From: Nicholas Piggin npiggin@gmail.com

[ Upstream commit 8ff00399b153440c1c83e20c43020385b416415b ]

powerpc/64s keeps a counter in the mm which counts bits set in mm_cpumask as well as other things. This means it can't use generic code to clear bits out of the mask and doesn't adjust the arch specific counter.

Add an arch override that allows powerpc/64s to use clear_tasks_mm_cpumask().

Signed-off-by: Nicholas Piggin npiggin@gmail.com Reviewed-by: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20201126102530.691335-4-npiggin@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/cpu.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c index 7527825ac7daa..fa0e5727b4d9c 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -815,6 +815,10 @@ void __init cpuhp_threads_init(void) }

#ifdef CONFIG_HOTPLUG_CPU +#ifndef arch_clear_mm_cpumask_cpu +#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) +#endif + /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id @@ -850,7 +854,7 @@ void clear_tasks_mm_cpumask(int cpu) t = find_lock_task_mm(p); if (!t) continue; - cpumask_clear_cpu(cpu, mm_cpumask(t->mm)); + arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock();

From: Ofir Bitton obitton@habana.ai

[ Upstream commit 5555b7c56bdec7a29c789fec27f84d40f52fbdfa ]

Driver never puts its device and control_device objects, hence a memory leak is introduced every driver removal.

Signed-off-by: Ofir Bitton obitton@habana.ai Reviewed-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/misc/habanalabs/device.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index a7a4fed4d8995..3eeb1920ddb43 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -229,16 +229,16 @@ delete_cdev_device:

static void device_cdev_sysfs_del(struct hl_device *hdev) { - /* device_release() won't be called so must free devices explicitly */ - if (!hdev->cdev_sysfs_created) { - kfree(hdev->dev_ctrl); - kfree(hdev->dev); - return; - } + if (!hdev->cdev_sysfs_created) + goto put_devices;

hl_sysfs_fini(hdev); cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl); cdev_device_del(&hdev->cdev, hdev->dev); + +put_devices: + put_device(hdev->dev); + put_device(hdev->dev_ctrl); }

/* @@ -1285,9 +1285,9 @@ sw_fini: early_fini: device_early_fini(hdev); free_dev_ctrl: - kfree(hdev->dev_ctrl); + put_device(hdev->dev_ctrl); free_dev: - kfree(hdev->dev); + put_device(hdev->dev); out_disabled: hdev->disabled = true; if (add_cdev_sysfs_on_err)

From: Sven Eckelmann sven@narfation.org

[ Upstream commit 0a35dc41fea67ac4495ce7584406bf9557a6e7d0 ]

It was observed that sending data via batadv over vxlan (on top of wireguard) reduced the performance massively compared to raw ethernet or batadv on raw ethernet. A check of perf data showed that the vxlan_build_skb was calling all the time pskb_expand_head to allocate enough headroom for:

min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + VXLAN_HLEN + iphdr_len;

But the vxlan_config_apply only requested needed headroom for:

lowerdev->hard_header_len + VXLAN6_HEADROOM or VXLAN_HEADROOM

So it completely ignored the needed_headroom of the lower device. The first caller of net_dev_xmit could therefore never make sure that enough headroom was allocated for the rest of the transmit path.

Cc: Annika Wickert annika.wickert@exaring.de Signed-off-by: Sven Eckelmann sven@narfation.org Tested-by: Annika Wickert aw@awlnx.space Link: https://lore.kernel.org/r/20201126125247.1047977-1-sven@narfation.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/vxlan.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 630ac00a34ede..3753cf0942865 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3538,6 +3538,7 @@ static void vxlan_config_apply(struct net_device *dev, dev->gso_max_segs = lowerdev->gso_max_segs;

needed_headroom = lowerdev->hard_header_len; + needed_headroom += lowerdev->needed_headroom;

max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);

From: "Andrea Parri (Microsoft)" parri.andrea@gmail.com

[ Upstream commit 3b8c72d076c42bf27284cda7b2b2b522810686f8 ]

Check that the packet is of the expected size at least, don't copy data past the packet.

Link: https://lore.kernel.org/r/20201118145348.109879-1-parri.andrea@gmail.com Cc: "James E.J. Bottomley" jejb@linux.ibm.com Cc: "Martin K. Petersen" martin.petersen@oracle.com Cc: linux-scsi@vger.kernel.org Reported-by: Saruhan Karademir skarade@microsoft.com Signed-off-by: Andrea Parri (Microsoft) parri.andrea@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/storvsc_drv.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 5087ed6afbdc3..9f78630e332f9 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1170,6 +1170,11 @@ static void storvsc_on_channel_callback(void *context) request = (struct storvsc_cmd_request *) ((unsigned long)desc->trans_id);

+ if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) - vmscsi_size_delta) { + dev_err(&device->device, "Invalid packet len\n"); + continue; + } + if (request == &stor_device->init_request || request == &stor_device->reset_request) { memcpy(&request->vstor_packet, packet,

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit e7b624183d921b49ef0a96329f21647d38865ee9 ]

The BUG_ON(in_interrupt()) in dm_table_event() is a historic leftover from a rework of the dm table code which changed the calling context.

Issuing a BUG for a wrong calling context is frowned upon and in_interrupt() is deprecated and only covering parts of the wrong contexts. The sanity check for the context is covered by CONFIG_DEBUG_ATOMIC_SLEEP and other debug facilities already.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/dm-table.c | 6 ------ 1 file changed, 6 deletions(-)

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 13ad791126618..6dd56afa048c2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1320,12 +1320,6 @@ void dm_table_event_callback(struct dm_table *t,

void dm_table_event(struct dm_table *t) { - /* - * You can no longer call dm_table_event() from interrupt - * context, use a bottom half instead. - */ - BUG_ON(in_interrupt()); - mutex_lock(&_event_lock); if (t->event_fn) t->event_fn(t->event_context);

From: Brandon Syu Brandon.Syu@amd.com

[ Upstream commit 7e0b367db85ef7b91399006253759a024eab7653 ]

[Why] While booting into OS, driver updates DPP/DISP CLKs. But init clock value is zero which is invalid.

[How] Get current clocks value to update init clocks. To avoid underflow.

Signed-off-by: Brandon Syu Brandon.Syu@amd.com Reviewed-by: Tony Cheng Tony.Cheng@amd.com Acked-by: Aurabindo Pillai aurabindo.pillai@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index dd92f9c295b45..9f301f8575a54 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -97,8 +97,17 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, new_clocks->dppclk_khz = 100000; }

- if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { - if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz) + /* + * Temporally ignore thew 0 cases for disp and dpp clks. + * We may have a new feature that requires 0 clks in the future. + */ + if (new_clocks->dppclk_khz == 0 || new_clocks->dispclk_khz == 0) { + new_clocks->dppclk_khz = clk_mgr_base->clks.dppclk_khz; + new_clocks->dispclk_khz = clk_mgr_base->clks.dispclk_khz; + } + + if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr_base->clks.dppclk_khz)) { + if (clk_mgr_base->clks.dppclk_khz > new_clocks->dppclk_khz) dpp_clock_lowered = true; clk_mgr_base->clks.dppclk_khz = new_clocks->dppclk_khz; update_dppclk = true;

From: Masahiro Yamada masahiroy@kernel.org

[ Upstream commit 7d32358be8acb119dcfe39b6cf67ec6d94bf1fe7 ]

"xargs echo" is not a safe way to remove line breaks because the input may exceed the command line limit and xargs may break it up into multiple invocations of echo. This should never happen because scripts/gen_autoksyms.sh expects all undefined symbols are placed in the second line of .mod files.

One possible way is to replace "xargs echo" with "sed ':x;N;$!bx;s/\n/ /g'" or something, but I rewrote the code by using awk because it is more readable.

This issue was reported by Sami Tolvanen; in his Clang LTO patch set, $(multi-used-m) is no longer an ELF object, but a thin archive that contains LLVM bitcode files. llvm-nm prints out symbols for each archive member separately, which results a lot of dupications, in some places, beyond the system-defined limit.

This problem must be fixed irrespective of LTO, and we must ensure zero possibility of having this issue.

Link: https://lkml.org/lkml/2020/12/1/1658 Reported-by: Sami Tolvanen samitolvanen@google.com Signed-off-by: Masahiro Yamada masahiroy@kernel.org Reviewed-by: Sami Tolvanen samitolvanen@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/Makefile.build | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 24a33c01bbf7c..9c689d011bced 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -234,6 +234,9 @@ objtool_dep = $(objtool_obj) \ ifdef CONFIG_TRIM_UNUSED_KSYMS cmd_gen_ksymdeps = \ $(CONFIG_SHELL) $(srctree)/scripts/gen_ksymdeps.sh $@ >> $(dot-target).cmd + +# List module undefined symbols +undefined_syms = $(NM) $< | $(AWK) '$$1 == "U" { printf("%s%s", x++ ? " " : "", $$2) }'; endif

define rule_cc_o_c @@ -253,13 +256,6 @@ define rule_as_o_S $(call cmd,modversions_S) endef

-# List module undefined symbols (or empty line if not enabled) -ifdef CONFIG_TRIM_UNUSED_KSYMS -cmd_undef_syms = $(NM) $< | sed -n 's/^ *U //p' | xargs echo -else -cmd_undef_syms = echo -endif - # Built-in and composite module parts $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_dep) FORCE $(call cmd,force_checksrc) @@ -267,7 +263,7 @@ $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_dep) FORCE

cmd_mod = { \ echo $(if $($*-objs)$($*-y)$($*-m), $(addprefix $(obj)/, $($*-objs) $($*-y) $($*-m)), $(@:.mod=.o)); \ - $(cmd_undef_syms); \ + $(undefined_syms) echo; \ } > $@

$(obj)/%.mod: $(obj)/%.o FORCE