From: Qiujun Huang hqjagain@gmail.com

[ Upstream commit e4ff08a4d727146bb6717a39a8d399d834654345 ]

Write out of slab bounds. We should check epid.

The case reported by syzbot: https://lore.kernel.org/linux-usb/0000000000006ac55b05a1c05d72@google.com BUG: KASAN: use-after-free in htc_process_conn_rsp drivers/net/wireless/ath/ath9k/htc_hst.c:131 [inline] BUG: KASAN: use-after-free in ath9k_htc_rx_msg+0xa25/0xaf0 drivers/net/wireless/ath/ath9k/htc_hst.c:443 Write of size 2 at addr ffff8881cea291f0 by task swapper/1/0

Call Trace: htc_process_conn_rsp drivers/net/wireless/ath/ath9k/htc_hst.c:131 [inline] ath9k_htc_rx_msg+0xa25/0xaf0 drivers/net/wireless/ath/ath9k/htc_hst.c:443 ath9k_hif_usb_reg_in_cb+0x1ba/0x630 drivers/net/wireless/ath/ath9k/hif_usb.c:718 __usb_hcd_giveback_urb+0x29a/0x550 drivers/usb/core/hcd.c:1650 usb_hcd_giveback_urb+0x368/0x420 drivers/usb/core/hcd.c:1716 dummy_timer+0x1258/0x32ae drivers/usb/gadget/udc/dummy_hcd.c:1966 call_timer_fn+0x195/0x6f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0x5f9/0x1500 kernel/time/timer.c:1786

Reported-and-tested-by: syzbot+b1c61e5f11be5782f192@syzkaller.appspotmail.com Signed-off-by: Qiujun Huang hqjagain@gmail.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/20200404041838.10426-4-hqjagain@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath9k/htc_hst.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c index 1bf63a4efb4c..d2e062eaf561 100644 --- a/drivers/net/wireless/ath/ath9k/htc_hst.c +++ b/drivers/net/wireless/ath/ath9k/htc_hst.c @@ -113,6 +113,9 @@ static void htc_process_conn_rsp(struct htc_target *target,

if (svc_rspmsg->status == HTC_SERVICE_SUCCESS) { epid = svc_rspmsg->endpoint_id; + if (epid < 0 || epid >= ENDPOINT_MAX) + return; + service_id = be16_to_cpu(svc_rspmsg->service_id); max_msglen = be16_to_cpu(svc_rspmsg->max_msg_len); endpoint = &target->endpoint[epid];

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit eebac678556d6927f09a992872f4464cf3aecc76 ]

DMADEVICES is the top-level option for the slave DMA subsystem, and should not be selected by device drivers, as this can cause circular dependencies such as:

drivers/net/ethernet/freescale/Kconfig:6:error: recursive dependency detected! drivers/net/ethernet/freescale/Kconfig:6: symbol NET_VENDOR_FREESCALE depends on PPC_BESTCOMM drivers/dma/bestcomm/Kconfig:6: symbol PPC_BESTCOMM depends on DMADEVICES drivers/dma/Kconfig:6: symbol DMADEVICES is selected by CRYPTO_DEV_SP_CCP drivers/crypto/ccp/Kconfig:10: symbol CRYPTO_DEV_SP_CCP depends on CRYPTO crypto/Kconfig:16: symbol CRYPTO is selected by LIBCRC32C lib/Kconfig:222: symbol LIBCRC32C is selected by LIQUIDIO drivers/net/ethernet/cavium/Kconfig:65: symbol LIQUIDIO depends on PTP_1588_CLOCK drivers/ptp/Kconfig:8: symbol PTP_1588_CLOCK is implied by FEC drivers/net/ethernet/freescale/Kconfig:23: symbol FEC depends on NET_VENDOR_FREESCALE

The LIQUIDIO driver causing this problem is addressed in a separate patch, but this change is needed to prevent it from happening again.

Using "depends on DMADEVICES" is what we do for all other implementations of slave DMA controllers as well.

Fixes: b3c2fee5d66b ("crypto: ccp - Ensure all dependencies are specified") Signed-off-by: Arnd Bergmann arnd@arndb.de Acked-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/crypto/ccp/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig index 6d626606b9c5..898dcf3200c3 100644 --- a/drivers/crypto/ccp/Kconfig +++ b/drivers/crypto/ccp/Kconfig @@ -8,10 +8,9 @@ config CRYPTO_DEV_CCP_DD config CRYPTO_DEV_SP_CCP bool "Cryptographic Coprocessor device" default y - depends on CRYPTO_DEV_CCP_DD + depends on CRYPTO_DEV_CCP_DD && DMADEVICES select HW_RANDOM select DMA_ENGINE - select DMADEVICES select CRYPTO_SHA1 select CRYPTO_SHA256 help

From: Julien Thierry jthierry@redhat.com

[ Upstream commit 7170cf47d16f1ba29eca07fd818870b7af0a93a5 ]

The .alternatives section can contain entries with no original instructions. Objtool will currently crash when handling such an entry.

Just skip that entry, but still give a warning to discourage useless entries.

Signed-off-by: Julien Thierry jthierry@redhat.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Miroslav Benes mbenes@suse.cz Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/objtool/check.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5685fe2c7a7d..247fbb5f6a38 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -778,6 +778,12 @@ static int add_special_section_alts(struct objtool_file *file) }

if (special_alt->group) { + if (!special_alt->orig_len) { + WARN_FUNC("empty alternative entry", + orig_insn->sec, orig_insn->offset); + continue; + } + ret = handle_group_alt(file, special_alt, orig_insn, &new_insn); if (ret)

From: Arthur Kiyanovski akiyano@amazon.com

[ Upstream commit e9a1de378dd46375f9abfd8de1e6f59ee114a793 ]

In case the "func" parameter is NULL we now return "-EINVAL". This shouldn't happen in general, but when it does happen, this is the proper way to handle it.

We also check func for NULL in the beginning of the function, as there is no reason to do all the work and realize in the end of the function it was useless.

Signed-off-by: Sameeh Jubran sameehj@amazon.com Signed-off-by: Arthur Kiyanovski akiyano@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/amazon/ena/ena_com.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index dc9149a32f41..bb1710ff910a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -2131,6 +2131,9 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev, rss->hash_key; int rc;

+ if (unlikely(!func)) + return -EINVAL; + rc = ena_com_get_feature_ex(ena_dev, &get_resp, ENA_ADMIN_RSS_HASH_FUNCTION, rss->hash_key_dma_addr, @@ -2143,8 +2146,7 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev, if (rss->hash_func) rss->hash_func--;

- if (func) - *func = rss->hash_func; + *func = rss->hash_func;

if (key) memcpy(key, hash_key->key, (size_t)(hash_key->keys_num) << 2);

From: Jesper Dangaard Brouer brouer@redhat.com

[ Upstream commit 88eb0ee17b2ece64fcf6689a4557a5c2e7a89c4b ]

The ixgbe driver have another memory model when compiled on archs with PAGE_SIZE above 4096 bytes. In this mode it doesn't split the page in two halves, but instead increment rx_buffer->page_offset by truesize of packet (which include headroom and tailroom for skb_shared_info).

This is done correctly in ixgbe_build_skb(), but in ixgbe_rx_buffer_flip which is currently only called on XDP_TX and XDP_REDIRECT, it forgets to add the tailroom for skb_shared_info. This breaks XDP_REDIRECT, for veth and cpumap. Fix by adding size of skb_shared_info tailroom.

Maintainers notice: This fix have been queued to Jeff.

Fixes: 6453073987ba ("ixgbe: add initial support for xdp redirect") Signed-off-by: Jesper Dangaard Brouer brouer@redhat.com Signed-off-by: Alexei Starovoitov ast@kernel.org Cc: Jeff Kirsher jeffrey.t.kirsher@intel.com Link: https://lore.kernel.org/bpf/158945344946.97035.17031588499266605743.stgit@fi... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ba184287e11f..64ee45b6680a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2274,7 +2274,8 @@ static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring, rx_buffer->page_offset ^= truesize; #else unsigned int truesize = ring_uses_build_skb(rx_ring) ? - SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) : + SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : SKB_DATA_ALIGN(size);

rx_buffer->page_offset += truesize;

From: Hsin-Yu Chao hychao@chromium.org

[ Upstream commit 56b5453a86203a44726f523b4133c1feca49ce7c ]

Bluetooth PTS test case HFP/AG/ACC/BI-12-I accepts SCO connection with invalid parameter at the first SCO request expecting AG to attempt another SCO request with the use of "safe settings" for given codec, base on section 5.7.1.2 of HFP 1.7 specification.

This patch addresses it by adding "Invalid LMP Parameters" (0x1e) to the SCO fallback case. Verified with below log:

< HCI Command: Setup Synchronous Connection (0x01|0x0028) plen 17 Handle: 256 Transmit bandwidth: 8000 Receive bandwidth: 8000 Max latency: 13 Setting: 0x0003 Input Coding: Linear Input Data Format: 1's complement Input Sample Size: 8-bit # of bits padding at MSB: 0 Air Coding Format: Transparent Data Retransmission effort: Optimize for link quality (0x02) Packet type: 0x0380 3-EV3 may not be used 2-EV5 may not be used 3-EV5 may not be used

HCI Event: Command Status (0x0f) plen 4

Setup Synchronous Connection (0x01|0x0028) ncmd 1 Status: Success (0x00)

HCI Event: Number of Completed Packets (0x13) plen 5

Num handles: 1 Handle: 256 Count: 1

HCI Event: Max Slots Change (0x1b) plen 3

Handle: 256 Max slots: 1

HCI Event: Synchronous Connect Complete (0x2c) plen 17

Status: Invalid LMP Parameters / Invalid LL Parameters (0x1e) Handle: 0 Address: 00:1B:DC:F2:21:59 (OUI 00-1B-DC) Link type: eSCO (0x02) Transmission interval: 0x00 Retransmission window: 0x02 RX packet length: 0 TX packet length: 0 Air mode: Transparent (0x03) < HCI Command: Setup Synchronous Connection (0x01|0x0028) plen 17 Handle: 256 Transmit bandwidth: 8000 Receive bandwidth: 8000 Max latency: 8 Setting: 0x0003 Input Coding: Linear Input Data Format: 1's complement Input Sample Size: 8-bit # of bits padding at MSB: 0 Air Coding Format: Transparent Data Retransmission effort: Optimize for link quality (0x02) Packet type: 0x03c8 EV3 may be used 2-EV3 may not be used 3-EV3 may not be used 2-EV5 may not be used 3-EV5 may not be used

HCI Event: Command Status (0x0f) plen 4

Setup Synchronous Connection (0x01|0x0028) ncmd 1 Status: Success (0x00)

HCI Event: Max Slots Change (0x1b) plen 3

Handle: 256 Max slots: 5

HCI Event: Max Slots Change (0x1b) plen 3

Handle: 256 Max slots: 1

HCI Event: Synchronous Connect Complete (0x2c) plen 17

Status: Success (0x00) Handle: 257 Address: 00:1B:DC:F2:21:59 (OUI 00-1B-DC) Link type: eSCO (0x02) Transmission interval: 0x06 Retransmission window: 0x04 RX packet length: 30 TX packet length: 30 Air mode: Transparent (0x03)

Signed-off-by: Hsin-Yu Chao hychao@chromium.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/hci_event.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 363dc85bbc5c..56e4ae7d7f63 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3775,6 +3775,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, case 0x11: /* Unsupported Feature or Parameter Value */ case 0x1c: /* SCO interval rejected */ case 0x1a: /* Unsupported Remote Feature */ + case 0x1e: /* Invalid LMP Parameters */ case 0x1f: /* Unspecified error */ case 0x20: /* Unsupported LMP Parameter value */ if (conn->out) {

From: Serge Semin Sergey.Semin@baikalelectronics.ru

[ Upstream commit 43dba9f3f98c2b184a19f856f06fe22817bfd9e0 ]

It's pointless to track the Tx overrun interrupts if Rx-only SPI transfer is issued. Similarly there is no need in handling the Rx overrun/underrun interrupts if Tx-only SPI transfer is executed. So lets unmask the interrupts only if corresponding SPI transactions are implied.

Co-developed-by: Georgy Vlasov Georgy.Vlasov@baikalelectronics.ru Signed-off-by: Georgy Vlasov Georgy.Vlasov@baikalelectronics.ru Signed-off-by: Serge Semin Sergey.Semin@baikalelectronics.ru Cc: Ramil Zaripov Ramil.Zaripov@baikalelectronics.ru Cc: Alexey Malahov Alexey.Malahov@baikalelectronics.ru Cc: Thomas Bogendoerfer tsbogend@alpha.franken.de Cc: Paul Burton paulburton@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Arnd Bergmann arnd@arndb.de Cc: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Rob Herring robh+dt@kernel.org Cc: linux-mips@vger.kernel.org Cc: devicetree@vger.kernel.org Link: https://lore.kernel.org/r/20200522000806.7381-3-Sergey.Semin@baikalelectroni... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-dw-mid.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index 4f41d44e8b4c..c4244d2f1ee3 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -228,19 +228,23 @@ static struct dma_async_tx_descriptor *dw_spi_dma_prepare_rx(struct dw_spi *dws,

static int mid_spi_dma_setup(struct dw_spi *dws, struct spi_transfer *xfer) { - u16 dma_ctrl = 0; + u16 imr = 0, dma_ctrl = 0;

dw_writel(dws, DW_SPI_DMARDLR, 0xf); dw_writel(dws, DW_SPI_DMATDLR, 0x10);

- if (xfer->tx_buf) + if (xfer->tx_buf) { dma_ctrl |= SPI_DMA_TDMAE; - if (xfer->rx_buf) + imr |= SPI_INT_TXOI; + } + if (xfer->rx_buf) { dma_ctrl |= SPI_DMA_RDMAE; + imr |= SPI_INT_RXUI | SPI_INT_RXOI; + } dw_writel(dws, DW_SPI_DMACR, dma_ctrl);

/* Set the interrupt mask */ - spi_umask_intr(dws, SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI); + spi_umask_intr(dws, imr);

dws->transfer_handler = dma_transfer;

From: Serge Semin Sergey.Semin@baikalelectronics.ru

[ Upstream commit 6d2e16a3181bafb77b535095c39ad1c8b9558c8c ]

Commit 100214889973 ("clocksource: dw_apb_timer_of: use clocksource_of_init") replaced a publicly available driver initialization method with one called by the timer_probe() method available after CLKSRC_OF. In current implementation it traverses all the timers available in the system and calls their initialization methods if corresponding devices were either in dtb or in acpi. But if before the commit any number of available timers would be installed as clockevent and clocksource devices, after that there would be at most two. The rest are just ignored since default case branch doesn't do anything. I don't see a reason of such behaviour, neither the commit message explains it. Moreover this might be wrong if on some platforms these timers might be used for different purpose, as virtually CPU-local clockevent timers and as an independent broadcast timer. So in order to keep the compatibility with the platforms where the order of the timers detection has some meaning, lets add the secondly discovered timer to be of clocksource/sched_clock type, while the very first and the others would provide the clockevents service.

Fixes: 100214889973 ("clocksource: dw_apb_timer_of: use clocksource_of_init") Signed-off-by: Serge Semin Sergey.Semin@baikalelectronics.ru Cc: Alexey Malahov Alexey.Malahov@baikalelectronics.ru Cc: Thomas Bogendoerfer tsbogend@alpha.franken.de Cc: Paul Burton paulburton@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Alessandro Zummo a.zummo@towertech.it Cc: Alexandre Belloni alexandre.belloni@bootlin.com Cc: Arnd Bergmann arnd@arndb.de Cc: Rob Herring robh+dt@kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-rtc@vger.kernel.org Cc: devicetree@vger.kernel.org Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Link: https://lore.kernel.org/r/20200521204818.25436-7-Sergey.Semin@baikalelectron... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clocksource/dw_apb_timer_of.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c index 69866cd8f4bb..3e4d0e5733d3 100644 --- a/drivers/clocksource/dw_apb_timer_of.c +++ b/drivers/clocksource/dw_apb_timer_of.c @@ -146,10 +146,6 @@ static int num_called; static int __init dw_apb_timer_init(struct device_node *timer) { switch (num_called) { - case 0: - pr_debug("%s: found clockevent timer\n", __func__); - add_clockevent(timer); - break; case 1: pr_debug("%s: found clocksource timer\n", __func__); add_clocksource(timer); @@ -160,6 +156,8 @@ static int __init dw_apb_timer_init(struct device_node *timer) #endif break; default: + pr_debug("%s: found clockevent timer\n", __func__); + add_clockevent(timer); break; }

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit e1de94380af588bdf6ad6f0cc1f75004c35bc096 ]

Recent work with KASan exposed the folling hard-coded bitmask in arch/arm/mm/proc-macros.S:

bic rd, sp, #8128 bic rd, rd, #63

This forms the bitmask 0x1FFF that is coinciding with (PAGE_SIZE << THREAD_SIZE_ORDER) - 1, this code was assuming that THREAD_SIZE is always 8K (8192).

As KASan was increasing THREAD_SIZE_ORDER to 2, I ran into this bug.

Fix it by this little oneline suggested by Ard:

bic rd, sp, #(THREAD_SIZE - 1) & ~63

Where THREAD_SIZE is defined using THREAD_SIZE_ORDER.

We have to also include <linux/const.h> since the THREAD_SIZE expands to use the _AC() macro.

Cc: Ard Biesheuvel ardb@kernel.org Cc: Florian Fainelli f.fainelli@gmail.com Suggested-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mm/proc-macros.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 5461d589a1e2..60ac7c5999a9 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -5,6 +5,7 @@ * VMA_VM_FLAGS * VM_EXEC */ +#include <linux/const.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h>

@@ -30,7 +31,7 @@ * act_mm - get current->active_mm */ .macro act_mm, rd - bic \rd, sp, #8128 + bic \rd, sp, #(THREAD_SIZE - 1) & ~63 bic \rd, \rd, #63 ldr \rd, [\rd, #TI_TASK] .if (TSK_ACTIVE_MM > IMM12_MASK)

From: Jon Doron arilou@gmail.com

[ Upstream commit f7d31e65368aeef973fab788aa22c4f1d5a6af66 ]

The problem the patch is trying to address is the fact that 'struct kvm_hyperv_exit' has different layout on when compiling in 32 and 64 bit modes.

In 64-bit mode the default alignment boundary is 64 bits thus forcing extra gaps after 'type' and 'msr' but in 32-bit mode the boundary is at 32 bits thus no extra gaps.

This is an issue as even when the kernel is 64 bit, the userspace using the interface can be both 32 and 64 bit but the same 32 bit userspace has to work with 32 bit kernel.

The issue is fixed by forcing the 64 bit layout, this leads to ABI change for 32 bit builds and while we are obviously breaking '32 bit userspace with 32 bit kernel' case, we're fixing the '32 bit userspace with 64 bit kernel' one.

As the interface has no (known) users and 32 bit KVM is rather baroque nowadays, this seems like a reasonable decision.

Reviewed-by: Vitaly Kuznetsov vkuznets@redhat.com Signed-off-by: Jon Doron arilou@gmail.com Message-Id: 20200424113746.3473563-2-arilou@gmail.com Reviewed-by: Roman Kagan rvkagan@yandex-team.ru Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/virtual/kvm/api.txt | 2 ++ include/uapi/linux/kvm.h | 2 ++ 2 files changed, 4 insertions(+)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index f67ed33d1054..81a8802cea88 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3737,9 +3737,11 @@ EOI was received. #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 __u32 type; + __u32 pad1; union { struct { __u32 msr; + __u32 pad2; __u64 control; __u64 evt_page; __u64 msg_page; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 27c62abb6c9e..efe8873943f6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -189,9 +189,11 @@ struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 __u32 type; + __u32 pad1; union { struct { __u32 msr; + __u32 pad2; __u64 control; __u64 evt_page; __u64 msg_page;

From: Christoph Hellwig hch@lst.de

[ Upstream commit 5bf9917452112694b2c774465ee4dbe441c84b77 ]

vm_map_ram can keep mappings around after the vm_unmap_ram. Using that with non-PAGE_KERNEL mappings can lead to all kinds of aliasing issues.

Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Andrew Morton akpm@linux-foundation.org Acked-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Christian Borntraeger borntraeger@de.ibm.com Cc: Christophe Leroy christophe.leroy@c-s.fr Cc: Daniel Vetter daniel.vetter@ffwll.ch Cc: David Airlie airlied@linux.ie Cc: Gao Xiang xiang@kernel.org Cc: Haiyang Zhang haiyangz@microsoft.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: "K. Y. Srinivasan" kys@microsoft.com Cc: Laura Abbott labbott@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Michael Kelley mikelley@microsoft.com Cc: Minchan Kim minchan@kernel.org Cc: Nitin Gupta ngupta@vflare.org Cc: Robin Murphy robin.murphy@arm.com Cc: Sakari Ailus sakari.ailus@linux.intel.com Cc: Stephen Hemminger sthemmin@microsoft.com Cc: Sumit Semwal sumit.semwal@linaro.org Cc: Wei Liu wei.liu@kernel.org Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Heiko Carstens heiko.carstens@de.ibm.com Cc: Paul Mackerras paulus@ozlabs.org Cc: Vasily Gorbik gor@linux.ibm.com Cc: Will Deacon will@kernel.org Link: http://lkml.kernel.org/r/20200414131348.444715-4-hch@lst.de Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/android/ion/ion_heap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c index babbd94c32d9..33a9777e7a99 100644 --- a/drivers/staging/android/ion/ion_heap.c +++ b/drivers/staging/android/ion/ion_heap.c @@ -105,12 +105,12 @@ int ion_heap_map_user(struct ion_heap *heap, struct ion_buffer *buffer,

static int ion_heap_clear_pages(struct page **pages, int num, pgprot_t pgprot) { - void *addr = vm_map_ram(pages, num, -1, pgprot); + void *addr = vmap(pages, num, VM_MAP, pgprot);

if (!addr) return -ENOMEM; memset(addr, 0, PAGE_SIZE * num); - vm_unmap_ram(addr, num); + vunmap(addr);

return 0; }

From: Qiujun Huang hqjagain@gmail.com

[ Upstream commit 2bbcaaee1fcbd83272e29f31e2bb7e70d8c49e05 ]

In ath9k_hif_usb_rx_cb interface number is assumed to be 0. usb_ifnum_to_if(urb->dev, 0) But it isn't always true.

The case reported by syzbot: https://lore.kernel.org/linux-usb/000000000000666c9c05a1c05d12@google.com usb 2-1: new high-speed USB device number 2 using dummy_hcd usb 2-1: config 1 has an invalid interface number: 2 but max is 0 usb 2-1: config 1 has no interface number 0 usb 2-1: New USB device found, idVendor=0cf3, idProduct=9271, bcdDevice= 1.08 usb 2-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3 general protection fault, probably for non-canonical address 0xdffffc0000000015: 0000 [#1] SMP KASAN KASAN: null-ptr-deref in range [0x00000000000000a8-0x00000000000000af] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.6.0-rc5-syzkaller #0

Call Trace __usb_hcd_giveback_urb+0x29a/0x550 drivers/usb/core/hcd.c:1650 usb_hcd_giveback_urb+0x368/0x420 drivers/usb/core/hcd.c:1716 dummy_timer+0x1258/0x32ae drivers/usb/gadget/udc/dummy_hcd.c:1966 call_timer_fn+0x195/0x6f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0x5f9/0x1500 kernel/time/timer.c:1786 __do_softirq+0x21e/0x950 kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0x178/0x1a0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:546 [inline] smp_apic_timer_interrupt+0x141/0x540 arch/x86/kernel/apic/apic.c:1146 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829

Reported-and-tested-by: syzbot+40d5d2e8a4680952f042@syzkaller.appspotmail.com Signed-off-by: Qiujun Huang hqjagain@gmail.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/20200404041838.10426-6-hqjagain@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath9k/hif_usb.c | 48 ++++++++++++++++++------ drivers/net/wireless/ath/ath9k/hif_usb.h | 5 +++ 2 files changed, 42 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 805d88ecc7ac..4e769cf07f59 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -641,9 +641,9 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev,

static void ath9k_hif_usb_rx_cb(struct urb *urb) { - struct sk_buff *skb = (struct sk_buff *) urb->context; - struct hif_device_usb *hif_dev = - usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0)); + struct rx_buf *rx_buf = (struct rx_buf *)urb->context; + struct hif_device_usb *hif_dev = rx_buf->hif_dev; + struct sk_buff *skb = rx_buf->skb; int ret;

if (!skb) @@ -683,14 +683,15 @@ static void ath9k_hif_usb_rx_cb(struct urb *urb) return; free: kfree_skb(skb); + kfree(rx_buf); }

static void ath9k_hif_usb_reg_in_cb(struct urb *urb) { - struct sk_buff *skb = (struct sk_buff *) urb->context; + struct rx_buf *rx_buf = (struct rx_buf *)urb->context; + struct hif_device_usb *hif_dev = rx_buf->hif_dev; + struct sk_buff *skb = rx_buf->skb; struct sk_buff *nskb; - struct hif_device_usb *hif_dev = - usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0)); int ret;

if (!skb) @@ -748,6 +749,7 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb) return; free: kfree_skb(skb); + kfree(rx_buf); urb->context = NULL; }

@@ -793,7 +795,7 @@ static int ath9k_hif_usb_alloc_tx_urbs(struct hif_device_usb *hif_dev) init_usb_anchor(&hif_dev->mgmt_submitted);

for (i = 0; i < MAX_TX_URB_NUM; i++) { - tx_buf = kzalloc(sizeof(struct tx_buf), GFP_KERNEL); + tx_buf = kzalloc(sizeof(*tx_buf), GFP_KERNEL); if (!tx_buf) goto err;

@@ -830,8 +832,9 @@ static void ath9k_hif_usb_dealloc_rx_urbs(struct hif_device_usb *hif_dev)

static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev) { - struct urb *urb = NULL; + struct rx_buf *rx_buf = NULL; struct sk_buff *skb = NULL; + struct urb *urb = NULL; int i, ret;

init_usb_anchor(&hif_dev->rx_submitted); @@ -839,6 +842,12 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)

for (i = 0; i < MAX_RX_URB_NUM; i++) {

+ rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL); + if (!rx_buf) { + ret = -ENOMEM; + goto err_rxb; + } + /* Allocate URB */ urb = usb_alloc_urb(0, GFP_KERNEL); if (urb == NULL) { @@ -853,11 +862,14 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev) goto err_skb; }

+ rx_buf->hif_dev = hif_dev; + rx_buf->skb = skb; + usb_fill_bulk_urb(urb, hif_dev->udev, usb_rcvbulkpipe(hif_dev->udev, USB_WLAN_RX_PIPE), skb->data, MAX_RX_BUF_SIZE, - ath9k_hif_usb_rx_cb, skb); + ath9k_hif_usb_rx_cb, rx_buf);

/* Anchor URB */ usb_anchor_urb(urb, &hif_dev->rx_submitted); @@ -883,6 +895,8 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev) err_skb: usb_free_urb(urb); err_urb: + kfree(rx_buf); +err_rxb: ath9k_hif_usb_dealloc_rx_urbs(hif_dev); return ret; } @@ -894,14 +908,21 @@ static void ath9k_hif_usb_dealloc_reg_in_urbs(struct hif_device_usb *hif_dev)

static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev) { - struct urb *urb = NULL; + struct rx_buf *rx_buf = NULL; struct sk_buff *skb = NULL; + struct urb *urb = NULL; int i, ret;

init_usb_anchor(&hif_dev->reg_in_submitted);

for (i = 0; i < MAX_REG_IN_URB_NUM; i++) {

+ rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL); + if (!rx_buf) { + ret = -ENOMEM; + goto err_rxb; + } + /* Allocate URB */ urb = usb_alloc_urb(0, GFP_KERNEL); if (urb == NULL) { @@ -916,11 +937,14 @@ static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev) goto err_skb; }

+ rx_buf->hif_dev = hif_dev; + rx_buf->skb = skb; + usb_fill_int_urb(urb, hif_dev->udev, usb_rcvintpipe(hif_dev->udev, USB_REG_IN_PIPE), skb->data, MAX_REG_IN_BUF_SIZE, - ath9k_hif_usb_reg_in_cb, skb, 1); + ath9k_hif_usb_reg_in_cb, rx_buf, 1);

/* Anchor URB */ usb_anchor_urb(urb, &hif_dev->reg_in_submitted); @@ -946,6 +970,8 @@ static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev) err_skb: usb_free_urb(urb); err_urb: + kfree(rx_buf); +err_rxb: ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev); return ret; } diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.h b/drivers/net/wireless/ath/ath9k/hif_usb.h index a94e7e1c86e9..5985aa15ca93 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.h +++ b/drivers/net/wireless/ath/ath9k/hif_usb.h @@ -86,6 +86,11 @@ struct tx_buf { struct list_head list; };

+struct rx_buf { + struct sk_buff *skb; + struct hif_device_usb *hif_dev; +}; + #define HIF_USB_TX_STOP BIT(0) #define HIF_USB_TX_FLUSH BIT(1)

From: Stephane Eranian eranian@google.com

[ Upstream commit c6fddb28bad26e5472cb7acf7b04cd5126f1a4ab ]

The xxx_mountpoint() interface provided by fs.c finds mount points for common pseudo filesystems. The first time xxx_mountpoint() is invoked, it scans the mount table (/proc/mounts) looking for a match. If found, it is cached. The price to scan /proc/mounts is paid once if the mount is found.

When the mount point is not found, subsequent calls to xxx_mountpoint() scan /proc/mounts over and over again. There is no caching.

This causes a scaling issue in perf record with hugeltbfs__mountpoint(). The function is called for each process found in synthesize__mmap_events(). If the machine has thousands of processes and if the /proc/mounts has many entries this could cause major overhead in perf record. We have observed multi-second slowdowns on some configurations.

As an example on a laptop:

Before:

$ sudo umount /dev/hugepages $ strace -e trace=openat -o /tmp/tt perf record -a ls $ fgrep mounts /tmp/tt 285

After:

$ sudo umount /dev/hugepages $ strace -e trace=openat -o /tmp/tt perf record -a ls $ fgrep mounts /tmp/tt 1

One could argue that the non-caching in case the moint point is not found is intentional. That way subsequent calls may discover a moint point if the sysadmin mounts the filesystem. But the same argument could be made against caching the mount point. It could be unmounted causing errors. It all depends on the intent of the interface. This patch assumes it is expected to scan /proc/mounts once. The patch documents the caching behavior in the fs.h header file.

An alternative would be to just fix perf record. But it would solve the problem with hugetlbs__mountpoint() but there could be similar issues (possibly down the line) with other xxx_mountpoint() calls in perf or other tools.

Signed-off-by: Stephane Eranian eranian@google.com Reviewed-by: Ian Rogers irogers@google.com Acked-by: Jiri Olsa jolsa@redhat.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Andrey Zhizhikin andrey.z@gmail.com Cc: Kan Liang kan.liang@linux.intel.com Cc: Kefeng Wang wangkefeng.wang@huawei.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Petr Mladek pmladek@suse.com Cc: Thomas Gleixner tglx@linutronix.de Link: http://lore.kernel.org/lkml/20200402154357.107873-3-irogers@google.com Signed-off-by: Ian Rogers irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/api/fs/fs.c | 17 +++++++++++++++++ tools/lib/api/fs/fs.h | 12 ++++++++++++ 2 files changed, 29 insertions(+)

diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 45b50b89009a..c61841051a90 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -90,6 +90,7 @@ struct fs { const char * const *mounts; char path[PATH_MAX]; bool found; + bool checked; long magic; };

@@ -111,31 +112,37 @@ static struct fs fs__entries[] = { .name = "sysfs", .mounts = sysfs__fs_known_mountpoints, .magic = SYSFS_MAGIC, + .checked = false, }, [FS__PROCFS] = { .name = "proc", .mounts = procfs__known_mountpoints, .magic = PROC_SUPER_MAGIC, + .checked = false, }, [FS__DEBUGFS] = { .name = "debugfs", .mounts = debugfs__known_mountpoints, .magic = DEBUGFS_MAGIC, + .checked = false, }, [FS__TRACEFS] = { .name = "tracefs", .mounts = tracefs__known_mountpoints, .magic = TRACEFS_MAGIC, + .checked = false, }, [FS__HUGETLBFS] = { .name = "hugetlbfs", .mounts = hugetlbfs__known_mountpoints, .magic = HUGETLBFS_MAGIC, + .checked = false, }, [FS__BPF_FS] = { .name = "bpf", .mounts = bpf_fs__known_mountpoints, .magic = BPF_FS_MAGIC, + .checked = false, }, };

@@ -158,6 +165,7 @@ static bool fs__read_mounts(struct fs *fs) }

fclose(fp); + fs->checked = true; return fs->found = found; }

@@ -220,6 +228,7 @@ static bool fs__env_override(struct fs *fs) return false;

fs->found = true; + fs->checked = true; strncpy(fs->path, override_path, sizeof(fs->path) - 1); fs->path[sizeof(fs->path) - 1] = '\0'; return true; @@ -246,6 +255,14 @@ static const char *fs__mountpoint(int idx) if (fs->found) return (const char *)fs->path;

+ /* the mount point was already checked for the mount point + * but and did not exist, so return NULL to avoid scanning again. + * This makes the found and not found paths cost equivalent + * in case of multiple calls. + */ + if (fs->checked) + return NULL; + return fs__get_mountpoint(fs); }

diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index dda49deefb52..57a3dc160b08 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -18,6 +18,18 @@ const char *name##__mount(void); \ bool name##__configured(void); \

+/* + * The xxxx__mountpoint() entry points find the first match mount point for each + * filesystems listed below, where xxxx is the filesystem type. + * + * The interface is as follows: + * + * - If a mount point is found on first call, it is cached and used for all + * subsequent calls. + * + * - If a mount point is not found, NULL is returned on first call and all + * subsequent calls. + */ FS(sysfs) FS(procfs) FS(debugfs)

From: Jitao Shi jitao.shi@mediatek.com

[ Upstream commit b0ff9b590733079f7f9453e5976a9dd2630949e3 ]

Add property "pinctrl-names" to swap pin mode between gpio and dpi mode. Set the dpi pins to gpio mode and output-low to avoid leakage current when dpi disabled.

Acked-by: Rob Herring robh@kernel.org Signed-off-by: Jitao Shi jitao.shi@mediatek.com Signed-off-by: Chun-Kuang Hu chunkuang.hu@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../devicetree/bindings/display/mediatek/mediatek,dpi.txt | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt index b6a7e7397b8b..b944fe067188 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt @@ -16,6 +16,9 @@ Required properties: Documentation/devicetree/bindings/graph.txt. This port should be connected to the input port of an attached HDMI or LVDS encoder chip.

+Optional properties: +- pinctrl-names: Contain "default" and "sleep". + Example:

dpi0: dpi@1401d000 { @@ -26,6 +29,9 @@ dpi0: dpi@1401d000 { <&mmsys CLK_MM_DPI_ENGINE>, <&apmixedsys CLK_APMIXED_TVDPLL>; clock-names = "pixel", "engine", "pll"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&dpi_pin_func>; + pinctrl-1 = <&dpi_pin_idle>;

port { dpi0_out: endpoint {

From: Colin Ian King colin.king@canonical.com

[ Upstream commit 96f3a9392799dd0f6472648a7366622ffd0989f3 ]

Currently when i2c transfers fail the error return -EREMOTEIO is assigned to err but then later overwritten when the tuner attach call is made. Fix this by returning early with the error return code -EREMOTEIO on i2c transfer failure errors.

If the transfer fails, an uninitialized value will be read from b2.

Addresses-Coverity: ("Unused value")

Fixes: fbfee8684ff2 ("V4L/DVB (5651): Dibusb-mb: convert pll handling to properly use dvb-pll") Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: Sean Young sean@mess.org Signed-off-by: Mauro Carvalho Chehab mchehab+huawei@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/dvb-usb/dibusb-mb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/dvb-usb/dibusb-mb.c b/drivers/media/usb/dvb-usb/dibusb-mb.c index a0057641cc86..c55180912c3a 100644 --- a/drivers/media/usb/dvb-usb/dibusb-mb.c +++ b/drivers/media/usb/dvb-usb/dibusb-mb.c @@ -84,7 +84,7 @@ static int dibusb_tuner_probe_and_attach(struct dvb_usb_adapter *adap)

if (i2c_transfer(&adap->dev->i2c_adap, msg, 2) != 2) { err("tuner i2c write failed."); - ret = -EREMOTEIO; + return -EREMOTEIO; }

if (adap->fe_adap[0].fe->ops.i2c_gate_ctrl)

From: Tiezhu Yang yangtiezhu@loongson.cn

[ Upstream commit 269b3a9ac538c4ae87f84be640b9fa89914a2489 ]

In the current code, if CONFIG_SWIOTLB is set, when failed to get IO TLB memory from the low pages by plat_swiotlb_setup(), it may lead to the boot process failed with kernel panic.

(1) On the Loongson and SiByte platform arch/mips/loongson64/dma.c arch/mips/sibyte/common/dma.c void __init plat_swiotlb_setup(void) { swiotlb_init(1); }

kernel/dma/swiotlb.c void __init swiotlb_init(int verbose) { ... vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE); if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; ... pr_warn("Cannot allocate buffer"); no_iotlb_memory = true; }

phys_addr_t swiotlb_tbl_map_single() { ... if (no_iotlb_memory) panic("Can not allocate SWIOTLB buffer earlier ..."); ... }

(2) On the Cavium OCTEON platform arch/mips/cavium-octeon/dma-octeon.c void __init plat_swiotlb_setup(void) { ... octeon_swiotlb = memblock_alloc_low(swiotlbsize, PAGE_SIZE); if (!octeon_swiotlb) panic("%s: Failed to allocate %zu bytes align=%lx\n", __func__, swiotlbsize, PAGE_SIZE); ... }

Because IO_TLB_DEFAULT_SIZE is 64M, if the rest size of low memory is less than 64M when call plat_swiotlb_setup(), we can easily reproduce the panic case.

In order to reduce the possibility of kernel panic when failed to get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate low memory as small as possible before plat_swiotlb_setup(), so make sparse_init() using top-down allocation.

Reported-by: Juxin Gao gaojuxin@loongson.cn Co-developed-by: Juxin Gao gaojuxin@loongson.cn Signed-off-by: Juxin Gao gaojuxin@loongson.cn Signed-off-by: Tiezhu Yang yangtiezhu@loongson.cn Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/kernel/setup.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 05ed4ed411c7..abd7ee9e90ab 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -911,7 +911,17 @@ static void __init arch_mem_init(char **cmdline_p) BOOTMEM_DEFAULT); #endif device_tree_init(); + + /* + * In order to reduce the possibility of kernel panic when failed to + * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate + * low memory as small as possible before plat_swiotlb_setup(), so + * make sparse_init() using top-down allocation. + */ + memblock_set_bottom_up(false); sparse_init(); + memblock_set_bottom_up(true); + plat_swiotlb_setup();

dma_contiguous_reserve(PFN_PHYS(max_low_pfn));

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 0d7c83463fdf7841350f37960a7abadd3e650b41 ]

Instead of EINVAL which should be used for malformed netlink messages.

Fixes: eb31628e37a0 ("netfilter: nf_tables: Add support for IPv6 NAT") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_nat.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index ed548d06b6dd..a18cceecef88 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -135,7 +135,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->type = NF_NAT_MANIP_DST; break; default: - return -EINVAL; + return -EOPNOTSUPP; }

if (tb[NFTA_NAT_FAMILY] == NULL) @@ -202,7 +202,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (tb[NFTA_NAT_FLAGS]) { priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS])); if (priv->flags & ~NF_NAT_RANGE_MASK) - return -EINVAL; + return -EOPNOTSUPP; }

return nf_ct_netns_get(ctx->net, family);

From: Nathan Chancellor natechancellor@gmail.com

[ Upstream commit 18f1ca46858eac22437819937ae44aa9a8f9f2fa ]

When building 64r6_defconfig with CONFIG_MIPS32_O32 disabled and CONFIG_CRYPTO_RSA enabled:

lib/mpi/generic_mpih-mul1.c:37:24: error: invalid use of a cast in a inline asm context requiring an l-value: remove the cast or build with -fheinous-gnu-extensions umul_ppmm(prod_high, prod_low, s1_ptr[j], s2_limb); ~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ lib/mpi/longlong.h:664:22: note: expanded from macro 'umul_ppmm' : "=d" ((UDItype)(w0)) ~~~~~~~~~~^~~ lib/mpi/generic_mpih-mul1.c:37:13: error: invalid use of a cast in a inline asm context requiring an l-value: remove the cast or build with -fheinous-gnu-extensions umul_ppmm(prod_high, prod_low, s1_ptr[j], s2_limb); ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ lib/mpi/longlong.h:668:22: note: expanded from macro 'umul_ppmm' : "=d" ((UDItype)(w1)) ~~~~~~~~~~^~~ 2 errors generated.

This special case for umul_ppmm for MIPS64r6 was added in commit bbc25bee37d2b ("lib/mpi: Fix umul_ppmm() for MIPS64r6"), due to GCC being inefficient and emitting a __multi3 intrinsic.

There is no such issue with clang; with this patch applied, I can build this configuration without any problems and there are no link errors like mentioned in the commit above (which I can still reproduce with GCC 9.3.0 when that commit is reverted). Only use this definition when GCC is being used.

This really should have been caught by commit b0c091ae04f67 ("lib/mpi: Eliminate unused umul_ppmm definitions for MIPS") when I was messing around in this area but I was not testing 64-bit MIPS at the time.

Link: https://github.com/ClangBuiltLinux/linux/issues/885 Reported-by: Dmitry Golovin dima@golovin.in Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- lib/mpi/longlong.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h index e01b705556aa..6c5229f98c9e 100644 --- a/lib/mpi/longlong.h +++ b/lib/mpi/longlong.h @@ -671,7 +671,7 @@ do { \ ************** MIPS/64 ************** ***************************************/ #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64 -#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 +#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 && defined(CONFIG_CC_IS_GCC) /* * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C * code below, so we special case MIPS64r6 until the compiler can do better.

From: Jann Horn jannh@google.com

[ Upstream commit 586b58cac8b4683eb58a1446fbc399de18974e40 ]

With CONFIG_DEBUG_ATOMIC_SLEEP=y and CONFIG_CGROUPS=y, kernel oopses in non-preemptible context look untidy; after the main oops, the kernel prints a "sleeping function called from invalid context" report because exit_signals() -> cgroup_threadgroup_change_begin() -> percpu_down_read() can sleep, and that happens before the preempt_count_set(PREEMPT_ENABLED) fixup.

It looks like the same thing applies to profile_task_exit() and kcov_task_exit().

Fix it by moving the preemption fixup up and the calls to profile_task_exit() and kcov_task_exit() down.

Fixes: 1dc0fffc48af ("sched/core: Robustify preemption leak checks") Signed-off-by: Jann Horn jannh@google.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20200305220657.46800-1-jannh@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/exit.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/kernel/exit.c b/kernel/exit.c index d1baf9c96c3e..8458a81a09e3 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -770,8 +770,12 @@ void __noreturn do_exit(long code) struct task_struct *tsk = current; int group_dead;

- profile_task_exit(tsk); - kcov_task_exit(tsk); + /* + * We can get here from a kernel oops, sometimes with preemption off. + * Start by checking for critical errors. + * Then fix up important state like USER_DS and preemption. + * Then do everything else. + */

WARN_ON(blk_needs_flush_plug(tsk));

@@ -789,6 +793,16 @@ void __noreturn do_exit(long code) */ set_fs(USER_DS);

+ if (unlikely(in_atomic())) { + pr_info("note: %s[%d] exited with preempt_count %d\n", + current->comm, task_pid_nr(current), + preempt_count()); + preempt_count_set(PREEMPT_ENABLED); + } + + profile_task_exit(tsk); + kcov_task_exit(tsk); + ptrace_event(PTRACE_EVENT_EXIT, code);

validate_creds_for_do_exit(tsk); @@ -806,13 +820,6 @@ void __noreturn do_exit(long code)

exit_signals(tsk); /* sets PF_EXITING */

- if (unlikely(in_atomic())) { - pr_info("note: %s[%d] exited with preempt_count %d\n", - current->comm, task_pid_nr(current), - preempt_count()); - preempt_count_set(PREEMPT_ENABLED); - } - /* sync mm's RSS info before statistics gathering */ if (tsk->mm) sync_mm_rss(tsk->mm);

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit 3b5af3171e2d5a73ae6f04965ed653d039904eb6 ]

The log_addrs->log_addr_type[i] value is a u8 which is controlled by the user and comes from the ioctl. If it's over 31 then that results in undefined behavior (shift wrapping) and that leads to a Smatch static checker warning. We already cap the value later so we can silence the warning just by re-ordering the existing checks.

I think the UBSan checker will also catch this bug at runtime and generate a warning. But otherwise the bug is harmless.

Fixes: 9881fe0ca187 ("[media] cec: add HDMI CEC framework (adapter)") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+huawei@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/cec/cec-adap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 0d7d687aeea0..061b7824f698 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -1624,6 +1624,10 @@ int __cec_s_log_addrs(struct cec_adapter *adap, unsigned j;

log_addrs->log_addr[i] = CEC_LOG_ADDR_INVALID; + if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) { + dprintk(1, "unknown logical address type\n"); + return -EINVAL; + } if (type_mask & (1 << log_addrs->log_addr_type[i])) { dprintk(1, "duplicate logical address type\n"); return -EINVAL; @@ -1644,10 +1648,6 @@ int __cec_s_log_addrs(struct cec_adapter *adap, dprintk(1, "invalid primary device type\n"); return -EINVAL; } - if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) { - dprintk(1, "unknown logical address type\n"); - return -EINVAL; - } for (j = 0; j < feature_sz; j++) { if ((features[j] & 0x80) == 0) { if (op_is_dev_features)

From: Jeremy Kerr jk@ozlabs.org

[ Upstream commit 88413a6bfbbe2f648df399b62f85c934460b7a4d ]

Currently, we may perform a copy_to_user (through simple_read_from_buffer()) while holding a context's register_lock, while accessing the context save area.

This change uses a temporary buffer for the context save area data, which we then pass to simple_read_from_buffer.

Includes changes from Christoph Hellwig hch@lst.de.

Fixes: bf1ab978be23 ("[POWERPC] coredump: Add SPU elf notes to coredump.") Signed-off-by: Jeremy Kerr jk@ozlabs.org Reviewed-by: Arnd Bergmann arnd@arndb.de [hch: renamed to function to avoid ___-prefixes] Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/platforms/cell/spufs/file.c | 113 +++++++++++++++-------- 1 file changed, 75 insertions(+), 38 deletions(-)

diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 5ffcdeb1eb17..9d9fffaedeef 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1988,8 +1988,9 @@ static ssize_t __spufs_mbox_info_read(struct spu_context *ctx, static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { - int ret; struct spu_context *ctx = file->private_data; + u32 stat, data; + int ret;

if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT; @@ -1998,11 +1999,16 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_mbox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.prob.pu_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx);

- return ret; + /* EOF if there's no entry in the mbox */ + if (!(stat & 0x0000ff)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); }

static const struct file_operations spufs_mbox_info_fops = { @@ -2029,6 +2035,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + u32 stat, data; int ret;

if (!access_ok(VERIFY_WRITE, buf, len)) @@ -2038,11 +2045,16 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_ibox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.priv2.puint_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx);

- return ret; + /* EOF if there's no entry in the ibox */ + if (!(stat & 0xff0000)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); }

static const struct file_operations spufs_ibox_info_fops = { @@ -2051,6 +2063,11 @@ static const struct file_operations spufs_ibox_info_fops = { .llseek = generic_file_llseek, };

+static size_t spufs_wbox_info_cnt(struct spu_context *ctx) +{ + return (4 - ((ctx->csa.prob.mb_stat_R & 0x00ff00) >> 8)) * sizeof(u32); +} + static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { @@ -2059,7 +2076,7 @@ static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, u32 wbox_stat;

wbox_stat = ctx->csa.prob.mb_stat_R; - cnt = 4 - ((wbox_stat & 0x00ff00) >> 8); + cnt = spufs_wbox_info_cnt(ctx); for (i = 0; i < cnt; i++) { data[i] = ctx->csa.spu_mailbox_data[i]; } @@ -2072,7 +2089,8 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; - int ret; + u32 data[ARRAY_SIZE(ctx->csa.spu_mailbox_data)]; + int ret, count;

if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT; @@ -2081,11 +2099,13 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_wbox_info_read(ctx, buf, len, pos); + count = spufs_wbox_info_cnt(ctx); + memcpy(&data, &ctx->csa.spu_mailbox_data, sizeof(data)); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx);

- return ret; + return simple_read_from_buffer(buf, len, pos, &data, + count * sizeof(u32)); }

static const struct file_operations spufs_wbox_info_fops = { @@ -2094,27 +2114,33 @@ static const struct file_operations spufs_wbox_info_fops = { .llseek = generic_file_llseek, };

-static ssize_t __spufs_dma_info_read(struct spu_context *ctx, - char __user *buf, size_t len, loff_t *pos) +static void spufs_get_dma_info(struct spu_context *ctx, + struct spu_dma_info *info) { - struct spu_dma_info info; - struct mfc_cq_sr *qp, *spuqp; int i;

- info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; - info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; - info.dma_info_status = ctx->csa.spu_chnldata_RW[24]; - info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; - info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; + info->dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; + info->dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; + info->dma_info_status = ctx->csa.spu_chnldata_RW[24]; + info->dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; + info->dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; for (i = 0; i < 16; i++) { - qp = &info.dma_info_command_data[i]; - spuqp = &ctx->csa.priv2.spuq[i]; + struct mfc_cq_sr *qp = &info->dma_info_command_data[i]; + struct mfc_cq_sr *spuqp = &ctx->csa.priv2.spuq[i];

qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW; qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW; qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW; qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW; } +} + +static ssize_t __spufs_dma_info_read(struct spu_context *ctx, + char __user *buf, size_t len, loff_t *pos) +{ + struct spu_dma_info info; + + spufs_get_dma_info(ctx, &info);

return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2124,6 +2150,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_dma_info info; int ret;

if (!access_ok(VERIFY_WRITE, buf, len)) @@ -2133,11 +2160,12 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_dma_info_read(ctx, buf, len, pos); + spufs_get_dma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx);

- return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); }

static const struct file_operations spufs_dma_info_fops = { @@ -2146,13 +2174,31 @@ static const struct file_operations spufs_dma_info_fops = { .llseek = no_llseek, };

+static void spufs_get_proxydma_info(struct spu_context *ctx, + struct spu_proxydma_info *info) +{ + int i; + + info->proxydma_info_type = ctx->csa.prob.dma_querytype_RW; + info->proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; + info->proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; + + for (i = 0; i < 8; i++) { + struct mfc_cq_sr *qp = &info->proxydma_info_command_data[i]; + struct mfc_cq_sr *puqp = &ctx->csa.priv2.puq[i]; + + qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; + qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; + qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; + qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; + } +} + static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { struct spu_proxydma_info info; - struct mfc_cq_sr *qp, *puqp; int ret = sizeof info; - int i;

if (len < ret) return -EINVAL; @@ -2160,18 +2206,7 @@ static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT;

- info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW; - info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; - info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; - for (i = 0; i < 8; i++) { - qp = &info.proxydma_info_command_data[i]; - puqp = &ctx->csa.priv2.puq[i]; - - qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; - qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; - qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; - qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; - } + spufs_get_proxydma_info(ctx, &info);

return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2181,17 +2216,19 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_proxydma_info info; int ret;

ret = spu_acquire_saved(ctx); if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_proxydma_info_read(ctx, buf, len, pos); + spufs_get_proxydma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx);

- return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); }

static const struct file_operations spufs_proxydma_info_fops = {

From: Devulapally Shiva Krishna shiva@chelsio.com

[ Upstream commit 10b0c75d7bc19606fa9a62c8ab9180e95c0e0385 ]

The ccm(aes) test fails when req->assoclen > ~240bytes.

The problem is the value assigned to auth_offset is wrong. As auth_offset is unsigned char, it can take max value as 255. So fix it by making it unsigned int.

Signed-off-by: Ayush Sawal ayush.sawal@chelsio.com Signed-off-by: Devulapally Shiva Krishna shiva@chelsio.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/crypto/chelsio/chcr_algo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index 8d39f3a07bf8..99c3827855c7 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -2201,7 +2201,7 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl, unsigned int mac_mode = CHCR_SCMD_AUTH_MODE_CBCMAC; unsigned int c_id = chcrctx->dev->rx_channel_id; unsigned int ccm_xtra; - unsigned char tag_offset = 0, auth_offset = 0; + unsigned int tag_offset = 0, auth_offset = 0; unsigned int assoclen;

if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309)

From: Serge Semin Sergey.Semin@baikalelectronics.ru

[ Upstream commit 8a0efb8b101665a843205eab3d67ab09cb2d9a8d ]

Commit 3885c2b463f6 ("MIPS: CM: Add support for reporting CM cache errors") adds cm2_causes[] array with map of error type ID and pointers to the short description string. There is a mistake in the table, since according to MIPS32 manual CM2_ERROR_TYPE = {17,18} correspond to INTVN_WR_ERR and INTVN_RD_ERR, while the table claims they have {0x17,0x18} codes. This is obviously hex-dec copy-paste bug. Moreover codes {0x18 - 0x1a} indicate L2 ECC errors.

Fixes: 3885c2b463f6 ("MIPS: CM: Add support for reporting CM cache errors") Signed-off-by: Serge Semin Sergey.Semin@baikalelectronics.ru Cc: Alexey Malahov Alexey.Malahov@baikalelectronics.ru Cc: Thomas Bogendoerfer tsbogend@alpha.franken.de Cc: Paul Burton paulburton@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Arnd Bergmann arnd@arndb.de Cc: Rob Herring robh+dt@kernel.org Cc: linux-pm@vger.kernel.org Cc: devicetree@vger.kernel.org Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/kernel/mips-cm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 7f3f136572de..50d3d74001cb 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -123,9 +123,9 @@ static char *cm2_causes[32] = { "COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07", "0x08", "0x09", "0x0a", "0x0b", "0x0c", "0x0d", "0x0e", "0x0f", - "0x10", "0x11", "0x12", "0x13", - "0x14", "0x15", "0x16", "INTVN_WR_ERR", - "INTVN_RD_ERR", "0x19", "0x1a", "0x1b", + "0x10", "INTVN_WR_ERR", "INTVN_RD_ERR", "0x13", + "0x14", "0x15", "0x16", "0x17", + "0x18", "0x19", "0x1a", "0x1b", "0x1c", "0x1d", "0x1e", "0x1f" };

From: Christoph Hellwig hch@lst.de

[ Upstream commit b9a5c3d4c34d8bd9fd75f7f28d18a57cb68da237 ]

Add a helper to check if we can use Identify CNS values > 1, and refine the Qemu quirk to not apply to reported versions larger than 1.1, as the Qemu implementation had been fixed by then.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Keith Busch kbusch@kernel.org Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a760c449f4a9..2d95755092e3 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -758,6 +758,19 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);

+/* + * In NVMe 1.0 the CNS field was just a binary controller or namespace + * flag, thus sending any new CNS opcodes has a big chance of not working. + * Qemu unfortunately had that bug after reporting a 1.1 version compliance + * (but not for any later version). + */ +static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl) +{ + if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS) + return ctrl->vs < NVME_VS(1, 2, 0); + return ctrl->vs < NVME_VS(1, 1, 0); +} + static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) { struct nvme_command c = { }; @@ -2538,8 +2551,7 @@ static void nvme_scan_work(struct work_struct *work) return;

nn = le32_to_cpu(id->nn); - if (ctrl->vs >= NVME_VS(1, 1, 0) && - !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { + if (!nvme_ctrl_limited_cns(ctrl)) { if (!nvme_scan_ns_list(ctrl, nn)) goto done; }

From: Bhupesh Sharma bhsharma@redhat.com

[ Upstream commit 73e030977f7884dbe1be0018bab517e8d02760f8 ]

Normally kdump kernel(s) run under severe memory constraint with the basic idea being to save the crashdump vmcore reliably when the primary kernel panics/hangs.

Currently the qed* ethernet driver ends up consuming a lot of memory in the kdump kernel, leading to kdump kernel panic when one tries to save the vmcore via ssh/nfs (thus utilizing the services of the underlying qed* network interfaces).

An example OOM message log seen in the kdump kernel can be seen here [1], with crashkernel size reservation of 512M.

Using tools like memstrack (see [2]), we can track the modules taking up the bulk of memory in the kdump kernel and organize the memory usage output as per 'highest allocator first'. An example log for the OOM case indicates that the qed* modules end up allocating approximately 216M memory, which is a large part of the total crashkernel size:

dracut-pre-pivot[676]: ======== Report format module_summary: ======== dracut-pre-pivot[676]: Module qed using 149.6MB (2394 pages), peak allocation 149.6MB (2394 pages) dracut-pre-pivot[676]: Module qede using 65.3MB (1045 pages), peak allocation 65.3MB (1045 pages)

This patch reduces the default RX and TX ring count from 1024 to 64 when running inside kdump kernel, which leads to a significant memory saving.

An example log with the patch applied shows the reduced memory allocation in the kdump kernel: dracut-pre-pivot[674]: ======== Report format module_summary: ======== dracut-pre-pivot[674]: Module qed using 141.8MB (2268 pages), peak allocation 141.8MB (2268 pages) <..snip..> [dracut-pre-pivot[674]: Module qede using 4.8MB (76 pages), peak allocation 4.9MB (78 pages)

Tested crashdump vmcore save via ssh/nfs protocol using underlying qed* network interface after applying this patch.

[1] OOM log: ------------

kworker/0:6: page allocation failure: order:6, mode:0x60c0c0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null) kworker/0:6 cpuset=/ mems_allowed=0 CPU: 0 PID: 145 Comm: kworker/0:6 Not tainted 4.18.0-109.el8.aarch64 #1 Hardware name: To be filled by O.E.M. Saber/Saber, BIOS 0ACKL025 01/18/2019 Workqueue: events work_for_cpu_fn Call trace: dump_backtrace+0x0/0x188 show_stack+0x24/0x30 dump_stack+0x90/0xb4 warn_alloc+0xf4/0x178 __alloc_pages_nodemask+0xcac/0xd58 alloc_pages_current+0x8c/0xf8 kmalloc_order_trace+0x38/0x108 qed_iov_alloc+0x40/0x248 [qed] qed_resc_alloc+0x224/0x518 [qed] qed_slowpath_start+0x254/0x928 [qed] __qede_probe+0xf8/0x5e0 [qede] qede_probe+0x68/0xd8 [qede] local_pci_probe+0x44/0xa8 work_for_cpu_fn+0x20/0x30 process_one_work+0x1ac/0x3e8 worker_thread+0x44/0x448 kthread+0x130/0x138 ret_from_fork+0x10/0x18 Cannot start slowpath qede: probe of 0000:05:00.1 failed with error -12

[2]. Memstrack tool: https://github.com/ryncsn/memstrack

Cc: kexec@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: Ariel Elior aelior@marvell.com Cc: GR-everest-linux-l2@marvell.com Cc: Manish Chopra manishc@marvell.com Cc: David S. Miller davem@davemloft.net Signed-off-by: Bhupesh Sharma bhsharma@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qede/qede.h | 2 ++ drivers/net/ethernet/qlogic/qede/qede_main.c | 11 +++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index a80531b5aecc..c132b08cefde 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -528,12 +528,14 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq); #define RX_RING_SIZE ((u16)BIT(RX_RING_SIZE_POW)) #define NUM_RX_BDS_MAX (RX_RING_SIZE - 1) #define NUM_RX_BDS_MIN 128 +#define NUM_RX_BDS_KDUMP_MIN 63 #define NUM_RX_BDS_DEF ((u16)BIT(10) - 1)

#define TX_RING_SIZE_POW 13 #define TX_RING_SIZE ((u16)BIT(TX_RING_SIZE_POW)) #define NUM_TX_BDS_MAX (TX_RING_SIZE - 1) #define NUM_TX_BDS_MIN 128 +#define NUM_TX_BDS_KDUMP_MIN 63 #define NUM_TX_BDS_DEF NUM_TX_BDS_MAX

#define QEDE_MIN_PKT_LEN 64 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index dab202f343c6..8bb734486bf3 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -29,6 +29,7 @@ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ +#include <linux/crash_dump.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/version.h> @@ -624,8 +625,14 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev, edev->dp_module = dp_module; edev->dp_level = dp_level; edev->ops = qed_ops; - edev->q_num_rx_buffers = NUM_RX_BDS_DEF; - edev->q_num_tx_buffers = NUM_TX_BDS_DEF; + + if (is_kdump_kernel()) { + edev->q_num_rx_buffers = NUM_RX_BDS_KDUMP_MIN; + edev->q_num_tx_buffers = NUM_TX_BDS_KDUMP_MIN; + } else { + edev->q_num_rx_buffers = NUM_RX_BDS_DEF; + edev->q_num_tx_buffers = NUM_TX_BDS_DEF; + }

DP_INFO(edev, "Allocated netdev with %d tx queues and %d rx queues\n", info->num_queues, info->num_queues);

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit beb12813bc75d4a23de43b85ad1c7cb28d27631e ]

Seven years ago we tried to fix a leak but actually introduced a double free instead. It was an understandable mistake because the code was a bit confusing and the free was done in the wrong place. The "skb" pointer is freed in both _rtl_usb_tx_urb_setup() and _rtl_usb_transmit(). The free belongs _rtl_usb_transmit() instead of _rtl_usb_tx_urb_setup() and I've cleaned the code up a bit to hopefully make it more clear.

Fixes: 36ef0b473fbf ("rtlwifi: usb: add missing freeing of skbuff") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/20200513093951.GD347693@mwanda Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/realtek/rtlwifi/usb.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index 93eda23f0123..7a050a75bdcb 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -910,10 +910,8 @@ static struct urb *_rtl_usb_tx_urb_setup(struct ieee80211_hw *hw,

WARN_ON(NULL == skb); _urb = usb_alloc_urb(0, GFP_ATOMIC); - if (!_urb) { - kfree_skb(skb); + if (!_urb) return NULL; - } _rtl_install_trx_info(rtlusb, skb, ep_num); usb_fill_bulk_urb(_urb, rtlusb->udev, usb_sndbulkpipe(rtlusb->udev, ep_num), skb->data, skb->len, _rtl_tx_complete, skb); @@ -927,7 +925,6 @@ static void _rtl_usb_transmit(struct ieee80211_hw *hw, struct sk_buff *skb, struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw)); u32 ep_num; struct urb *_urb = NULL; - struct sk_buff *_skb = NULL;

WARN_ON(NULL == rtlusb->usb_tx_aggregate_hdl); if (unlikely(IS_USB_STOP(rtlusb))) { @@ -936,8 +933,7 @@ static void _rtl_usb_transmit(struct ieee80211_hw *hw, struct sk_buff *skb, return; } ep_num = rtlusb->ep_map.ep_mapping[qnum]; - _skb = skb; - _urb = _rtl_usb_tx_urb_setup(hw, _skb, ep_num); + _urb = _rtl_usb_tx_urb_setup(hw, skb, ep_num); if (unlikely(!_urb)) { pr_err("Can't allocate urb. Drop skb!\n"); kfree_skb(skb);

From: Arvind Sankar nivedita@alum.mit.edu

[ Upstream commit 5214028dd89e49ba27007c3ee475279e584261f0 ]

For the 32-bit kernel, as described in

6d92bc9d483a ("x86/build: Build compressed x86 kernels as PIE"),

pre-2.26 binutils generates R_386_32 relocations in PIE mode. Since the startup code does not perform relocation, any reloc entry with R_386_32 will remain as 0 in the executing code.

Commit

974f221c84b0 ("x86/boot: Move compressed kernel to the end of the decompression buffer")

added a new symbol _end but did not mark it hidden, which doesn't give the correct offset on older linkers. This causes the compressed kernel to be copied beyond the end of the decompression buffer, rather than flush against it. This region of memory may be reserved or already allocated for other purposes by the bootloader.

Mark _end as hidden to fix. This changes the relocation from R_386_32 to R_386_RELATIVE even on the pre-2.26 binutils.

For 64-bit, this is not strictly necessary, as the 64-bit kernel is only built as PIE if the linker supports -z noreloc-overflow, which implies binutils-2.27+, but for consistency, mark _end as hidden here too.

The below illustrates the before/after impact of the patch using binutils-2.25 and gcc-4.6.4 (locally compiled from source) and QEMU.

Disassembly before patch: 48: 8b 86 60 02 00 00 mov 0x260(%esi),%eax 4e: 2d 00 00 00 00 sub $0x0,%eax 4f: R_386_32 _end Disassembly after patch: 48: 8b 86 60 02 00 00 mov 0x260(%esi),%eax 4e: 2d 00 f0 76 00 sub $0x76f000,%eax 4f: R_386_RELATIVE *ABS*

Dump from extract_kernel before patch: early console in extract_kernel input_data: 0x0207c098 <--- this is at output + init_size input_len: 0x0074fef1 output: 0x01000000 output_len: 0x00fa63d0 kernel_total_size: 0x0107c000 needed_size: 0x0107c000

Dump from extract_kernel after patch: early console in extract_kernel input_data: 0x0190d098 <--- this is at output + init_size - _end input_len: 0x0074fef1 output: 0x01000000 output_len: 0x00fa63d0 kernel_total_size: 0x0107c000 needed_size: 0x0107c000

Fixes: 974f221c84b0 ("x86/boot: Move compressed kernel to the end of the decompression buffer") Signed-off-by: Arvind Sankar nivedita@alum.mit.edu Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20200207214926.3564079-1-nivedita@alum.mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/boot/compressed/head_32.S | 5 +++-- arch/x86/boot/compressed/head_64.S | 1 + 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 01d628ea3402..c6c4b877f3d2 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -49,16 +49,17 @@ * Position Independent Executable (PIE) so that linker won't optimize * R_386_GOT32X relocation to its fixed symbol address. Older * linkers generate R_386_32 relocations against locally defined symbols, - * _bss, _ebss, _got and _egot, in PIE. It isn't wrong, just less + * _bss, _ebss, _got, _egot and _end, in PIE. It isn't wrong, just less * optimal than R_386_RELATIVE. But the x86 kernel fails to properly handle * R_386_32 relocations when relocating the kernel. To generate - * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as + * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as * hidden: */ .hidden _bss .hidden _ebss .hidden _got .hidden _egot + .hidden _end

__HEAD ENTRY(startup_32) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index a25127916e67..7ab1c6bcc66a 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -41,6 +41,7 @@ .hidden _ebss .hidden _got .hidden _egot + .hidden _end

__HEAD .code32

From: Serge Semin Sergey.Semin@baikalelectronics.ru

[ Upstream commit ed26aacfb5f71eecb20a51c4467da440cb719d66 ]

Loops-per-jiffies is a special number which represents a number of noop-loop cycles per CPU-scheduler quantum - jiffies. As you understand aside from CPU-specific implementation it depends on the CPU frequency. So when a platform has the CPU frequency fixed, we have no problem and the current udelay interface will work just fine. But as soon as CPU-freq driver is enabled and the cores frequency changes, we'll end up with distorted udelay's. In order to fix this we have to accordinly adjust the per-CPU udelay_val (the same as the global loops_per_jiffy) number. This can be done in the CPU-freq transition event handler. We subscribe to that event in the MIPS arch time-inititalization method.

Co-developed-by: Alexey Malahov Alexey.Malahov@baikalelectronics.ru Signed-off-by: Alexey Malahov Alexey.Malahov@baikalelectronics.ru Signed-off-by: Serge Semin Sergey.Semin@baikalelectronics.ru Reviewed-by: Jiaxun Yang jiaxun.yang@flygoat.com Cc: Thomas Bogendoerfer tsbogend@alpha.franken.de Cc: Paul Burton paulburton@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Arnd Bergmann arnd@arndb.de Cc: Rob Herring robh+dt@kernel.org Cc: devicetree@vger.kernel.org Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/kernel/time.c | 70 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+)

diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index a6ebc8135112..df18f386d457 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -22,12 +22,82 @@ #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/export.h> +#include <linux/cpufreq.h> +#include <linux/delay.h>

#include <asm/cpu-features.h> #include <asm/cpu-type.h> #include <asm/div64.h> #include <asm/time.h>

+#ifdef CONFIG_CPU_FREQ + +static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref); +static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref_freq); +static unsigned long glb_lpj_ref; +static unsigned long glb_lpj_ref_freq; + +static int cpufreq_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct cpufreq_freqs *freq = data; + struct cpumask *cpus = freq->policy->cpus; + unsigned long lpj; + int cpu; + + /* + * Skip lpj numbers adjustment if the CPU-freq transition is safe for + * the loops delay. (Is this possible?) + */ + if (freq->flags & CPUFREQ_CONST_LOOPS) + return NOTIFY_OK; + + /* Save the initial values of the lpjes for future scaling. */ + if (!glb_lpj_ref) { + glb_lpj_ref = boot_cpu_data.udelay_val; + glb_lpj_ref_freq = freq->old; + + for_each_online_cpu(cpu) { + per_cpu(pcp_lpj_ref, cpu) = + cpu_data[cpu].udelay_val; + per_cpu(pcp_lpj_ref_freq, cpu) = freq->old; + } + } + + /* + * Adjust global lpj variable and per-CPU udelay_val number in + * accordance with the new CPU frequency. + */ + if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || + (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) { + loops_per_jiffy = cpufreq_scale(glb_lpj_ref, + glb_lpj_ref_freq, + freq->new); + + for_each_cpu(cpu, cpus) { + lpj = cpufreq_scale(per_cpu(pcp_lpj_ref, cpu), + per_cpu(pcp_lpj_ref_freq, cpu), + freq->new); + cpu_data[cpu].udelay_val = (unsigned int)lpj; + } + } + + return NOTIFY_OK; +} + +static struct notifier_block cpufreq_notifier = { + .notifier_call = cpufreq_callback, +}; + +static int __init register_cpufreq_notifier(void) +{ + return cpufreq_register_notifier(&cpufreq_notifier, + CPUFREQ_TRANSITION_NOTIFIER); +} +core_initcall(register_cpufreq_notifier); + +#endif /* CONFIG_CPU_FREQ */ + /* * forward reference */

From: Finn Thain fthain@telegraphics.com.au

[ Upstream commit bcc44f6b74106b31f0b0408b70305a40360d63b7 ]

There is no VIA2 chip on the Mac IIfx, so don't call via_flush_cache(). This avoids a boot crash which appeared in v5.4.

printk: console [ttyS0] enabled printk: bootconsole [debug0] disabled printk: bootconsole [debug0] disabled Calibrating delay loop... 9.61 BogoMIPS (lpj=48064) pid_max: default: 32768 minimum: 301 Mount-cache hash table entries: 1024 (order: 0, 4096 bytes, linear) Mountpoint-cache hash table entries: 1024 (order: 0, 4096 bytes, linear) devtmpfs: initialized random: get_random_u32 called from bucket_table_alloc.isra.27+0x68/0x194 with crng_init=0 clocksource: jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 19112604462750000 ns futex hash table entries: 256 (order: -1, 3072 bytes, linear) NET: Registered protocol family 16 Data read fault at 0x00000000 in Super Data (pc=0x8a6a) BAD KERNEL BUSERR Oops: 00000000 Modules linked in: PC: [<00008a6a>] via_flush_cache+0x12/0x2c SR: 2700 SP: 01c1fe3c a2: 01c24000 d0: 00001119 d1: 0000000c d2: 00012000 d3: 0000000f d4: 01c06840 d5: 00033b92 a0: 00000000 a1: 00000000 Process swapper (pid: 1, task=01c24000) Frame format=B ssw=0755 isc=0200 isb=fff7 daddr=00000000 dobuf=01c1fed0 baddr=00008a6e dibuf=0000004e ver=f Stack from 01c1fec4: 01c1fed0 00007d7e 00010080 01c1fedc 0000792e 00000001 01c1fef4 00006b40 01c80000 00040000 00000006 00000003 01c1ff1c 004a545e 004ff200 00040000 00000000 00000003 01c06840 00033b92 004a5410 004b6c88 01c1ff84 000021e2 00000073 00000003 01c06840 00033b92 0038507a 004bb094 004b6ca8 004b6c88 004b6ca4 004b6c88 000021ae 00020002 00000000 01c0685d 00000000 01c1ffb4 0049f938 00409c85 01c06840 0045bd40 00000073 00000002 00000002 00000000 Call Trace: [<00007d7e>] mac_cache_card_flush+0x12/0x1c [<00010080>] fix_dnrm+0x2/0x18 [<0000792e>] cache_push+0x46/0x5a [<00006b40>] arch_dma_prep_coherent+0x60/0x6e [<00040000>] switched_to_dl+0x76/0xd0 [<004a545e>] dma_atomic_pool_init+0x4e/0x188 [<00040000>] switched_to_dl+0x76/0xd0 [<00033b92>] parse_args+0x0/0x370 [<004a5410>] dma_atomic_pool_init+0x0/0x188 [<000021e2>] do_one_initcall+0x34/0x1be [<00033b92>] parse_args+0x0/0x370 [<0038507a>] strcpy+0x0/0x1e [<000021ae>] do_one_initcall+0x0/0x1be [<00020002>] do_proc_dointvec_conv+0x54/0x74 [<0049f938>] kernel_init_freeable+0x126/0x190 [<0049f94c>] kernel_init_freeable+0x13a/0x190 [<004a5410>] dma_atomic_pool_init+0x0/0x188 [<00041798>] complete+0x0/0x3c [<000b9b0c>] kfree+0x0/0x20a [<0038df98>] schedule+0x0/0xd0 [<0038d604>] kernel_init+0x0/0xda [<0038d610>] kernel_init+0xc/0xda [<0038d604>] kernel_init+0x0/0xda [<00002d38>] ret_from_kernel_thread+0xc/0x14 Code: 0000 2079 0048 10da 2279 0048 10c8 d3c8 <1011> 0200 fff7 1280 d1f9 0048 10c8 1010 0000 0008 1080 4e5e 4e75 4e56 0000 2039 Disabling lock debugging due to kernel taint Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b

Thanks to Stan Johnson for capturing the console log and running git bisect.

Git bisect said commit 8e3a68fb55e0 ("dma-mapping: make dma_atomic_pool_init self-contained") is the first "bad" commit. I don't know why. Perhaps mach_l2_flush first became reachable with that commit.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: Stan Johnson userm57@yahoo.com Signed-off-by: Finn Thain fthain@telegraphics.com.au Cc: Joshua Thompson funaho@jurai.org Link: https://lore.kernel.org/r/b8bbeef197d6b3898e82ed0d231ad08f575a4b34.158994912... Signed-off-by: Geert Uytterhoeven geert@linux-m68k.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/m68k/include/asm/mac_via.h | 1 + arch/m68k/mac/config.c | 21 ++------------------- arch/m68k/mac/via.c | 6 +++++- 3 files changed, 8 insertions(+), 20 deletions(-)

diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h index de1470c4d829..1149251ea58d 100644 --- a/arch/m68k/include/asm/mac_via.h +++ b/arch/m68k/include/asm/mac_via.h @@ -257,6 +257,7 @@ extern int rbv_present,via_alt_mapping;

struct irq_desc;

+extern void via_l2_flush(int writeback); extern void via_register_interrupts(void); extern void via_irq_enable(int); extern void via_irq_disable(int); diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index 2004b3f72d80..3ea7450c51f2 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -61,7 +61,6 @@ extern void iop_preinit(void); extern void iop_init(void); extern void via_init(void); extern void via_init_clock(irq_handler_t func); -extern void via_flush_cache(void); extern void oss_init(void); extern void psc_init(void); extern void baboon_init(void); @@ -132,21 +131,6 @@ int __init mac_parse_bootinfo(const struct bi_record *record) return unknown; }

-/* - * Flip into 24bit mode for an instant - flushes the L2 cache card. We - * have to disable interrupts for this. Our IRQ handlers will crap - * themselves if they take an IRQ in 24bit mode! - */ - -static void mac_cache_card_flush(int writeback) -{ - unsigned long flags; - - local_irq_save(flags); - via_flush_cache(); - local_irq_restore(flags); -} - void __init config_mac(void) { if (!MACH_IS_MAC) @@ -179,9 +163,8 @@ void __init config_mac(void) * not. */

- if (macintosh_config->ident == MAC_MODEL_IICI - || macintosh_config->ident == MAC_MODEL_IIFX) - mach_l2_flush = mac_cache_card_flush; + if (macintosh_config->ident == MAC_MODEL_IICI) + mach_l2_flush = via_l2_flush; }

diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c index 863806e6775a..6ab6a1d54b37 100644 --- a/arch/m68k/mac/via.c +++ b/arch/m68k/mac/via.c @@ -300,10 +300,14 @@ void via_debug_dump(void) * the system into 24-bit mode for an instant. */

-void via_flush_cache(void) +void via_l2_flush(int writeback) { + unsigned long flags; + + local_irq_save(flags); via2[gBufB] &= ~VIA2B_vMode32; via2[gBufB] |= VIA2B_vMode32; + local_irq_restore(flags); }

/*

From: Jiaxun Yang jiaxun.yang@flygoat.com

[ Upstream commit b6caa1d8c80cb71b6162cb1f1ec13aa655026c9f ]

Don't disable MEM/IO decoding when a device have both non_compliant_bars and mmio_always_on.

That would allow us quirk devices with junk in BARs but can't disable their decoding.

Signed-off-by: Jiaxun Yang jiaxun.yang@flygoat.com Acked-by: Bjorn Helgaas helgaas@kernel.org Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index e23bfd9845b1..92c3abe0b2b9 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1446,7 +1446,7 @@ int pci_setup_device(struct pci_dev *dev) /* device class may be changed after fixup */ class = dev->class >> 8;

- if (dev->non_compliant_bars) { + if (dev->non_compliant_bars && !dev->mmio_always_on) { pci_read_config_word(dev, PCI_COMMAND, &cmd); if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { dev_info(&dev->dev, "device has non-compliant BARs; disabling IO/MEM decoding\n");

From: Dave Chinner david@fromorbit.com

[ Upstream commit dc3ffbb14060c943469d5e12900db3a60bc3fa64 ]

xfs: gut error handling in xfs_trans_unreserve_and_mod_sb()

From: Dave Chinner dchinner@redhat.com

The error handling in xfs_trans_unreserve_and_mod_sb() is largely incorrect - rolling back the changes in the transaction if only one counter underruns makes all the other counters incorrect. We still allow the change to proceed and committing the transaction, except now we have multiple incorrect counters instead of a single underflow.

Further, we don't actually report the error to the caller, so this is completely silent except on debug kernels that will assert on failure before we even get to the rollback code. Hence this error handling is broken, untested, and largely unnecessary complexity.

Just remove it.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/xfs/xfs_trans.c | 163 ++++++--------------------------------------- 1 file changed, 20 insertions(+), 143 deletions(-)

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index a87f657f59c9..cad4b04e31a7 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -493,57 +493,9 @@ xfs_trans_apply_sb_deltas( sizeof(sbp->sb_frextents) - 1); }

-STATIC int -xfs_sb_mod8( - uint8_t *field, - int8_t delta) -{ - int8_t counter = *field; - - counter += delta; - if (counter < 0) { - ASSERT(0); - return -EINVAL; - } - *field = counter; - return 0; -} - -STATIC int -xfs_sb_mod32( - uint32_t *field, - int32_t delta) -{ - int32_t counter = *field; - - counter += delta; - if (counter < 0) { - ASSERT(0); - return -EINVAL; - } - *field = counter; - return 0; -} - -STATIC int -xfs_sb_mod64( - uint64_t *field, - int64_t delta) -{ - int64_t counter = *field; - - counter += delta; - if (counter < 0) { - ASSERT(0); - return -EINVAL; - } - *field = counter; - return 0; -} - /* - * xfs_trans_unreserve_and_mod_sb() is called to release unused reservations - * and apply superblock counter changes to the in-core superblock. The + * xfs_trans_unreserve_and_mod_sb() is called to release unused reservations and + * apply superblock counter changes to the in-core superblock. The * t_res_fdblocks_delta and t_res_frextents_delta fields are explicitly NOT * applied to the in-core superblock. The idea is that that has already been * done. @@ -588,20 +540,17 @@ xfs_trans_unreserve_and_mod_sb( /* apply the per-cpu counters */ if (blkdelta) { error = xfs_mod_fdblocks(mp, blkdelta, rsvd); - if (error) - goto out; + ASSERT(!error); }

if (idelta) { error = xfs_mod_icount(mp, idelta); - if (error) - goto out_undo_fdblocks; + ASSERT(!error); }

if (ifreedelta) { error = xfs_mod_ifree(mp, ifreedelta); - if (error) - goto out_undo_icount; + ASSERT(!error); }

if (rtxdelta == 0 && !(tp->t_flags & XFS_TRANS_SB_DIRTY)) @@ -609,95 +558,23 @@ xfs_trans_unreserve_and_mod_sb(

/* apply remaining deltas */ spin_lock(&mp->m_sb_lock); - if (rtxdelta) { - error = xfs_sb_mod64(&mp->m_sb.sb_frextents, rtxdelta); - if (error) - goto out_undo_ifree; - } - - if (tp->t_dblocks_delta != 0) { - error = xfs_sb_mod64(&mp->m_sb.sb_dblocks, tp->t_dblocks_delta); - if (error) - goto out_undo_frextents; - } - if (tp->t_agcount_delta != 0) { - error = xfs_sb_mod32(&mp->m_sb.sb_agcount, tp->t_agcount_delta); - if (error) - goto out_undo_dblocks; - } - if (tp->t_imaxpct_delta != 0) { - error = xfs_sb_mod8(&mp->m_sb.sb_imax_pct, tp->t_imaxpct_delta); - if (error) - goto out_undo_agcount; - } - if (tp->t_rextsize_delta != 0) { - error = xfs_sb_mod32(&mp->m_sb.sb_rextsize, - tp->t_rextsize_delta); - if (error) - goto out_undo_imaxpct; - } - if (tp->t_rbmblocks_delta != 0) { - error = xfs_sb_mod32(&mp->m_sb.sb_rbmblocks, - tp->t_rbmblocks_delta); - if (error) - goto out_undo_rextsize; - } - if (tp->t_rblocks_delta != 0) { - error = xfs_sb_mod64(&mp->m_sb.sb_rblocks, tp->t_rblocks_delta); - if (error) - goto out_undo_rbmblocks; - } - if (tp->t_rextents_delta != 0) { - error = xfs_sb_mod64(&mp->m_sb.sb_rextents, - tp->t_rextents_delta); - if (error) - goto out_undo_rblocks; - } - if (tp->t_rextslog_delta != 0) { - error = xfs_sb_mod8(&mp->m_sb.sb_rextslog, - tp->t_rextslog_delta); - if (error) - goto out_undo_rextents; - } + mp->m_sb.sb_frextents += rtxdelta; + mp->m_sb.sb_dblocks += tp->t_dblocks_delta; + mp->m_sb.sb_agcount += tp->t_agcount_delta; + mp->m_sb.sb_imax_pct += tp->t_imaxpct_delta; + mp->m_sb.sb_rextsize += tp->t_rextsize_delta; + mp->m_sb.sb_rbmblocks += tp->t_rbmblocks_delta; + mp->m_sb.sb_rblocks += tp->t_rblocks_delta; + mp->m_sb.sb_rextents += tp->t_rextents_delta; + mp->m_sb.sb_rextslog += tp->t_rextslog_delta; spin_unlock(&mp->m_sb_lock); - return;

-out_undo_rextents: - if (tp->t_rextents_delta) - xfs_sb_mod64(&mp->m_sb.sb_rextents, -tp->t_rextents_delta); -out_undo_rblocks: - if (tp->t_rblocks_delta) - xfs_sb_mod64(&mp->m_sb.sb_rblocks, -tp->t_rblocks_delta); -out_undo_rbmblocks: - if (tp->t_rbmblocks_delta) - xfs_sb_mod32(&mp->m_sb.sb_rbmblocks, -tp->t_rbmblocks_delta); -out_undo_rextsize: - if (tp->t_rextsize_delta) - xfs_sb_mod32(&mp->m_sb.sb_rextsize, -tp->t_rextsize_delta); -out_undo_imaxpct: - if (tp->t_rextsize_delta) - xfs_sb_mod8(&mp->m_sb.sb_imax_pct, -tp->t_imaxpct_delta); -out_undo_agcount: - if (tp->t_agcount_delta) - xfs_sb_mod32(&mp->m_sb.sb_agcount, -tp->t_agcount_delta); -out_undo_dblocks: - if (tp->t_dblocks_delta) - xfs_sb_mod64(&mp->m_sb.sb_dblocks, -tp->t_dblocks_delta); -out_undo_frextents: - if (rtxdelta) - xfs_sb_mod64(&mp->m_sb.sb_frextents, -rtxdelta); -out_undo_ifree: - spin_unlock(&mp->m_sb_lock); - if (ifreedelta) - xfs_mod_ifree(mp, -ifreedelta); -out_undo_icount: - if (idelta) - xfs_mod_icount(mp, -idelta); -out_undo_fdblocks: - if (blkdelta) - xfs_mod_fdblocks(mp, -blkdelta, rsvd); -out: - ASSERT(error == 0); + /* + * Debug checks outside of the spinlock so they don't lock up the + * machine if they fail. + */ + ASSERT(mp->m_sb.sb_imax_pct >= 0); + ASSERT(mp->m_sb.sb_rextslog >= 0); return; }

From: Ulf Hansson ulf.hansson@linaro.org

[ Upstream commit a389087ee9f195fcf2f31cd771e9ec5f02c16650 ]

Using a fixed 1s timeout for all commands is a bit problematic.

For some commands it means waiting longer than needed for the timeout to expire, which may not a big issue, but still. For other commands, like for an erase (CMD38) that uses a R1B response, may require longer timeouts than 1s. In these cases, we may end up treating the command as it failed, while it just needed some more time to complete successfully.

Fix the problem by respecting the cmd->busy_timeout, which is provided by the mmc core.

Cc: Rui Miguel Silva rmfrfs@gmail.com Cc: Johan Hovold johan@kernel.org Cc: Alex Elder elder@kernel.org Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: greybus-dev@lists.linaro.org Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Acked-by: Rui Miguel Silva rmfrfs@gmail.com Acked-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Link: https://lore.kernel.org/r/20200414161413.3036-20-ulf.hansson@linaro.org Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/greybus/sdio.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/greybus/sdio.c b/drivers/staging/greybus/sdio.c index 101ca5097fc9..93e2c091c565 100644 --- a/drivers/staging/greybus/sdio.c +++ b/drivers/staging/greybus/sdio.c @@ -412,6 +412,7 @@ static int gb_sdio_command(struct gb_sdio_host *host, struct mmc_command *cmd) struct gb_sdio_command_request request = {0}; struct gb_sdio_command_response response; struct mmc_data *data = host->mrq->data; + unsigned int timeout_ms; u8 cmd_flags; u8 cmd_type; int i; @@ -470,9 +471,12 @@ static int gb_sdio_command(struct gb_sdio_host *host, struct mmc_command *cmd) request.data_blksz = cpu_to_le16(data->blksz); }

- ret = gb_operation_sync(host->connection, GB_SDIO_TYPE_COMMAND, - &request, sizeof(request), &response, - sizeof(response)); + timeout_ms = cmd->busy_timeout ? cmd->busy_timeout : + GB_OPERATION_TIMEOUT_DEFAULT; + + ret = gb_operation_sync_timeout(host->connection, GB_SDIO_TYPE_COMMAND, + &request, sizeof(request), &response, + sizeof(response), timeout_ms); if (ret < 0) goto out;

From: Xie XiuQi xiexiuqi@huawei.com

[ Upstream commit 3b70683fc4d68f5d915d9dc7e5ba72c732c7315c ]

ubsan report this warning, fix it by adding a unsigned suffix.

UBSAN: signed-integer-overflow in drivers/net/ethernet/intel/ixgbe/ixgbe_common.c:2246:26 65535 * 65537 cannot be represented in type 'int' CPU: 21 PID: 7 Comm: kworker/u256:0 Not tainted 5.7.0-rc3-debug+ #39 Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 03/27/2020 Workqueue: ixgbe ixgbe_service_task [ixgbe] Call trace: dump_backtrace+0x0/0x3f0 show_stack+0x28/0x38 dump_stack+0x154/0x1e4 ubsan_epilogue+0x18/0x60 handle_overflow+0xf8/0x148 __ubsan_handle_mul_overflow+0x34/0x48 ixgbe_fc_enable_generic+0x4d0/0x590 [ixgbe] ixgbe_service_task+0xc20/0x1f78 [ixgbe] process_one_work+0x8f0/0xf18 worker_thread+0x430/0x6d0 kthread+0x218/0x238 ret_from_fork+0x10/0x18

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Xie XiuQi xiexiuqi@huawei.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 815284fe9324..6b5662674c75 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -2267,7 +2267,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) }

/* Configure pause time (2 TCs per register) */ - reg = hw->fc.pause_time * 0x00010001; + reg = hw->fc.pause_time * 0x00010001U; for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg);

From: Serge Semin Sergey.Semin@baikalelectronics.ru

[ Upstream commit f0410bbf7d0fb80149e3b17d11d31f5b5197873e ]

DW APB SSI DMA-part of the driver may need to perform the requested SPI-transfer synchronously. In that case the dma_transfer() callback will return 0 as a marker of the SPI transfer being finished so the SPI core doesn't need to wait and may proceed with the SPI message trasnfers pumping procedure. This will be needed to fix the problem when DMA transactions are finished, but there is still data left in the SPI Tx/Rx FIFOs being sent/received. But for now make dma_transfer to return 1 as the normal dw_spi_transfer_one() method.

Signed-off-by: Serge Semin Sergey.Semin@baikalelectronics.ru Cc: Georgy Vlasov Georgy.Vlasov@baikalelectronics.ru Cc: Ramil Zaripov Ramil.Zaripov@baikalelectronics.ru Cc: Alexey Malahov Alexey.Malahov@baikalelectronics.ru Cc: Thomas Bogendoerfer tsbogend@alpha.franken.de Cc: Arnd Bergmann arnd@arndb.de Cc: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Feng Tang feng.tang@intel.com Cc: Rob Herring robh+dt@kernel.org Cc: linux-mips@vger.kernel.org Cc: devicetree@vger.kernel.org Link: https://lore.kernel.org/r/20200529131205.31838-3-Sergey.Semin@baikalelectron... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-dw-mid.c | 2 +- drivers/spi/spi-dw.c | 7 ++----- 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index c4244d2f1ee3..cb268cc4ba2b 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -274,7 +274,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, struct spi_transfer *xfer) dma_async_issue_pending(dws->txchan); }

- return 0; + return 1; }

static void mid_spi_dma_stop(struct dw_spi *dws) diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index 26ed3b4233a2..9d0f655a65c6 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -381,11 +381,8 @@ static int dw_spi_transfer_one(struct spi_master *master,

spi_enable_chip(dws, 1);

- if (dws->dma_mapped) { - ret = dws->dma_ops->dma_transfer(dws, transfer); - if (ret < 0) - return ret; - } + if (dws->dma_mapped) + return dws->dma_ops->dma_transfer(dws, transfer);

if (chip->poll_mode) return poll_transfer(dws);

From: Andy Shevchenko andriy.shevchenko@linux.intel.com

[ Upstream commit 5cdc45ed3948042f0d73c6fec5ee9b59e637d0d2 ]

First of all, unsigned long can overflow u32 value on 64-bit machine. Second, simple_strtoul() doesn't check for overflow in the input.

Convert simple_strtoul() to kstrtou32() to eliminate above issues.

Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/hp-wmi.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 06a3c1ef8eee..952544ca0d84 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -474,8 +474,14 @@ static ssize_t postcode_show(struct device *dev, struct device_attribute *attr, static ssize_t als_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - u32 tmp = simple_strtoul(buf, NULL, 10); - int ret = hp_wmi_perform_query(HPWMI_ALS_QUERY, HPWMI_WRITE, &tmp, + u32 tmp; + int ret; + + ret = kstrtou32(buf, 10, &tmp); + if (ret) + return ret; + + ret = hp_wmi_perform_query(HPWMI_ALS_QUERY, HPWMI_WRITE, &tmp, sizeof(tmp), sizeof(tmp)); if (ret) return ret < 0 ? ret : -EINVAL;

From: Daniel Axtens dja@axtens.net

[ Upstream commit 47227d27e2fcb01a9e8f5958d8997cf47a820afc ]

The memcmp KASAN self-test fails on a kernel with both KASAN and FORTIFY_SOURCE.

When FORTIFY_SOURCE is on, a number of functions are replaced with fortified versions, which attempt to check the sizes of the operands. However, these functions often directly invoke __builtin_foo() once they have performed the fortify check. Using __builtins may bypass KASAN checks if the compiler decides to inline it's own implementation as sequence of instructions, rather than emit a function call that goes out to a KASAN-instrumented implementation.

Why is only memcmp affected? ============================

Of the string and string-like functions that kasan_test tests, only memcmp is replaced by an inline sequence of instructions in my testing on x86 with gcc version 9.2.1 20191008 (Ubuntu 9.2.1-9ubuntu2).

I believe this is due to compiler heuristics. For example, if I annotate kmalloc calls with the alloc_size annotation (and disable some fortify compile-time checking!), the compiler will replace every memset except the one in kmalloc_uaf_memset with inline instructions. (I have some WIP patches to add this annotation.)

Does this affect other functions in string.h? =============================================

Yes. Anything that uses __builtin_* rather than __real_* could be affected. This looks like:

- strncpy - strcat - strlen - strlcpy maybe, under some circumstances? - strncat under some circumstances - memset - memcpy - memmove - memcmp (as noted) - memchr - strcpy

Whether a function call is emitted always depends on the compiler. Most bugs should get caught by FORTIFY_SOURCE, but the missed memcmp test shows that this is not always the case.

Isn't FORTIFY_SOURCE disabled with KASAN? ========================================-

The string headers on all arches supporting KASAN disable fortify with kasan, but only when address sanitisation is _also_ disabled. For example from x86:

#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) /* * For files that are not instrumented (e.g. mm/slub.c) we * should use not instrumented version of mem* functions. */ #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n)

#ifndef __NO_FORTIFY #define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ #endif

#endif

This comes from commit 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions"), and doesn't work when KASAN is enabled and the file is supposed to be sanitised - as with test_kasan.c

I'm pretty sure this is not wrong, but not as expansive it should be:

* we shouldn't use __builtin_memcpy etc in files where we don't have instrumentation - it could devolve into a function call to memcpy, which will be instrumented. Rather, we should use __memcpy which by convention is not instrumented.

* we also shouldn't be using __builtin_memcpy when we have a KASAN instrumented file, because it could be replaced with inline asm that will not be instrumented.

What is correct behaviour? ==========================

Firstly, there is some overlap between fortification and KASAN: both provide some level of _runtime_ checking. Only fortify provides compile-time checking.

KASAN and fortify can pick up different things at runtime:

- Some fortify functions, notably the string functions, could easily be modified to consider sub-object sizes (e.g. members within a struct), and I have some WIP patches to do this. KASAN cannot detect these because it cannot insert poision between members of a struct.

- KASAN can detect many over-reads/over-writes when the sizes of both operands are unknown, which fortify cannot.

So there are a couple of options:

1) Flip the test: disable fortify in santised files and enable it in unsanitised files. This at least stops us missing KASAN checking, but we lose the fortify checking.

2) Make the fortify code always call out to real versions. Do this only for KASAN, for fear of losing the inlining opportunities we get from __builtin_*.

(We can't use kasan_check_{read,write}: because the fortify functions are _extern inline_, you can't include _static_ inline functions without a compiler warning. kasan_check_{read,write} are static inline so we can't use them even when they would otherwise be suitable.)

Take approach 2 and call out to real versions when KASAN is enabled.

Use __underlying_foo to distinguish from __real_foo: __real_foo always refers to the kernel's implementation of foo, __underlying_foo could be either the kernel implementation or the __builtin_foo implementation.

This is sometimes enough to make the memcmp test succeed with FORTIFY_SOURCE enabled. It is at least enough to get the function call into the module. One more fix is needed to make it reliable: see the next patch.

Fixes: 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions") Signed-off-by: Daniel Axtens dja@axtens.net Signed-off-by: Andrew Morton akpm@linux-foundation.org Tested-by: David Gow davidgow@google.com Reviewed-by: Dmitry Vyukov dvyukov@google.com Cc: Daniel Micay danielmicay@gmail.com Cc: Andrey Ryabinin aryabinin@virtuozzo.com Cc: Alexander Potapenko glider@google.com Link: http://lkml.kernel.org/r/20200423154503.5103-3-dja@axtens.net Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/string.h | 60 +++++++++++++++++++++++++++++++++--------- 1 file changed, 48 insertions(+), 12 deletions(-)

diff --git a/include/linux/string.h b/include/linux/string.h index 3d43329c20be..315fef3aff4e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -238,6 +238,31 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter");

#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) + +#ifdef CONFIG_KASAN +extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); +extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); +extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); +extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); +extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); +extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); +#else +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp +#define __underlying_memcpy __builtin_memcpy +#define __underlying_memmove __builtin_memmove +#define __underlying_memset __builtin_memset +#define __underlying_strcat __builtin_strcat +#define __underlying_strcpy __builtin_strcpy +#define __underlying_strlen __builtin_strlen +#define __underlying_strncat __builtin_strncat +#define __underlying_strncpy __builtin_strncpy +#endif + __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -245,14 +270,14 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_strncpy(p, q, size); + return __underlying_strncpy(p, q, size); }

__FORTIFY_INLINE char *strcat(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); if (p_size == (size_t)-1) - return __builtin_strcat(p, q); + return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); return p; @@ -266,7 +291,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) /* Work around gcc excess stack consumption issue */ if (p_size == (size_t)-1 || (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) - return __builtin_strlen(p); + return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(__func__); @@ -299,7 +324,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) __write_overflow(); if (len >= p_size) fortify_panic(__func__); - __builtin_memcpy(p, q, len); + __underlying_memcpy(p, q, len); p[len] = '\0'; } return ret; @@ -312,12 +337,12 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strncat(p, q, count); + return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); if (p_size < p_len + copy_len + 1) fortify_panic(__func__); - __builtin_memcpy(p + p_len, q, copy_len); + __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } @@ -329,7 +354,7 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memset(p, c, size); + return __underlying_memset(p, c, size); }

__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) @@ -344,7 +369,7 @@ __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcpy(p, q, size); + return __underlying_memcpy(p, q, size); }

__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) @@ -359,7 +384,7 @@ __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memmove(p, q, size); + return __underlying_memmove(p, q, size); }

extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); @@ -385,7 +410,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcmp(p, q, size); + return __underlying_memcmp(p, q, size); }

__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) @@ -395,7 +420,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) __read_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memchr(p, c, size); + return __underlying_memchr(p, c, size); }

void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); @@ -426,11 +451,22 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strcpy(p, q); + return __underlying_strcpy(p, q); memcpy(p, q, strlen(q) + 1); return p; }

+/* Don't use these outside the FORITFY_SOURCE implementation */ +#undef __underlying_memchr +#undef __underlying_memcmp +#undef __underlying_memcpy +#undef __underlying_memmove +#undef __underlying_memset +#undef __underlying_strcat +#undef __underlying_strcpy +#undef __underlying_strlen +#undef __underlying_strncat +#undef __underlying_strncpy #endif

/**