang (r355672) lowers comparisons of the return value of memcmp against zero to comparisons of the return value of bcmp against zero. This helps some platforms that implement bcmp more efficiently than memcmp. glibc simply aliases bcmp to memcmp, but an optimized implementation is in the works.

This results in linkage failures for all targets with Clang due to the undefined symbol. For now, just implement bcmp as a tailcail to memcmp to unbreak the build. This routine can be further optimized in the future.

Other ideas discussed:

* A weak alias was discussed, but breaks for architectures that define their own implementations of memcmp since aliases to declarations are not permitted (only definitions). Arch-specific memcmp implementations typically declare memcmp in C headers, but implement them in assembly.

* -ffreestanding also is used sporadically throughout the kernel.

* -fno-builtin-bcmp doesn't work when doing LTO.

Link: https://bugs.llvm.org/show_bug.cgi?id=41035 Link: https://code.woboq.org/userspace/glibc/string/memcmp.c.html#bcmp Link: https://github.com/llvm/llvm-project/commit/8e16d73346f8091461319a7dfc4ddd18... Link: https://github.com/ClangBuiltLinux/linux/issues/416 Link: http://lkml.kernel.org/r/20190313211335.165605-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers ndesaulniers@google.com Reported-by: Nathan Chancellor natechancellor@gmail.com Reported-by: Adhemerval Zanella adhemerval.zanella@linaro.org Suggested-by: Arnd Bergmann arnd@arndb.de Suggested-by: James Y Knight jyknight@google.com Suggested-by: Masahiro Yamada yamada.masahiro@socionext.com Suggested-by: Nathan Chancellor natechancellor@gmail.com Suggested-by: Rasmus Villemoes linux@rasmusvillemoes.dk Acked-by: Steven Rostedt (VMware) rostedt@goodmis.org Reviewed-by: Nathan Chancellor natechancellor@gmail.com Tested-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Masahiro Yamada yamada.masahiro@socionext.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: David Laight David.Laight@ACULAB.COM Cc: Rasmus Villemoes linux@rasmusvillemoes.dk Cc: Namhyung Kim namhyung@kernel.org Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Dan Williams dan.j.williams@intel.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/string.h | 3 +++ lib/string.c | 20 ++++++++++++++++++++ 2 files changed, 23 insertions(+)

diff --git a/include/linux/string.h b/include/linux/string.h index 96115bf561b4..3d43329c20be 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -142,6 +142,9 @@ extern void * memscan(void *,int,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif +#ifndef __HAVE_ARCH_BCMP +extern int bcmp(const void *,const void *,__kernel_size_t); +#endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif diff --git a/lib/string.c b/lib/string.c index 5e8d410a93df..1530643edf00 100644 --- a/lib/string.c +++ b/lib/string.c @@ -865,6 +865,26 @@ __visible int memcmp(const void *cs, const void *ct, size_t count) EXPORT_SYMBOL(memcmp); #endif

+#ifndef __HAVE_ARCH_BCMP +/** + * bcmp - returns 0 if and only if the buffers have identical contents. + * @a: pointer to first buffer. + * @b: pointer to second buffer. + * @len: size of buffers. + * + * The sign or magnitude of a non-zero return value has no particular + * meaning, and architectures may implement their own more efficient bcmp(). So + * while this particular implementation is a simple (tail) call to memcmp, do + * not rely on anything but whether the return value is zero or non-zero. + */ +#undef bcmp +int bcmp(const void *a, const void *b, size_t len) +{ + return memcmp(a, b, len); +} +EXPORT_SYMBOL(bcmp); +#endif + #ifndef __HAVE_ARCH_MEMSCAN /** * memscan - Find a character in an area of memory.

[ Upstream commit c8a43c18a97845e7f94ed7d181c11f41964976a2 ]

When KASLR is enabled (CONFIG_RANDOMIZE_BASE=y), the top 4K of kernel virtual address space may be mapped to physical addresses despite being reserved for ERR_PTR values.

Fix the randomization of the linear region so that we avoid mapping the last page of the virtual address space.

Cc: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: liyueyi liyueyi@live.com [will: rewrote commit message; merged in suggestion from Ard] Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin (Microsoft) sashal@kernel.org --- arch/arm64/mm/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index caa295cd5d09..9e6c822d458d 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -447,7 +447,7 @@ void __init arm64_memblock_init(void) * memory spans, randomize the linear region as well. */ if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) { - range = range / ARM64_MEMSTART_ALIGN + 1; + range /= ARM64_MEMSTART_ALIGN; memstart_addr -= ARM64_MEMSTART_ALIGN * ((range * memstart_offset_seed) >> 16); }

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

commit 7c0cca7c847e6e019d67b7d793efbbe3b947d004 upstream.

By default, the kernel will automatically load the module of any line dicipline that is asked for. As this sometimes isn't the safest thing to do, provide a sysctl to disable this feature.

By default, we set this to 'y' as that is the historical way that Linux has worked, and we do not want to break working systems. But in the future, perhaps this can default to 'n' to prevent this functionality.

Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/tty/Kconfig | 24 ++++++++++++++++++++++++ drivers/tty/tty_io.c | 3 +++ drivers/tty/tty_ldisc.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 74 insertions(+)

--- a/drivers/tty/Kconfig +++ b/drivers/tty/Kconfig @@ -467,4 +467,28 @@ config VCC depends on SUN_LDOMS help Support for Sun logical domain consoles. + +config LDISC_AUTOLOAD + bool "Automatically load TTY Line Disciplines" + default y + help + Historically the kernel has always automatically loaded any + line discipline that is in a kernel module when a user asks + for it to be loaded with the TIOCSETD ioctl, or through other + means. This is not always the best thing to do on systems + where you know you will not be using some of the more + "ancient" line disciplines, so prevent the kernel from doing + this unless the request is coming from a process with the + CAP_SYS_MODULE permissions. + + Say 'Y' here if you trust your userspace users to do the right + thing, or if you have only provided the line disciplines that + you know you will be using, or if you wish to continue to use + the traditional method of on-demand loading of these modules + by any user. + + This functionality can be changed at runtime with the + dev.tty.ldisc_autoload sysctl, this configuration option will + only set the default value of this functionality. + endif # TTY --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -511,6 +511,8 @@ static const struct file_operations hung static DEFINE_SPINLOCK(redirect_lock); static struct file *redirect;

+extern void tty_sysctl_init(void); + /** * tty_wakeup - request more data * @tty: terminal @@ -3332,6 +3334,7 @@ void console_sysfs_notify(void) */ int __init tty_init(void) { + tty_sysctl_init(); cdev_init(&tty_cdev, &tty_fops); if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0) --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -155,6 +155,13 @@ static void put_ldops(struct tty_ldisc_o * takes tty_ldiscs_lock to guard against ldisc races */

+#if defined(CONFIG_LDISC_AUTOLOAD) + #define INITIAL_AUTOLOAD_STATE 1 +#else + #define INITIAL_AUTOLOAD_STATE 0 +#endif +static int tty_ldisc_autoload = INITIAL_AUTOLOAD_STATE; + static struct tty_ldisc *tty_ldisc_get(struct tty_struct *tty, int disc) { struct tty_ldisc *ld; @@ -169,6 +176,8 @@ static struct tty_ldisc *tty_ldisc_get(s */ ldops = get_ldops(disc); if (IS_ERR(ldops)) { + if (!capable(CAP_SYS_MODULE) && !tty_ldisc_autoload) + return ERR_PTR(-EPERM); request_module("tty-ldisc-%d", disc); ldops = get_ldops(disc); if (IS_ERR(ldops)) @@ -841,3 +850,41 @@ void tty_ldisc_deinit(struct tty_struct tty_ldisc_put(tty->ldisc); tty->ldisc = NULL; } + +static int zero; +static int one = 1; +static struct ctl_table tty_table[] = { + { + .procname = "ldisc_autoload", + .data = &tty_ldisc_autoload, + .maxlen = sizeof(tty_ldisc_autoload), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &one, + }, + { } +}; + +static struct ctl_table tty_dir_table[] = { + { + .procname = "tty", + .mode = 0555, + .child = tty_table, + }, + { } +}; + +static struct ctl_table tty_root_table[] = { + { + .procname = "dev", + .mode = 0555, + .child = tty_dir_table, + }, + { } +}; + +void tty_sysctl_init(void) +{ + register_sysctl_table(tty_root_table); +}

From: Lorenzo Bianconi lorenzo.bianconi@redhat.com

[ Upstream commit bb9bd814ebf04f579be466ba61fc922625508807 ]

ipip6 tunnels run iptunnel_pull_header on received skbs. This can determine the following use-after-free accessing iph pointer since the packet will be 'uncloned' running pskb_expand_head if it is a cloned gso skb (e.g if the packet has been sent though a veth device)

[ 706.369655] BUG: KASAN: use-after-free in ipip6_rcv+0x1678/0x16e0 [sit] [ 706.449056] Read of size 1 at addr ffffe01b6bd855f5 by task ksoftirqd/1/= [ 706.669494] Hardware name: HPE ProLiant m400 Server/ProLiant m400 Server, BIOS U02 08/19/2016 [ 706.771839] Call trace: [ 706.801159] dump_backtrace+0x0/0x2f8 [ 706.845079] show_stack+0x24/0x30 [ 706.884833] dump_stack+0xe0/0x11c [ 706.925629] print_address_description+0x68/0x260 [ 706.982070] kasan_report+0x178/0x340 [ 707.025995] __asan_report_load1_noabort+0x30/0x40 [ 707.083481] ipip6_rcv+0x1678/0x16e0 [sit] [ 707.132623] tunnel64_rcv+0xd4/0x200 [tunnel4] [ 707.185940] ip_local_deliver_finish+0x3b8/0x988 [ 707.241338] ip_local_deliver+0x144/0x470 [ 707.289436] ip_rcv_finish+0x43c/0x14b0 [ 707.335447] ip_rcv+0x628/0x1138 [ 707.374151] __netif_receive_skb_core+0x1670/0x2600 [ 707.432680] __netif_receive_skb+0x28/0x190 [ 707.482859] process_backlog+0x1d0/0x610 [ 707.529913] net_rx_action+0x37c/0xf68 [ 707.574882] __do_softirq+0x288/0x1018 [ 707.619852] run_ksoftirqd+0x70/0xa8 [ 707.662734] smpboot_thread_fn+0x3a4/0x9e8 [ 707.711875] kthread+0x2c8/0x350 [ 707.750583] ret_from_fork+0x10/0x18

[ 707.811302] Allocated by task 16982: [ 707.854182] kasan_kmalloc.part.1+0x40/0x108 [ 707.905405] kasan_kmalloc+0xb4/0xc8 [ 707.948291] kasan_slab_alloc+0x14/0x20 [ 707.994309] __kmalloc_node_track_caller+0x158/0x5e0 [ 708.053902] __kmalloc_reserve.isra.8+0x54/0xe0 [ 708.108280] __alloc_skb+0xd8/0x400 [ 708.150139] sk_stream_alloc_skb+0xa4/0x638 [ 708.200346] tcp_sendmsg_locked+0x818/0x2b90 [ 708.251581] tcp_sendmsg+0x40/0x60 [ 708.292376] inet_sendmsg+0xf0/0x520 [ 708.335259] sock_sendmsg+0xac/0xf8 [ 708.377096] sock_write_iter+0x1c0/0x2c0 [ 708.424154] new_sync_write+0x358/0x4a8 [ 708.470162] __vfs_write+0xc4/0xf8 [ 708.510950] vfs_write+0x12c/0x3d0 [ 708.551739] ksys_write+0xcc/0x178 [ 708.592533] __arm64_sys_write+0x70/0xa0 [ 708.639593] el0_svc_handler+0x13c/0x298 [ 708.686646] el0_svc+0x8/0xc

[ 708.739019] Freed by task 17: [ 708.774597] __kasan_slab_free+0x114/0x228 [ 708.823736] kasan_slab_free+0x10/0x18 [ 708.868703] kfree+0x100/0x3d8 [ 708.905320] skb_free_head+0x7c/0x98 [ 708.948204] skb_release_data+0x320/0x490 [ 708.996301] pskb_expand_head+0x60c/0x970 [ 709.044399] __iptunnel_pull_header+0x3b8/0x5d0 [ 709.098770] ipip6_rcv+0x41c/0x16e0 [sit] [ 709.146873] tunnel64_rcv+0xd4/0x200 [tunnel4] [ 709.200195] ip_local_deliver_finish+0x3b8/0x988 [ 709.255596] ip_local_deliver+0x144/0x470 [ 709.303692] ip_rcv_finish+0x43c/0x14b0 [ 709.349705] ip_rcv+0x628/0x1138 [ 709.388413] __netif_receive_skb_core+0x1670/0x2600 [ 709.446943] __netif_receive_skb+0x28/0x190 [ 709.497120] process_backlog+0x1d0/0x610 [ 709.544169] net_rx_action+0x37c/0xf68 [ 709.589131] __do_softirq+0x288/0x1018

[ 709.651938] The buggy address belongs to the object at ffffe01b6bd85580 which belongs to the cache kmalloc-1024 of size 1024 [ 709.804356] The buggy address is located 117 bytes inside of 1024-byte region [ffffe01b6bd85580, ffffe01b6bd85980) [ 709.946340] The buggy address belongs to the page: [ 710.003824] page:ffff7ff806daf600 count:1 mapcount:0 mapping:ffffe01c4001f600 index:0x0 [ 710.099914] flags: 0xfffff8000000100(slab) [ 710.149059] raw: 0fffff8000000100 dead000000000100 dead000000000200 ffffe01c4001f600 [ 710.242011] raw: 0000000000000000 0000000000380038 00000001ffffffff 0000000000000000 [ 710.334966] page dumped because: kasan: bad access detected

Fix it resetting iph pointer after iptunnel_pull_header

Fixes: a09a4c8dd1ec ("tunnels: Remove encapsulation offloads on decap") Tested-by: Jianlin Shi jishi@redhat.com Signed-off-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/sit.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -661,6 +661,10 @@ static int ipip6_rcv(struct sk_buff *skb !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out;

+ /* skb can be uncloned in iptunnel_pull_header, so + * old iph is no longer valid + */ + iph = (const struct iphdr *)skb_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error)

From: Steffen Klassert steffen.klassert@secunet.com

[ Upstream commit 0ab03f353d3613ea49d1f924faf98559003670a8 ]

Currently we may merge incorrectly a received GSO packet or a packet with frag_list into a packet sitting in the gro_hash list. skb_segment() may crash case because the assumptions on the skb layout are not met. The correct behaviour would be to flush the packet in the gro_hash list and send the received GSO packet directly afterwards. Commit d61d072e87c8e ("net-gro: avoid reorders") sets NAPI_GRO_CB(skb)->flush in this case, but this is not checked before merging. This patch makes sure to check this flag and to not merge in that case.

Fixes: d61d072e87c8e ("net-gro: avoid reorders") Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3808,7 +3808,7 @@ int skb_gro_receive(struct sk_buff **hea struct sk_buff *lp, *p = *head; unsigned int delta_truesize;

- if (unlikely(p->len + len >= 65536)) + if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) return -E2BIG;

lp = NAPI_GRO_CB(p)->last;

From: Mao Wenan maowenan@huawei.com

[ Upstream commit cb66ddd156203daefb8d71158036b27b0e2caf63 ]

When it is to cleanup net namespace, rds_tcp_exit_net() will call rds_tcp_kill_sock(), if t_sock is NULL, it will not call rds_conn_destroy(), rds_conn_path_destroy() and rds_tcp_conn_free() to free connection, and the worker cp_conn_w is not stopped, afterwards the net is freed in net_drop_ns(); While cp_conn_w rds_connect_worker() will call rds_tcp_conn_path_connect() and reference 'net' which has already been freed.

In rds_tcp_conn_path_connect(), rds_tcp_set_callbacks() will set t_sock = sock before sock->ops->connect, but if connect() is failed, it will call rds_tcp_restore_callbacks() and set t_sock = NULL, if connect is always failed, rds_connect_worker() will try to reconnect all the time, so rds_tcp_kill_sock() will never to cancel worker cp_conn_w and free the connections.

Therefore, the condition !tc->t_sock is not needed if it is going to do cleanup_net->rds_tcp_exit_net->rds_tcp_kill_sock, because tc->t_sock is always NULL, and there is on other path to cancel cp_conn_w and free connection. So this patch is to fix this.

rds_tcp_kill_sock(): ... if (net != c_net || !tc->t_sock) ... Acked-by: Santosh Shilimkar santosh.shilimkar@oracle.com

================================================================== BUG: KASAN: use-after-free in inet_create+0xbcc/0xd28 net/ipv4/af_inet.c:340 Read of size 4 at addr ffff8003496a4684 by task kworker/u8:4/3721

CPU: 3 PID: 3721 Comm: kworker/u8:4 Not tainted 5.1.0 #11 Hardware name: linux,dummy-virt (DT) Workqueue: krdsd rds_connect_worker Call trace: dump_backtrace+0x0/0x3c0 arch/arm64/kernel/time.c:53 show_stack+0x28/0x38 arch/arm64/kernel/traps.c:152 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x120/0x188 lib/dump_stack.c:113 print_address_description+0x68/0x278 mm/kasan/report.c:253 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x21c/0x348 mm/kasan/report.c:409 __asan_report_load4_noabort+0x30/0x40 mm/kasan/report.c:429 inet_create+0xbcc/0xd28 net/ipv4/af_inet.c:340 __sock_create+0x4f8/0x770 net/socket.c:1276 sock_create_kern+0x50/0x68 net/socket.c:1322 rds_tcp_conn_path_connect+0x2b4/0x690 net/rds/tcp_connect.c:114 rds_connect_worker+0x108/0x1d0 net/rds/threads.c:175 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296 kthread+0x2f0/0x378 kernel/kthread.c:255 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

Allocated by task 687: save_stack mm/kasan/kasan.c:448 [inline] set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xd4/0x180 mm/kasan/kasan.c:553 kasan_slab_alloc+0x14/0x20 mm/kasan/kasan.c:490 slab_post_alloc_hook mm/slab.h:444 [inline] slab_alloc_node mm/slub.c:2705 [inline] slab_alloc mm/slub.c:2713 [inline] kmem_cache_alloc+0x14c/0x388 mm/slub.c:2718 kmem_cache_zalloc include/linux/slab.h:697 [inline] net_alloc net/core/net_namespace.c:384 [inline] copy_net_ns+0xc4/0x2d0 net/core/net_namespace.c:424 create_new_namespaces+0x300/0x658 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xa0/0x198 kernel/nsproxy.c:206 ksys_unshare+0x340/0x628 kernel/fork.c:2577 __do_sys_unshare kernel/fork.c:2645 [inline] __se_sys_unshare kernel/fork.c:2643 [inline] __arm64_sys_unshare+0x38/0x58 kernel/fork.c:2643 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall arch/arm64/kernel/syscall.c:47 [inline] el0_svc_common+0x168/0x390 arch/arm64/kernel/syscall.c:83 el0_svc_handler+0x60/0xd0 arch/arm64/kernel/syscall.c:129 el0_svc+0x8/0xc arch/arm64/kernel/entry.S:960

Freed by task 264: save_stack mm/kasan/kasan.c:448 [inline] set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x114/0x220 mm/kasan/kasan.c:521 kasan_slab_free+0x10/0x18 mm/kasan/kasan.c:528 slab_free_hook mm/slub.c:1370 [inline] slab_free_freelist_hook mm/slub.c:1397 [inline] slab_free mm/slub.c:2952 [inline] kmem_cache_free+0xb8/0x3a8 mm/slub.c:2968 net_free net/core/net_namespace.c:400 [inline] net_drop_ns.part.6+0x78/0x90 net/core/net_namespace.c:407 net_drop_ns net/core/net_namespace.c:406 [inline] cleanup_net+0x53c/0x6d8 net/core/net_namespace.c:569 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296 kthread+0x2f0/0x378 kernel/kthread.c:255 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

The buggy address belongs to the object at ffff8003496a3f80 which belongs to the cache net_namespace of size 7872 The buggy address is located 1796 bytes inside of 7872-byte region [ffff8003496a3f80, ffff8003496a5e40) The buggy address belongs to the page: page:ffff7e000d25a800 count:1 mapcount:0 mapping:ffff80036ce4b000 index:0x0 compound_mapcount: 0 flags: 0xffffe0000008100(slab|head) raw: 0ffffe0000008100 dead000000000100 dead000000000200 ffff80036ce4b000 raw: 0000000000000000 0000000080040004 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff8003496a4580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8003496a4600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

ffff8003496a4680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

^ ffff8003496a4700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8003496a4780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

Fixes: 467fa15356ac("RDS-TCP: Support multiple RDS-TCP listen endpoints, one per netns.") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Mao Wenan maowenan@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/rds/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -530,7 +530,7 @@ static void rds_tcp_kill_sock(struct net list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);

- if (net != c_net || !tc->t_sock) + if (net != c_net) continue; if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) { list_move_tail(&tc->t_tcp_node, &tmp_list);

From: Andrea Righi andrea.righi@canonical.com

[ Upstream commit f28cd2af22a0c134e4aa1c64a70f70d815d473fb ]

The flow action buffer can be resized if it's not big enough to contain all the requested flow actions. However, this resize doesn't take into account the new requested size, the buffer is only increased by a factor of 2x. This might be not enough to contain the new data, causing a buffer overflow, for example:

[ 42.044472] ============================================================================= [ 42.045608] BUG kmalloc-96 (Not tainted): Redzone overwritten [ 42.046415] -----------------------------------------------------------------------------

[ 42.047715] Disabling lock debugging due to kernel taint [ 42.047716] INFO: 0x8bf2c4a5-0x720c0928. First byte 0x0 instead of 0xcc [ 42.048677] INFO: Slab 0xbc6d2040 objects=29 used=18 fp=0xdc07dec4 flags=0x2808101 [ 42.049743] INFO: Object 0xd53a3464 @offset=2528 fp=0xccdcdebb

[ 42.050747] Redzone 76f1b237: cc cc cc cc cc cc cc cc ........ [ 42.051839] Object d53a3464: 6b 6b 6b 6b 6b 6b 6b 6b 0c 00 00 00 6c 00 00 00 kkkkkkkk....l... [ 42.053015] Object f49a30cc: 6c 00 0c 00 00 00 00 00 00 00 00 03 78 a3 15 f6 l...........x... [ 42.054203] Object acfe4220: 20 00 02 00 ff ff ff ff 00 00 00 00 00 00 00 00 ............... [ 42.055370] Object 21024e91: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [ 42.056541] Object 070e04c3: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [ 42.057797] Object 948a777a: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [ 42.059061] Redzone 8bf2c4a5: 00 00 00 00 .... [ 42.060189] Padding a681b46e: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ

Fix by making sure the new buffer is properly resized to contain all the requested data.

BugLink: https://bugs.launchpad.net/bugs/1813244 Signed-off-by: Andrea Righi andrea.righi@canonical.com Acked-by: Pravin B Shelar pshelar@ovn.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/openvswitch/flow_netlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1967,14 +1967,14 @@ static struct nlattr *reserve_sfa_size(s

struct sw_flow_actions *acts; int new_acts_size; - int req_size = NLA_ALIGN(attr_len); + size_t req_size = NLA_ALIGN(attr_len); int next_offset = offsetof(struct sw_flow_actions, actions) + (*sfa)->actions_len;

if (req_size <= (ksize(*sfa) - next_offset)) goto out;

- new_acts_size = ksize(*sfa) * 2; + new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);

if (new_acts_size > MAX_ACTIONS_BUFSIZE) { if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 09279e615c81ce55e04835970601ae286e3facbe ]

Syzbot report a kernel-infoleak:

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 Call Trace: _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 copy_to_user include/linux/uaccess.h:174 [inline] sctp_getsockopt_peer_addrs net/sctp/socket.c:5911 [inline] sctp_getsockopt+0x1668e/0x17f70 net/sctp/socket.c:7562 ... Uninit was stored to memory at: sctp_transport_init net/sctp/transport.c:61 [inline] sctp_transport_new+0x16d/0x9a0 net/sctp/transport.c:115 sctp_assoc_add_peer+0x532/0x1f70 net/sctp/associola.c:637 sctp_process_param net/sctp/sm_make_chunk.c:2548 [inline] sctp_process_init+0x1a1b/0x3ed0 net/sctp/sm_make_chunk.c:2361 ... Bytes 8-15 of 16 are uninitialized

It was caused by that th _pad field (the 8-15 bytes) of a v4 addr (saved in struct sockaddr_in) wasn't initialized, but directly copied to user memory in sctp_getsockopt_peer_addrs().

So fix it by calling memset(addr->v4.sin_zero, 0, 8) to initialize _pad of sockaddr_in before copying it to user memory in sctp_v4_addr_to_user(), as sctp_v6_addr_to_user() does.

Reported-by: syzbot+86b5c7c236a22616a72f@syzkaller.appspotmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Tested-by: Alexander Potapenko glider@google.com Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/protocol.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -605,6 +605,7 @@ out: static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { /* No address mapping for V4 sockets */ + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return sizeof(struct sockaddr_in); }

From: Stephen Suryaputra ssuryaextr@gmail.com

[ Upstream commit 8c83f2df9c6578ea4c5b940d8238ad8a41b87e9e ]

Configuration check to accept source route IP options should be made on the incoming netdevice when the skb->dev is an l3mdev master. The route lookup for the source route next hop also needs the incoming netdev.

v2->v3: - Simplify by passing the original netdevice down the stack (per David Ahern).

Signed-off-by: Stephen Suryaputra ssuryaextr@gmail.com Reviewed-by: David Ahern dsahern@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/ip.h | 2 +- net/ipv4/ip_input.c | 7 +++---- net/ipv4/ip_options.c | 4 ++-- 3 files changed, 6 insertions(+), 7 deletions(-)

--- a/include/net/ip.h +++ b/include/net/ip.h @@ -603,7 +603,7 @@ int ip_options_get_from_user(struct net unsigned char __user *data, int optlen); void ip_options_undo(struct ip_options *opt); void ip_forward_options(struct sk_buff *skb); -int ip_options_rcv_srr(struct sk_buff *skb); +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);

/* * Functions provided by ip_sockglue.c --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -259,11 +259,10 @@ int ip_local_deliver(struct sk_buff *skb ip_local_deliver_finish); }

-static inline bool ip_rcv_options(struct sk_buff *skb) +static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt; const struct iphdr *iph; - struct net_device *dev = skb->dev;

/* It looks as overkill, because not all IP options require packet mangling. @@ -299,7 +298,7 @@ static inline bool ip_rcv_options(struct } }

- if (ip_options_rcv_srr(skb)) + if (ip_options_rcv_srr(skb, dev)) goto drop; }

@@ -362,7 +361,7 @@ static int ip_rcv_finish(struct net *net } #endif

- if (iph->ihl > 5 && ip_rcv_options(skb)) + if (iph->ihl > 5 && ip_rcv_options(skb, dev)) goto drop;

rt = skb_rtable(skb); --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff * } }

-int ip_options_rcv_srr(struct sk_buff *skb) +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt = &(IPCB(skb)->opt); int srrspace, srrptr; @@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *s

orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); - err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); + err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb);

From: Yuval Avnery yuvalav@mellanox.com

[ Upstream commit 80a2a9026b24c6bd34b8d58256973e22270bedec ]

Refresh tirs is looping over a global list of tirs while netdevs are adding and removing tirs from that list. That is why a lock is required.

Fixes: 724b2aa15126 ("net/mlx5e: TIRs management refactoring") Signed-off-by: Yuval Avnery yuvalav@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 7 +++++++ include/linux/mlx5/driver.h | 2 ++ 2 files changed, 9 insertions(+)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_de if (err) return err;

+ mutex_lock(&mdev->mlx5e_res.td.list_lock); list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock);

return 0; } @@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_de void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir) { + mutex_lock(&mdev->mlx5e_res.td.list_lock); mlx5_core_destroy_tir(mdev, tir->tirn); list_del(&tir->list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); }

static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, @@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct m }

INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list); + mutex_init(&mdev->mlx5e_res.td.list_lock);

return 0;

@@ -158,6 +163,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv

MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);

+ mutex_lock(&mdev->mlx5e_res.td.list_lock); list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) { tirn = tir->tirn; err = mlx5_core_modify_tir(mdev, tirn, in, inlen); @@ -169,6 +175,7 @@ out: kvfree(in); if (err) netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); + mutex_unlock(&mdev->mlx5e_res.td.list_lock);

return err; } --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -743,6 +743,8 @@ struct mlx5_pagefault { };

struct mlx5_td { + /* protects tirs list changes while tirs refresh */ + struct mutex list_lock; struct list_head tirs_list; u32 tdn; };

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit a1b0e4e684e9c300b9e759b46cb7a0147e61ddff ]

There is logic to check that the RX/TPA consumer index is the expected index to work around a hardware problem. However, the potentially bad consumer index is first used to index into an array to reference an entry. This can potentially crash if the bad consumer index is beyond legal range. Improve the logic to use the consumer index for dereferencing after the validity check and log an error message.

Fixes: fa7e28127a5a ("bnxt_en: Add workaround to detect bad opaque in rx completion (part 2)") Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1076,6 +1076,8 @@ static void bnxt_tpa_start(struct bnxt * tpa_info = &rxr->rx_tpa[agg_id];

if (unlikely(cons != rxr->rx_next_cons)) { + netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n", + cons, rxr->rx_next_cons); bnxt_sched_reset(bp, rxr); return; } @@ -1528,15 +1530,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, }

cons = rxcmp->rx_cmp_opaque; - rx_buf = &rxr->rx_buf_ring[cons]; - data = rx_buf->data; - data_ptr = rx_buf->data_ptr; if (unlikely(cons != rxr->rx_next_cons)) { int rc1 = bnxt_discard_rx(bp, bnapi, raw_cons, rxcmp);

+ netdev_warn(bp->dev, "RX cons %x != expected cons %x\n", + cons, rxr->rx_next_cons); bnxt_sched_reset(bp, rxr); return rc1; } + rx_buf = &rxr->rx_buf_ring[cons]; + data = rx_buf->data; + data_ptr = rx_buf->data_ptr; prefetch(data_ptr);

misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);

From: Davide Caratti dcaratti@redhat.com

[ Upstream commit fae2708174ae95d98d19f194e03d6e8f688ae195 ]

the control path of 'sample' action does not validate the value of 'rate' provided by the user, but then it uses it as divisor in the traffic path. Validate it in tcf_sample_init(), and return -EINVAL with a proper extack message in case that value is zero, to fix a splat with the script below:

# tc f a dev test0 egress matchall action sample rate 0 group 1 index 2 # tc -s a s action sample total acts 1

action order 0: sample rate 1/0 group 1 pipe index 2 ref 1 bind 1 installed 19 sec used 19 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 # ping 192.0.2.1 -I test0 -c1 -q

divide error: 0000 [#1] SMP PTI CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample] Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000 FS: 00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x7c/0x1c0 tcf_classify+0x57/0x160 __dev_queue_xmit+0x3dc/0xd10 ip_finish_output2+0x257/0x6d0 ip_output+0x75/0x280 ip_send_skb+0x15/0x40 raw_sendmsg+0xae3/0x1410 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x60/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe [...] Kernel panic - not syncing: Fatal exception in interrupt

Add a TDC selftest to document that 'rate' is now being validated.

Reported-by: Matteo Croce mcroce@redhat.com Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Signed-off-by: Davide Caratti dcaratti@redhat.com Acked-by: Yotam Gigi yotam.gi@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/act_sample.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -45,6 +45,7 @@ static int tcf_sample_init(struct net *n struct tc_sample *parm; struct tcf_sample *s; bool exists = false; + u32 rate; int ret;

if (!nla) @@ -73,10 +74,17 @@ static int tcf_sample_init(struct net *n if (!ovr) return -EEXIST; } - s = to_sample(*a);

+ rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + if (!rate) { + tcf_idr_release(*a, bind); + return -EINVAL; + } + + s = to_sample(*a); s->tcf_action = parm->action; s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + s->rate = rate; s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); psample_group = psample_group_get(net, s->psample_group_num); if (!psample_group) {

From: Li RongQing lirongqing@baidu.com

[ Upstream commit 3d8830266ffc28c16032b859e38a0252e014b631 ]

NULL or ZERO_SIZE_PTR will be returned for zero sized memory request, and derefencing them will lead to a segfault

so it is unnecessory to call vzalloc for zero sized memory request and not call functions which maybe derefence the NULL allocated memory

this also fixes a possible memory leak if phy_ethtool_get_stats returns error, memory should be freed before exit

Signed-off-by: Li RongQing lirongqing@baidu.com Reviewed-by: Wang Li wangli39@baidu.com Reviewed-by: Michal Kubecek mkubecek@suse.cz Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/ethtool.c | 43 +++++++++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 16 deletions(-)

--- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1815,11 +1815,15 @@ static int ethtool_get_strings(struct ne WARN_ON_ONCE(!ret);

gstrings.len = ret; - data = vzalloc(gstrings.len * ETH_GSTRING_LEN); - if (gstrings.len && !data) - return -ENOMEM; + if (gstrings.len) { + data = vzalloc(gstrings.len * ETH_GSTRING_LEN); + if (!data) + return -ENOMEM;

- __ethtool_get_strings(dev, gstrings.string_set, data); + __ethtool_get_strings(dev, gstrings.string_set, data); + } else { + data = NULL; + }

ret = -EFAULT; if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) @@ -1915,11 +1919,14 @@ static int ethtool_get_stats(struct net_ return -EFAULT;

stats.n_stats = n_stats; - data = vzalloc(n_stats * sizeof(u64)); - if (n_stats && !data) - return -ENOMEM; - - ops->get_ethtool_stats(dev, &stats, data); + if (n_stats) { + data = vzalloc(n_stats * sizeof(u64)); + if (!data) + return -ENOMEM; + ops->get_ethtool_stats(dev, &stats, data); + } else { + data = NULL; + }

ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) @@ -1955,13 +1962,17 @@ static int ethtool_get_phy_stats(struct return -EFAULT;

stats.n_stats = n_stats; - data = vzalloc(n_stats * sizeof(u64)); - if (n_stats && !data) - return -ENOMEM; - - mutex_lock(&phydev->lock); - phydev->drv->get_stats(phydev, &stats, data); - mutex_unlock(&phydev->lock); + if (n_stats) { + data = vzalloc(n_stats * sizeof(u64)); + if (!data) + return -ENOMEM; + + mutex_lock(&phydev->lock); + phydev->drv->get_stats(phydev, &stats, data); + mutex_unlock(&phydev->lock); + } else { + data = NULL; + }

ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats)))

From: Sheena Mira-ato sheena.mira-ato@alliedtelesis.co.nz

[ Upstream commit b2e54b09a3d29c4db883b920274ca8dca4d9f04d ]

The device type for ip6 tunnels is set to ARPHRD_TUNNEL6. However, the ip4ip6_err function is expecting the device type of the tunnel to be ARPHRD_TUNNEL. Since the device types do not match, the function exits and the ICMP error packet is not sent to the originating host. Note that the device type for IPv4 tunnels is set to ARPHRD_TUNNEL.

Fix is to expect a tunnel device type of ARPHRD_TUNNEL6 instead. Now the tunnel device type matches and the ICMP error packet is sent to the originating host.

Signed-off-by: Sheena Mira-ato sheena.mira-ato@alliedtelesis.co.nz Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ip6_tunnel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -633,7 +633,7 @@ ip4ip6_err(struct sk_buff *skb, struct i IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt) || - rt->dst.dev->type != ARPHRD_TUNNEL) { + rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; @@ -643,7 +643,7 @@ ip4ip6_err(struct sk_buff *skb, struct i ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) + skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6) goto out; }

From: Peter Geis pgwipeout@gmail.com

commit 09f91381fa5de1d44bc323d8bf345f5d57b3d9b5 upstream.

Various rk3328 based boards experience occasional sdmmc0 write errors. This is due to the rk3328.dtsi tx drive levels being set to 4ma, vs 8ma per the rk3328 datasheet default settings.

Fix this by setting the tx signal pins to 8ma. Inspiration from tonymac32's patch, https://github.com/ayufan-rock64/linux-kernel/commit/dc1212b347e0da17c5460bc...

Fixes issues on the rk3328-roc-cc and the rk3328-rock64 (as per the above commit message).

Tested on the rk3328-roc-cc board.

Fixes: 52e02d377a72 ("arm64: dts: rockchip: add core dtsi file for RK3328 SoCs") Cc: stable@vger.kernel.org Signed-off-by: Peter Geis pgwipeout@gmail.com Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/boot/dts/rockchip/rk3328.dtsi | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -1333,11 +1333,11 @@

sdmmc0 { sdmmc0_clk: sdmmc0-clk { - rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_4ma>; + rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_8ma>; };

sdmmc0_cmd: sdmmc0-cmd { - rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_8ma>; };

sdmmc0_dectn: sdmmc0-dectn { @@ -1349,14 +1349,14 @@ };

sdmmc0_bus1: sdmmc0-bus1 { - rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>; };

sdmmc0_bus4: sdmmc0-bus4 { - rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>, - <1 RK_PA1 1 &pcfg_pull_up_4ma>, - <1 RK_PA2 1 &pcfg_pull_up_4ma>, - <1 RK_PA3 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>, + <1 RK_PA1 1 &pcfg_pull_up_8ma>, + <1 RK_PA2 1 &pcfg_pull_up_8ma>, + <1 RK_PA3 1 &pcfg_pull_up_8ma>; };

sdmmc0_gpio: sdmmc0-gpio {

From: Sven Schnelle svens@stackframe.org

commit 45efd871bf0a47648f119d1b41467f70484de5bc upstream.

While working on kretprobes for PA-RISC I was wondering while the kprobes sanity test always fails on kretprobes. This is caused by returning gpr20 instead of gpr28.

Signed-off-by: Sven Schnelle svens@stackframe.org Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org # 4.14+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/parisc/include/asm/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/parisc/include/asm/ptrace.h +++ b/arch/parisc/include/asm/ptrace.h @@ -22,7 +22,7 @@ unsigned long profile_pc(struct pt_regs

static inline unsigned long regs_return_value(struct pt_regs *regs) { - return regs->gr[20]; + return regs->gr[28]; }

#endif

From: Dave Airlie airlied@redhat.com

commit 9b39b013037fbfa8d4b999345d9e904d8a336fc2 upstream.

If we unplug a udl device, the usb callback with deinit the mode_config struct, however userspace will still have an open file descriptor and a framebuffer on that device. When userspace closes the fd, we'll oops because it'll try and look stuff up in the object idr which we've destroyed.

This punts destroying the mode objects until release time instead.

Cc: stable@vger.kernel.org Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch Signed-off-by: Dave Airlie airlied@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/20190405031715.5959-2-airlied@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/udl/udl_drv.c | 1 + drivers/gpu/drm/udl/udl_drv.h | 1 + drivers/gpu/drm/udl/udl_main.c | 8 +++++++- 3 files changed, 9 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/udl/udl_drv.c +++ b/drivers/gpu/drm/udl/udl_drv.c @@ -47,6 +47,7 @@ static struct drm_driver driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME, .load = udl_driver_load, .unload = udl_driver_unload, + .release = udl_driver_release,

/* gem hooks */ .gem_free_object = udl_gem_free_object, --- a/drivers/gpu/drm/udl/udl_drv.h +++ b/drivers/gpu/drm/udl/udl_drv.h @@ -101,6 +101,7 @@ void udl_urb_completion(struct urb *urb)

int udl_driver_load(struct drm_device *dev, unsigned long flags); void udl_driver_unload(struct drm_device *dev); +void udl_driver_release(struct drm_device *dev);

int udl_fbdev_init(struct drm_device *dev); void udl_fbdev_cleanup(struct drm_device *dev); --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -378,6 +378,12 @@ void udl_driver_unload(struct drm_device udl_free_urb_list(dev);

udl_fbdev_cleanup(dev); - udl_modeset_cleanup(dev); kfree(udl); } + +void udl_driver_release(struct drm_device *dev) +{ + udl_modeset_cleanup(dev); + drm_dev_fini(dev); + kfree(dev); +}

From: S.j. Wang shengjiu.wang@nxp.com

commit 0ff4e8c61b794a4bf6c854ab071a1abaaa80f358 upstream.

There is very low possibility ( < 0.1% ) that channel swap happened in beginning when multi output/input pin is enabled. The issue is that hardware can't send data to correct pin in the beginning with the normal enable flow.

This is hardware issue, but there is no errata, the workaround flow is that: Each time playback/recording, firstly clear the xSMA/xSMB, then enable TE/RE, then enable xSMB and xSMA (xSMB must be enabled before xSMA). Which is to use the xSMA as the trigger start register, previously the xCR_TE or xCR_RE is the bit for starting.

Fixes commit 43d24e76b698 ("ASoC: fsl_esai: Add ESAI CPU DAI driver") Cc: stable@vger.kernel.org Reviewed-by: Fabio Estevam festevam@gmail.com Acked-by: Nicolin Chen nicoleotsuka@gmail.com Signed-off-by: Shengjiu Wang shengjiu.wang@nxp.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/soc/fsl/fsl_esai.c | 47 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 10 deletions(-)

--- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -58,6 +58,8 @@ struct fsl_esai { u32 fifo_depth; u32 slot_width; u32 slots; + u32 tx_mask; + u32 rx_mask; u32 hck_rate[2]; u32 sck_rate[2]; bool hck_dir[2]; @@ -358,21 +360,13 @@ static int fsl_esai_set_dai_tdm_slot(str regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));

- regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));

- regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask)); - esai_priv->slot_width = slot_width; esai_priv->slots = slots; + esai_priv->tx_mask = tx_mask; + esai_priv->rx_mask = rx_mask;

return 0; } @@ -593,6 +587,7 @@ static int fsl_esai_trigger(struct snd_p bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; u8 i, channels = substream->runtime->channels; u32 pins = DIV_ROUND_UP(channels, esai_priv->slots); + u32 mask;

switch (cmd) { case SNDRV_PCM_TRIGGER_START: @@ -605,15 +600,38 @@ static int fsl_esai_trigger(struct snd_p for (i = 0; tx && i < channels; i++) regmap_write(esai_priv->regmap, REG_ESAI_ETDR, 0x0);

+ /* + * When set the TE/RE in the end of enablement flow, there + * will be channel swap issue for multi data line case. + * In order to workaround this issue, we switch the bit + * enablement sequence to below sequence + * 1) clear the xSMB & xSMA: which is done in probe and + * stop state. + * 2) set TE/RE + * 3) set xSMB + * 4) set xSMA: xSMA is the last one in this flow, which + * will trigger esai to start. + */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins)); + mask = tx ? esai_priv->tx_mask : esai_priv->rx_mask; + + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(mask)); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(mask)); + break; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, 0);

/* Disable and reset FIFO */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx), @@ -903,6 +921,15 @@ static int fsl_esai_probe(struct platfor return ret; }

+ esai_priv->tx_mask = 0xFFFFFFFF; + esai_priv->rx_mask = 0xFFFFFFFF; + + /* Clear the TSMA, TSMB, RSMA, RSMB */ + regmap_write(esai_priv->regmap, REG_ESAI_TSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_TSMB, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMB, 0); + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component, &fsl_esai_dai, 1); if (ret) {

From: Anand Jain anand.jain@oracle.com

commit 50398fde997f6be8faebdb5f38e9c9c467370f51 upstream.

We let pass zstd compression parameter even if it is not fully valid. For example:

$ btrfs prop set /btrfs compression zst $ btrfs prop get /btrfs compression compression=zst

zlib and lzo are fine.

Fix it by checking the correct prefix length.

Fixes: 5c1aab1dd544 ("btrfs: Add zstd support") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Nikolay Borisov nborisov@suse.com Signed-off-by: Anand Jain anand.jain@oracle.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/props.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -416,7 +416,7 @@ static int prop_compression_apply(struct btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); } else if (!strncmp("zlib", value, 4)) { type = BTRFS_COMPRESS_ZLIB; - } else if (!strncmp("zstd", value, len)) { + } else if (!strncmp("zstd", value, 4)) { type = BTRFS_COMPRESS_ZSTD; btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } else {

From: Jérôme Glisse jglisse@redhat.com

commit a3761c3c91209b58b6f33bf69dd8bb8ec0c9d925 upstream.

When bio_add_pc_page() fails in bio_copy_user_iov() we should free the page we just allocated otherwise we are leaking it.

Cc: linux-block@vger.kernel.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: stable@vger.kernel.org Reviewed-by: Chaitanya Kulkarni chaitanya.kulkarni@wdc.com Signed-off-by: Jérôme Glisse jglisse@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- block/bio.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/block/bio.c +++ b/block/bio.c @@ -1280,8 +1280,11 @@ struct bio *bio_copy_user_iov(struct req } }

- if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) + if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) { + if (!map_data) + __free_page(page); break; + }

len -= bytes; offset = 0;

From: Stephen Boyd swboyd@chromium.org

commit 325aa19598e410672175ed50982f902d4e3f31c5 upstream.

If a child irqchip calls irq_chip_set_wake_parent() but its parent irqchip has the IRQCHIP_SKIP_SET_WAKE flag set an error is returned.

This is inconsistent behaviour vs. set_irq_wake_real() which returns 0 when the irqchip has the IRQCHIP_SKIP_SET_WAKE flag set. It doesn't attempt to walk the chain of parents and set irq wake on any chips that don't have the flag set either. If the intent is to call the .irq_set_wake() callback of the parent irqchip, then we expect irqchip implementations to omit the IRQCHIP_SKIP_SET_WAKE flag and implement an .irq_set_wake() function that calls irq_chip_set_wake_parent().

The problem has been observed on a Qualcomm sdm845 device where set wake fails on any GPIO interrupts after applying work in progress wakeup irq patches to the GPIO driver. The chain of chips looks like this:

QCOM GPIO -> QCOM PDC (SKIP) -> ARM GIC (SKIP)

The GPIO controllers parent is the QCOM PDC irqchip which in turn has ARM GIC as parent. The QCOM PDC irqchip has the IRQCHIP_SKIP_SET_WAKE flag set, and so does the grandparent ARM GIC.

The GPIO driver doesn't know if the parent needs to set wake or not, so it unconditionally calls irq_chip_set_wake_parent() causing this function to return a failure because the parent irqchip (PDC) doesn't have the .irq_set_wake() callback set. Returning 0 instead makes everything work and irqs from the GPIO controller can be configured for wakeup.

Make it consistent by returning 0 (success) from irq_chip_set_wake_parent() when a parent chip has IRQCHIP_SKIP_SET_WAKE set.

[ tglx: Massaged changelog ]

Fixes: 08b55e2a9208e ("genirq: Add irqchip_set_wake_parent") Signed-off-by: Stephen Boyd swboyd@chromium.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Marc Zyngier marc.zyngier@arm.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-gpio@vger.kernel.org Cc: Lina Iyer ilina@codeaurora.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190325181026.247796-1-swboyd@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/irq/chip.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1363,6 +1363,10 @@ int irq_chip_set_vcpu_affinity_parent(st int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) { data = data->parent_data; + + if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE) + return 0; + if (data->chip->irq_set_wake) return data->chip->irq_set_wake(data, on);

From: Cornelia Huck cohuck@redhat.com

commit cf94db21905333e610e479688add629397a4b384 upstream.

vring_create_virtqueue() allows the caller to specify via the may_reduce_num parameter whether the vring code is allowed to allocate a smaller ring than specified.

However, the split ring allocation code tries to allocate a smaller ring on allocation failure regardless of what the caller specified. This may cause trouble for e.g. virtio-pci in legacy mode, which does not support ring resizing. (The packed ring code does not resize in any case.)

Let's fix this by bailing out immediately in the split ring code if the requested size cannot be allocated and may_reduce_num has not been specified.

While at it, fix a typo in the usage instructions.

Fixes: 2a2d1382fe9d ("virtio: Add improved queue allocation API") Cc: stable@vger.kernel.org # v4.6+ Signed-off-by: Cornelia Huck cohuck@redhat.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Reviewed-by: Halil Pasic pasic@linux.ibm.com Reviewed-by: Jens Freimann jfreimann@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/virtio/virtio_ring.c | 2 ++ include/linux/virtio_ring.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1087,6 +1087,8 @@ struct virtqueue *vring_create_virtqueue GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO); if (queue) break; + if (!may_reduce_num) + return NULL; }

if (!num) --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -63,7 +63,7 @@ struct virtqueue; /* * Creates a virtqueue and allocates the descriptor ring. If * may_reduce_num is set, then this may allocate a smaller ring than - * expected. The caller should query virtqueue_get_ring_size to learn + * expected. The caller should query virtqueue_get_vring_size to learn * the actual size of the ring. */ struct virtqueue *vring_create_virtqueue(unsigned int index,

From: Peter Ujfalusi peter.ujfalusi@ti.com

commit 4f96dc0a3e79ec257a2b082dab3ee694ff88c317 upstream.

Correctly map the regulators used by tlv320aic3106. Both 1.8V and 3.3V for the codec is derived from VBAT via fixed regulators.

Cc: Stable@vger.kernel.org # v4.14+ Signed-off-by: Peter Ujfalusi peter.ujfalusi@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/am335x-evm.dts | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-)

--- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -57,6 +57,24 @@ enable-active-high; };

+ /* TPS79501 */ + v1_8d_reg: fixedregulator-v1_8d { + compatible = "regulator-fixed"; + regulator-name = "v1_8d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + /* TPS79501 */ + v3_3d_reg: fixedregulator-v3_3d { + compatible = "regulator-fixed"; + regulator-name = "v3_3d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + matrix_keypad: matrix_keypad0 { compatible = "gpio-matrix-keypad"; debounce-delay-ms = <5>; @@ -492,10 +510,10 @@ status = "okay";

/* Regulators */ - AVDD-supply = <&vaux2_reg>; - IOVDD-supply = <&vaux2_reg>; - DRVDD-supply = <&vaux2_reg>; - DVDD-supply = <&vbat>; + AVDD-supply = <&v3_3d_reg>; + IOVDD-supply = <&v3_3d_reg>; + DRVDD-supply = <&v3_3d_reg>; + DVDD-supply = <&v1_8d_reg>; }; };

From: Will Deacon will.deacon@arm.com

commit 045afc24124d80c6998d9c770844c67912083506 upstream.

Rather embarrassingly, our futex() FUTEX_WAKE_OP implementation doesn't explicitly set the return value on the non-faulting path and instead leaves it holding the result of the underlying atomic operation. This means that any FUTEX_WAKE_OP atomic operation which computes a non-zero value will be reported as having failed. Regrettably, I wrote the buggy code back in 2011 and it was upstreamed as part of the initial arm64 support in 2012.

The reasons we appear to get away with this are:

1. FUTEX_WAKE_OP is rarely used and therefore doesn't appear to get exercised by futex() test applications

2. If the result of the atomic operation is zero, the system call behaves correctly

3. Prior to version 2.25, the only operation used by GLIBC set the futex to zero, and therefore worked as expected. From 2.25 onwards, FUTEX_WAKE_OP is not used by GLIBC at all.

Fix the implementation by ensuring that the return value is either 0 to indicate that the atomic operation completed successfully, or -EFAULT if we encountered a fault when accessing the user mapping.

Cc: stable@kernel.org Fixes: 6170a97460db ("arm64: Atomic operations") Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/include/asm/futex.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -30,8 +30,8 @@ do { \ " prfm pstl1strm, %2\n" \ "1: ldxr %w1, %2\n" \ insn "\n" \ -"2: stlxr %w3, %w0, %2\n" \ -" cbnz %w3, 1b\n" \ +"2: stlxr %w0, %w3, %2\n" \ +" cbnz %w0, 1b\n" \ " dmb ish\n" \ "3:\n" \ " .pushsection .fixup,"ax"\n" \ @@ -50,30 +50,30 @@ do { \ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { - int oldval = 0, ret, tmp; + int oldval, ret, tmp; u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);

pagefault_disable();

switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("mov %w0, %w4", + __futex_atomic_op("mov %w3, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %w0, %w1, %w4", + __futex_atomic_op("add %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("orr %w0, %w1, %w4", + __futex_atomic_op("orr %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("and %w0, %w1, %w4", + __futex_atomic_op("and %w3, %w1, %w4", ret, oldval, uaddr, tmp, ~oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("eor %w0, %w1, %w4", + __futex_atomic_op("eor %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; default:

From: Will Deacon will.deacon@arm.com

commit 1e6f5440a6814d28c32d347f338bfef68bc3e69d upstream.

Calling dump_backtrace() with a pt_regs argument corresponding to userspace doesn't make any sense and our unwinder will simply print "Call trace:" before unwinding the stack looking for user frames.

Rather than go through this song and dance, just return early if we're passed a user register state.

Cc: stable@vger.kernel.org Fixes: 1149aad10b1e ("arm64: Add dump_backtrace() in show_regs") Reported-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/kernel/traps.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

--- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -145,10 +145,16 @@ static void dump_instr(const char *lvl, void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; - int skip; + int skip = 0;

pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);

+ if (regs) { + if (user_mode(regs)) + return; + skip = 1; + } + if (!tsk) tsk = current;

@@ -169,7 +175,6 @@ void dump_backtrace(struct pt_regs *regs frame.graph = tsk->curr_ret_stack; #endif

- skip = !!regs; printk("Call trace:\n"); while (1) { unsigned long stack; @@ -232,15 +237,13 @@ static int __die(const char *str, int er return ret;

print_modules(); - __show_regs(regs); pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk)); + show_regs(regs);

- if (!user_mode(regs)) { - dump_backtrace(regs, tsk); + if (!user_mode(regs)) dump_instr(KERN_EMERG, regs); - }

return ret; }

From: Mel Gorman mgorman@techsingularity.net

commit 0e9f02450da07fc7b1346c8c32c771555173e397 upstream.

A NULL pointer dereference bug was reported on a distribution kernel but the same issue should be present on mainline kernel. It occured on s390 but should not be arch-specific. A partial oops looks like:

Unable to handle kernel pointer dereference in virtual kernel address space ... Call Trace: ... try_to_wake_up+0xfc/0x450 vhost_poll_wakeup+0x3a/0x50 [vhost] __wake_up_common+0xbc/0x178 __wake_up_common_lock+0x9e/0x160 __wake_up_sync_key+0x4e/0x60 sock_def_readable+0x5e/0x98

The bug hits any time between 1 hour to 3 days. The dereference occurs in update_cfs_rq_h_load when accumulating h_load. The problem is that cfq_rq->h_load_next is not protected by any locking and can be updated by parallel calls to task_h_load. Depending on the compiler, code may be generated that re-reads cfq_rq->h_load_next after the check for NULL and then oops when reading se->avg.load_avg. The dissassembly showed that it was possible to reread h_load_next after the check for NULL.

While this does not appear to be an issue for later compilers, it's still an accident if the correct code is generated. Full locking in this path would have high overhead so this patch uses READ_ONCE to read h_load_next only once and check for NULL before dereferencing. It was confirmed that there were no further oops after 10 days of testing.

As Peter pointed out, it is also necessary to use WRITE_ONCE() to avoid any potential problems with store tearing.

Signed-off-by: Mel Gorman mgorman@techsingularity.net Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Valentin Schneider valentin.schneider@arm.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Mike Galbraith efault@gmx.de Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Fixes: 685207963be9 ("sched: Move h_load calculation to task_h_load()") Link: https://lkml.kernel.org/r/20190319123610.nsivgf3mjbjjesxb@techsingularity.ne... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/sched/fair.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7018,10 +7018,10 @@ static void update_cfs_rq_h_load(struct if (cfs_rq->last_h_load_update == now) return;

- cfs_rq->h_load_next = NULL; + WRITE_ONCE(cfs_rq->h_load_next, NULL); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_load_next = se; + WRITE_ONCE(cfs_rq->h_load_next, se); if (cfs_rq->last_h_load_update == now) break; } @@ -7031,7 +7031,7 @@ static void update_cfs_rq_h_load(struct cfs_rq->last_h_load_update = now; }

- while ((se = cfs_rq->h_load_next) != NULL) { + while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) { load = cfs_rq->h_load; load = div64_ul(load * se->avg.load_avg, cfs_rq_load_avg(cfs_rq) + 1);

From: Lendacky, Thomas Thomas.Lendacky@amd.com

commit 914123fa39042e651d79eaf86bbf63a1b938dddf upstream.

On AMD processors, the detection of an overflowed counter in the NMI handler relies on the current value of the counter. So, for example, to check for overflow on a 48 bit counter, bit 47 is checked to see if it is 1 (not overflowed) or 0 (overflowed).

There is currently a race condition present when disabling and then updating the PMC. Increased NMI latency in newer AMD processors makes this race condition more pronounced. If the counter value has overflowed, it is possible to update the PMC value before the NMI handler can run. The updated PMC value is not an overflowed value, so when the perf NMI handler does run, it will not find an overflowed counter. This may appear as an unknown NMI resulting in either a panic or a series of messages, depending on how the kernel is configured.

To eliminate this race condition, the PMC value must be checked after disabling the counter. Add an AMD function, amd_pmu_disable_all(), that will wait for the NMI handler to reset any active and overflowed counter after calling x86_pmu_disable_all().

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org # 4.14.x- Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lkml.kernel.org/r/Message-ID: Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/events/amd/core.c | 65 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 62 insertions(+), 3 deletions(-)

--- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -3,6 +3,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/delay.h> #include <asm/apicdef.h>

#include "../perf_event.h" @@ -429,6 +430,64 @@ static void amd_pmu_cpu_dead(int cpu) } }

+/* + * When a PMC counter overflows, an NMI is used to process the event and + * reset the counter. NMI latency can result in the counter being updated + * before the NMI can run, which can result in what appear to be spurious + * NMIs. This function is intended to wait for the NMI to run and reset + * the counter to avoid possible unhandled NMI messages. + */ +#define OVERFLOW_WAIT_COUNT 50 + +static void amd_pmu_wait_on_overflow(int idx) +{ + unsigned int i; + u64 counter; + + /* + * Wait for the counter to be reset if it has overflowed. This loop + * should exit very, very quickly, but just in case, don't wait + * forever... + */ + for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) { + rdmsrl(x86_pmu_event_addr(idx), counter); + if (counter & (1ULL << (x86_pmu.cntval_bits - 1))) + break; + + /* Might be in IRQ context, so can't sleep */ + udelay(1); + } +} + +static void amd_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int idx; + + x86_pmu_disable_all(); + + /* + * This shouldn't be called from NMI context, but add a safeguard here + * to return, since if we're in NMI context we can't wait for an NMI + * to reset an overflowed counter value. + */ + if (in_nmi()) + return; + + /* + * Check each counter for overflow and wait for it to be reset by the + * NMI if it has overflowed. This relies on the fact that all active + * counters are always enabled when this function is caled and + * ARCH_PERFMON_EVENTSEL_INT is always set. + */ + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + if (!test_bit(idx, cpuc->active_mask)) + continue; + + amd_pmu_wait_on_overflow(idx); + } +} + static struct event_constraint * amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -622,7 +681,7 @@ static ssize_t amd_event_sysfs_show(char static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, + .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, @@ -728,7 +787,7 @@ void amd_pmu_enable_virt(void) cpuc->perf_ctr_virt_mask = 0;

/* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); @@ -746,7 +805,7 @@ void amd_pmu_disable_virt(void) cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;

/* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);

From: Lendacky, Thomas Thomas.Lendacky@amd.com

commit 3966c3feca3fd10b2935caa0b4a08c7dd59469e5 upstream.

Spurious interrupt support was added to perf in the following commit, almost a decade ago:

63e6be6d98e1 ("perf, x86: Catch spurious interrupts after disabling counters")

The two previous patches (resolving the race condition when disabling a PMC and NMI latency mitigation) allow for the removal of this older spurious interrupt support.

Currently in x86_pmu_stop(), the bit for the PMC in the active_mask bitmap is cleared before disabling the PMC, which sets up a race condition. This race condition was mitigated by introducing the running bitmap. That race condition can be eliminated by first disabling the PMC, waiting for PMC reset on overflow and then clearing the bit for the PMC in the active_mask bitmap. The NMI handler will not re-enable a disabled counter.

If x86_pmu_stop() is called from the perf NMI handler, the NMI latency mitigation support will guard against any unhandled NMI messages.

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org # 4.14.x- Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lkml.kernel.org/r/Message-ID: Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/events/amd/core.c | 21 +++++++++++++++++++-- arch/x86/events/core.c | 13 +++---------- 2 files changed, 22 insertions(+), 12 deletions(-)

--- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -4,8 +4,8 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> -#include <linux/nmi.h> #include <asm/apicdef.h> +#include <asm/nmi.h>

#include "../perf_event.h"

@@ -491,6 +491,23 @@ static void amd_pmu_disable_all(void) } }

+static void amd_pmu_disable_event(struct perf_event *event) +{ + x86_pmu_disable_event(event); + + /* + * This can be called from NMI context (via x86_pmu_stop). The counter + * may have overflowed, but either way, we'll never see it get reset + * by the NMI if we're already in the NMI. And the NMI latency support + * below will take care of any pending NMI that might have been + * generated by the overflow. + */ + if (in_nmi()) + return; + + amd_pmu_wait_on_overflow(event->hw.idx); +} + /* * Because of NMI latency, if multiple PMC counters are active or other sources * of NMIs are received, the perf NMI handler can handle one or more overflowed @@ -738,7 +755,7 @@ static __initconst const struct x86_pmu .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, + .disable = amd_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1328,8 +1328,9 @@ void x86_pmu_stop(struct perf_event *eve struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw;

- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { + if (test_bit(hwc->idx, cpuc->active_mask)) { x86_pmu.disable(event); + __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; @@ -1426,16 +1427,8 @@ int x86_pmu_handle_irq(struct pt_regs *r apic_write(APIC_LVTPC, APIC_DM_NMI);

for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) { - /* - * Though we deactivated the counter some cpus - * might still deliver spurious interrupts still - * in flight. Catch them: - */ - if (__test_and_clear_bit(idx, cpuc->running)) - handled++; + if (!test_bit(idx, cpuc->active_mask)) continue; - }

event = cpuc->events[idx];

From: Ilya Dryomov idryomov@gmail.com

commit eb40c0acdc342b815d4d03ae6abb09e80c0f2988 upstream.

Some devices don't use blk_integrity but still want stable pages because they do their own checksumming. Examples include rbd and iSCSI when data digests are negotiated. Stacking DM (and thus LVM) on top of these devices results in sporadic checksum errors.

Set BDI_CAP_STABLE_WRITES if any underlying device has it set.

Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm-table.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+)

--- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1789,6 +1789,36 @@ static bool dm_table_supports_discards(s return true; }

+static int device_requires_stable_pages(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return q && bdi_cap_stable_pages_required(q->backing_dev_info); +} + +/* + * If any underlying device requires stable pages, a table must require + * them as well. Only targets that support iterate_devices are considered: + * don't want error, zero, etc to require stable pages. + */ +static bool dm_table_requires_stable_pages(struct dm_table *t) +{ + struct dm_target *ti; + unsigned i; + + for (i = 0; i < dm_table_get_num_targets(t); i++) { + ti = dm_table_get_target(t, i); + + if (ti->type->iterate_devices && + ti->type->iterate_devices(ti, device_requires_stable_pages, NULL)) + return true; + } + + return false; +} + void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { @@ -1838,6 +1868,15 @@ void dm_table_set_restrictions(struct dm dm_table_verify_integrity(t);

/* + * Some devices don't use blk_integrity but still want stable pages + * because they do their own checksumming. + */ + if (dm_table_requires_stable_pages(t)) + q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + else + q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; + + /* * Determine whether or not this queue's I/O timings contribute * to the entropy pool, Only request-based targets use this. * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not

From: Tomohiro Mayama parly-gh@iris.mystia.org

commit a8772e5d826d0f61f8aa9c284b3ab49035d5273d upstream.

This patch makes USB ports functioning again.

Fixes: 955bebde057e ("arm64: dts: rockchip: add rk3328-rock64 board") Cc: stable@vger.kernel.org Suggested-by: Robin Murphy robin.murphy@arm.com Signed-off-by: Tomohiro Mayama parly-gh@iris.mystia.org Tested-by: Katsuhiro Suzuki katsuhiro@katsuster.net Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/boot/dts/rockchip/rk3328-rock64.dts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -82,8 +82,7 @@

vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator { compatible = "regulator-fixed"; - enable-active-high; - gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>; + gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; pinctrl-0 = <&usb20_host_drv>; regulator-name = "vcc_host1_5v";