From: Erik Ekman erik@kryo.se

[ Upstream commit 2191b1dfef7d45f44b5008d2148676d9f2c82874 ]

When link modes were initially added in commit 2c762679435dc ("net/mlx4_en: Use PTYS register to query ethtool settings") and later updated for the new ethtool API in commit 3d8f7cc78d0eb ("net: mlx4: use new ETHTOOL_G/SSETTINGS API") the only 1/10G non-baseT link modes configured were 1000baseKX, 10000baseKX4 and 10000baseKR. It looks like these got picked to represent other modes since nothing better was available.

Switch to using more specific link modes added in commit 5711a98221443 ("net: ethtool: add support for 1000BaseX and missing 10G link modes").

Tested with MCX311A-XCAT connected via DAC. Before:

% sudo ethtool enp3s0 Settings for enp3s0: Supported ports: [ FIBRE ] Supported link modes: 1000baseKX/Full 10000baseKR/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: No Supported FEC modes: Not reported Advertised link modes: 1000baseKX/Full 10000baseKR/Full Advertised pause frame use: Symmetric Advertised auto-negotiation: No Advertised FEC modes: Not reported Speed: 10000Mb/s Duplex: Full Auto-negotiation: off Port: Direct Attach Copper PHYAD: 0 Transceiver: internal Supports Wake-on: d Wake-on: d Current message level: 0x00000014 (20) link ifdown Link detected: yes

With this change:

% sudo ethtool enp3s0 Settings for enp3s0: Supported ports: [ FIBRE ] Supported link modes: 1000baseX/Full 10000baseCR/Full 10000baseSR/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: No Supported FEC modes: Not reported Advertised link modes: 1000baseX/Full 10000baseCR/Full 10000baseSR/Full Advertised pause frame use: Symmetric Advertised auto-negotiation: No Advertised FEC modes: Not reported Speed: 10000Mb/s Duplex: Full Auto-negotiation: off Port: Direct Attach Copper PHYAD: 0 Transceiver: internal Supports Wake-on: d Wake-on: d Current message level: 0x00000014 (20) link ifdown Link detected: yes

Tested-by: Michael Stapelberg michael@stapelberg.ch Signed-off-by: Erik Ekman erik@kryo.se Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 410a36c982419..1569300844f0c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -620,7 +620,7 @@ void __init mlx4_en_init_ptys2ethtool_map(void) MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_T, SPEED_1000, ETHTOOL_LINK_MODE_1000baseT_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_CX_SGMII, SPEED_1000, - ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); + ETHTOOL_LINK_MODE_1000baseX_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_KX, SPEED_1000, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_T, SPEED_10000, @@ -632,9 +632,9 @@ void __init mlx4_en_init_ptys2ethtool_map(void) MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KR, SPEED_10000, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CR, SPEED_10000, - ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + ETHTOOL_LINK_MODE_10000baseCR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_SR, SPEED_10000, - ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_20GBASE_KR2, SPEED_20000, ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT);

From: Ondrej Jirman megous@megous.com

[ Upstream commit 02fe0fbd8a21e183687925c3a266ae27dda9840f ]

In a typical read transfer, start completion flag is being set after read finishes (notice ipd bit 4 being set):

trasnfer poll=0 i2c start rk3x-i2c fdd40000.i2c: IRQ: state 1, ipd: 10 i2c read rk3x-i2c fdd40000.i2c: IRQ: state 2, ipd: 1b i2c stop rk3x-i2c fdd40000.i2c: IRQ: state 4, ipd: 33

This causes I2C transfer being aborted in polled mode from a stop completion handler:

trasnfer poll=1 i2c start rk3x-i2c fdd40000.i2c: IRQ: state 1, ipd: 10 i2c read rk3x-i2c fdd40000.i2c: IRQ: state 2, ipd: 0 rk3x-i2c fdd40000.i2c: IRQ: state 2, ipd: 1b i2c stop rk3x-i2c fdd40000.i2c: IRQ: state 4, ipd: 13 i2c stop rk3x-i2c fdd40000.i2c: unexpected irq in STOP: 0x10

Clearing the START flag after read fixes the issue without any obvious side effects.

This issue was dicovered on RK3566 when adding support for powering off the RK817 PMIC.

Signed-off-by: Ondrej Jirman megous@megous.com Reviewed-by: John Keeping john@metanate.com Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-rk3x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index df220666d6274..b4f8cd7dc8b74 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -424,8 +424,8 @@ static void rk3x_i2c_handle_read(struct rk3x_i2c *i2c, unsigned int ipd) if (!(ipd & REG_INT_MBRF)) return;

- /* ack interrupt */ - i2c_writel(i2c, REG_INT_MBRF, REG_IPD); + /* ack interrupt (read also produces a spurious START flag, clear it too) */ + i2c_writel(i2c, REG_INT_MBRF | REG_INT_START, REG_IPD);

/* Can only handle a maximum of 32 bytes at a time */ if (len > 32)

From: Chen Jun chenjun102@huawei.com

[ Upstream commit f25667e5980a4333729cac3101e5de1bb851f71a ]

Doing the command: echo 'hist:key=common_pid.execname,common_timestamp' > /sys/kernel/debug/tracing/events/xxx/trigger

Triggers many kmemleak reports:

unreferenced object 0xffff0000c7ea4980 (size 128): comm "bash", pid 338, jiffies 4294912626 (age 9339.324s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000f3469921>] kmem_cache_alloc_trace+0x4c0/0x6f0 [<0000000054ca40c3>] hist_trigger_elt_data_alloc+0x140/0x178 [<00000000633bd154>] tracing_map_init+0x1f8/0x268 [<000000007e814ab9>] event_hist_trigger_func+0xca0/0x1ad0 [<00000000bf8520ed>] trigger_process_regex+0xd4/0x128 [<00000000f549355a>] event_trigger_write+0x7c/0x120 [<00000000b80f898d>] vfs_write+0xc4/0x380 [<00000000823e1055>] ksys_write+0x74/0xf8 [<000000008a9374aa>] __arm64_sys_write+0x24/0x30 [<0000000087124017>] do_el0_svc+0x88/0x1c0 [<00000000efd0dcd1>] el0_svc+0x1c/0x28 [<00000000dbfba9b3>] el0_sync_handler+0x88/0xc0 [<00000000e7399680>] el0_sync+0x148/0x180 unreferenced object 0xffff0000c7ea4980 (size 128): comm "bash", pid 338, jiffies 4294912626 (age 9339.324s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000f3469921>] kmem_cache_alloc_trace+0x4c0/0x6f0 [<0000000054ca40c3>] hist_trigger_elt_data_alloc+0x140/0x178 [<00000000633bd154>] tracing_map_init+0x1f8/0x268 [<000000007e814ab9>] event_hist_trigger_func+0xca0/0x1ad0 [<00000000bf8520ed>] trigger_process_regex+0xd4/0x128 [<00000000f549355a>] event_trigger_write+0x7c/0x120 [<00000000b80f898d>] vfs_write+0xc4/0x380 [<00000000823e1055>] ksys_write+0x74/0xf8 [<000000008a9374aa>] __arm64_sys_write+0x24/0x30 [<0000000087124017>] do_el0_svc+0x88/0x1c0 [<00000000efd0dcd1>] el0_svc+0x1c/0x28 [<00000000dbfba9b3>] el0_sync_handler+0x88/0xc0 [<00000000e7399680>] el0_sync+0x148/0x180

The reason is elts->pages[i] is alloced by get_zeroed_page. and kmemleak will not scan the area alloced by get_zeroed_page. The address stored in elts->pages will be regarded as leaked.

That is, the elts->pages[i] will have pointers loaded onto it as well, and without telling kmemleak about it, those pointers will look like memory without a reference.

To fix this, call kmemleak_alloc to tell kmemleak to scan elts->pages[i]

Link: https://lkml.kernel.org/r/20211124140801.87121-1-chenjun102@huawei.com

Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/tracing_map.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 379db35838b64..572c0854d631c 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -24,6 +24,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> +#include <linux/kmemleak.h>

#include "tracing_map.h" #include "trace.h" @@ -227,6 +228,7 @@ void tracing_map_array_free(struct tracing_map_array *a) for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; + kmemleak_free(a->pages[i]); free_page((unsigned long)a->pages[i]); }

@@ -262,6 +264,7 @@ struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL); if (!a->pages[i]) goto free; + kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL); } out: return a;

From: Felix Fietkau nbd@nbd.name

commit 1fe98f5690c4219d419ea9cc190f94b3401cf324 upstream.

Sending them out on a different queue can cause a race condition where a number of packets in the queue may be discarded by the receiver, because the ADDBA request is sent too early. This affects any driver with software A-MPDU setup which does not allocate packet seqno in hardware on tx, regardless of whether iTXQ is used or not. The only driver I've seen that explicitly deals with this issue internally is mwl8k.

Cc: stable@vger.kernel.org Signed-off-by: Felix Fietkau nbd@nbd.name Link: https://lore.kernel.org/r/20211202124533.80388-1-nbd@nbd.name Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mac80211/agg-tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -109,7 +109,7 @@ static void ieee80211_send_addba_request mgmt->u.action.u.addba_req.start_seq_num = cpu_to_le16(start_seq_num << 4);

- ieee80211_tx_skb(sdata, skb); + ieee80211_tx_skb_tid(sdata, skb, tid); }

void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn)

From: Joe Thornber ejt@redhat.com

commit 1b8d2789dad0005fd5e7d35dab26a8e1203fb6da upstream.

Move dm_tm_unlock() after dm_tm_dec().

Cc: stable@vger.kernel.org Signed-off-by: Joe Thornber ejt@redhat.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/persistent-data/dm-btree-remove.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -423,9 +423,9 @@ static int rebalance_children(struct sha

memcpy(n, dm_block_data(child), dm_bm_block_size(dm_tm_get_bm(info->tm))); - dm_tm_unlock(info->tm, child);

dm_tm_dec(info->tm, dm_block_location(child)); + dm_tm_unlock(info->tm, child); return 0; }

From: Nathan Chancellor nathan@kernel.org

[ Upstream commit a7083763619f7485ccdade160deb81737cf2732f ]

A new warning in clang points out two instances where boolean expressions are being used with a bitwise OR instead of logical OR:

drivers/soc/tegra/fuse/speedo-tegra20.c:72:9: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical] reg = tegra_fuse_read_spare(i) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ || drivers/soc/tegra/fuse/speedo-tegra20.c:72:9: note: cast one or both operands to int to silence this warning drivers/soc/tegra/fuse/speedo-tegra20.c:87:9: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical] reg = tegra_fuse_read_spare(i) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ || drivers/soc/tegra/fuse/speedo-tegra20.c:87:9: note: cast one or both operands to int to silence this warning 2 warnings generated.

The motivation for the warning is that logical operations short circuit while bitwise operations do not.

In this instance, tegra_fuse_read_spare() is not semantically returning a boolean, it is returning a bit value. Use u32 for its return type so that it can be used with either bitwise or boolean operators without any warnings.

Fixes: 25cd5a391478 ("ARM: tegra: Add speedo-based process identification") Link: https://github.com/ClangBuiltLinux/linux/issues/1488 Suggested-by: Michał Mirosław mirq-linux@rere.qmqm.pl Signed-off-by: Nathan Chancellor nathan@kernel.org Reviewed-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Thierry Reding treding@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/tegra/fuse/fuse-tegra.c | 2 +- drivers/soc/tegra/fuse/fuse.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c index c4f5e5bbb8dce..9397e8ba26469 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra.c +++ b/drivers/soc/tegra/fuse/fuse-tegra.c @@ -176,7 +176,7 @@ static struct platform_driver tegra_fuse_driver = { }; module_platform_driver(tegra_fuse_driver);

-bool __init tegra_fuse_read_spare(unsigned int spare) +u32 __init tegra_fuse_read_spare(unsigned int spare) { unsigned int offset = fuse->soc->info->spare + spare * 4;

diff --git a/drivers/soc/tegra/fuse/fuse.h b/drivers/soc/tegra/fuse/fuse.h index 10c2076d5089a..f368bd5373088 100644 --- a/drivers/soc/tegra/fuse/fuse.h +++ b/drivers/soc/tegra/fuse/fuse.h @@ -62,7 +62,7 @@ struct tegra_fuse { void tegra_init_revision(void); void tegra_init_apbmisc(void);

-bool __init tegra_fuse_read_spare(unsigned int spare); +u32 __init tegra_fuse_read_spare(unsigned int spare); u32 __init tegra_fuse_read_early(unsigned int offset);

#ifdef CONFIG_ARCH_TEGRA_2x_SOC

From: Cyril Novikov cnovikov@lynx.com

[ Upstream commit bf0a375055bd1afbbf02a0ef45f7655da7b71317 ]

The MDIO bus speed must be initialized before talking to the PHY the first time in order to avoid talking to it using a speed that the PHY doesn't support.

This fixes HW initialization error -17 (IXGBE_ERR_PHY_ADDR_INVALID) on Denverton CPUs (a.k.a. the Atom C3000 family) on ports with a 10Gb network plugged in. On those devices, HLREG0[MDCSPD] resets to 1, which combined with the 10Gb network results in a 24MHz MDIO speed, which is apparently too fast for the connected PHY. PHY register reads over MDIO bus return garbage, leading to initialization failure.

Reproduced with Linux kernel 4.19 and 5.15-rc7. Can be reproduced using the following setup:

* Use an Atom C3000 family system with at least one X552 LAN on the SoC * Disable PXE or other BIOS network initialization if possible (the interface must not be initialized before Linux boots) * Connect a live 10Gb Ethernet cable to an X550 port * Power cycle (not reset, doesn't always work) the system and boot Linux * Observe: ixgbe interfaces w/ 10GbE cables plugged in fail with error -17

Fixes: e84db7272798 ("ixgbe: Introduce function to control MDIO speed") Signed-off-by: Cyril Novikov cnovikov@lynx.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 8466f3874a285..5029db8835d7d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -2597,6 +2597,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) /* flush pending Tx transactions */ ixgbe_clear_tx_pending(hw);

+ /* set MDIO speed before talking to the PHY in case it's the 1st time */ + ixgbe_set_mdio_speed(hw); + /* PHY ops must be identified and initialized prior to reset */

/* Identify PHY and related function pointers */

From: Thomas Gleixner tglx@linutronix.de

commit 94185adbfad56815c2c8401e16d81bdb74a79201 upstream.

PCI_MSIX_FLAGS_MASKALL is set in the MSI-X control register at MSI-X interrupt setup time. It's cleared on success, but the error handling path only clears the PCI_MSIX_FLAGS_ENABLE bit.

That's incorrect as the reset state of the PCI_MSIX_FLAGS_MASKALL bit is zero. That can be observed via lspci:

Capabilities: [b0] MSI-X: Enable- Count=67 Masked+

Clear the bit in the error path to restore the reset state.

Fixes: 438553958ba1 ("PCI/MSI: Enable and mask MSI-X early") Reported-by: Stefan Roese sr@denx.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Stefan Roese sr@denx.de Cc: linux-pci@vger.kernel.org Cc: Bjorn Helgaas bhelgaas@google.com Cc: Michal Simek michal.simek@xilinx.com Cc: Marek Vasut marex@denx.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87tufevoqx.ffs@tglx Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -871,7 +871,7 @@ out_free: free_msi_irqs(dev);

out_disable: - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0);

return ret; }

From: Yu Liao liaoyu15@huawei.com

commit 4e8c11b6b3f0b6a283e898344f154641eda94266 upstream.

Even after commit e1d7ba873555 ("time: Always make sure wall_to_monotonic isn't positive") it is still possible to make wall_to_monotonic positive by running the following code:

int main(void) { struct timespec time;

clock_gettime(CLOCK_MONOTONIC, &time); time.tv_nsec = 0; clock_settime(CLOCK_REALTIME, &time); return 0; }

The reason is that the second parameter of timespec64_compare(), ts_delta, may be unnormalized because the delta is calculated with an open coded substraction which causes the comparison of tv_sec to yield the wrong result:

wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 } ts_delta = { .tv_sec = -9, .tv_nsec = -900000000 }

That makes timespec64_compare() claim that wall_to_monotonic < ts_delta, but actually the result should be wall_to_monotonic > ts_delta.

After normalization, the result of timespec64_compare() is correct because the tv_sec comparison is not longer misleading:

wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 } ts_delta = { .tv_sec = -10, .tv_nsec = 100000000 }

Use timespec64_sub() to ensure that ts_delta is normalized, which fixes the issue.

Fixes: e1d7ba873555 ("time: Always make sure wall_to_monotonic isn't positive") Signed-off-by: Yu Liao liaoyu15@huawei.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211213135727.1656662-1-liaoyu15@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/time/timekeeping.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1198,8 +1198,7 @@ int do_settimeofday64(const struct times timekeeping_forward_now(tk);

xt = tk_xtime(tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta = timespec64_sub(*ts, xt);

if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL;

From: Sudeep Holla sudeep.holla@arm.com

commit 865ed67ab955428b9aa771d8b4f1e4fb7fd08945 upstream.

Without the bound checks for scpi_pd->name, it could result in the buffer overflow when copying the SCPI device name from the corresponding device tree node as the name string is set at maximum size of 30.

Let us fix it by using devm_kasprintf so that the string buffer is allocated dynamically.

Fixes: 8bec4337ad40 ("firmware: scpi: add device power domain support using genpd") Reported-by: Pedro Batista pedbap.g@gmail.com Signed-off-by: Sudeep Holla sudeep.holla@arm.com Cc: stable@vger.kernel.org Cc: Cristian Marussi cristian.marussi@arm.com Link: https://lore.kernel.org/r/20211209120456.696879-1-sudeep.holla@arm.com' Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/firmware/scpi_pm_domain.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

--- a/drivers/firmware/scpi_pm_domain.c +++ b/drivers/firmware/scpi_pm_domain.c @@ -27,7 +27,6 @@ struct scpi_pm_domain { struct generic_pm_domain genpd; struct scpi_ops *ops; u32 domain; - char name[30]; };

/* @@ -121,8 +120,13 @@ static int scpi_pm_domain_probe(struct p

scpi_pd->domain = i; scpi_pd->ops = scpi_ops; - sprintf(scpi_pd->name, "%s.%d", np->name, i); - scpi_pd->genpd.name = scpi_pd->name; + scpi_pd->genpd.name = devm_kasprintf(dev, GFP_KERNEL, + "%s.%d", np->name, i); + if (!scpi_pd->genpd.name) { + dev_err(dev, "Failed to allocate genpd name:%s.%d\n", + np->name, i); + continue; + } scpi_pd->genpd.power_off = scpi_pd_power_off; scpi_pd->genpd.power_on = scpi_pd_power_on;

From: George Kennedy george.kennedy@oracle.com

commit e0a2c28da11e2c2b963fc01d50acbf03045ac732 upstream.

In resp_mode_select() sanity check the block descriptor len to avoid UAF.

BUG: KASAN: use-after-free in resp_mode_select+0xa4c/0xb40 drivers/scsi/scsi_debug.c:2509 Read of size 1 at addr ffff888026670f50 by task scsicmd/15032

CPU: 1 PID: 15032 Comm: scsicmd Not tainted 5.15.0-01d0625 #15 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Call Trace: <TASK> dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:107 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:257 kasan_report.cold.14+0x7d/0x117 mm/kasan/report.c:443 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report_generic.c:306 resp_mode_select+0xa4c/0xb40 drivers/scsi/scsi_debug.c:2509 schedule_resp+0x4af/0x1a10 drivers/scsi/scsi_debug.c:5483 scsi_debug_queuecommand+0x8c9/0x1e70 drivers/scsi/scsi_debug.c:7537 scsi_queue_rq+0x16b4/0x2d10 drivers/scsi/scsi_lib.c:1521 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1640 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1762 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1839 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:63 sg_common_write.isra.18+0xeb3/0x2000 drivers/scsi/sg.c:837 sg_new_write.isra.19+0x570/0x8c0 drivers/scsi/sg.c:775 sg_ioctl_common+0x14d6/0x2710 drivers/scsi/sg.c:941 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1166 __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:52 do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:50 entry_SYSCALL_64_after_hwframe+0x44/0xae arch/x86/entry/entry_64.S:113

Link: https://lore.kernel.org/r/1637262208-28850-1-git-send-email-george.kennedy@o... Reported-by: syzkaller syzkaller@googlegroups.com Acked-by: Douglas Gilbert dgilbert@interlog.com Signed-off-by: George Kennedy george.kennedy@oracle.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/scsi_debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -2175,11 +2175,11 @@ static int resp_mode_select(struct scsi_ __func__, param_len, res); md_len = mselect6 ? (arr[0] + 1) : (get_unaligned_be16(arr + 0) + 2); bd_len = mselect6 ? arr[3] : get_unaligned_be16(arr + 6); - if (md_len > 2) { + off = bd_len + (mselect6 ? 4 : 8); + if (md_len > 2 || off >= res) { mk_sense_invalid_fld(scp, SDEB_IN_DATA, 0, -1); return check_condition_result; } - off = bd_len + (mselect6 ? 4 : 8); mpage = arr[off] & 0x3f; ps = !!(arr[off] & 0x80); if (ps) {

From: Nicolas Pitre nicolas.pitre@linaro.org

commit b99afae1390140f5b0039e6b37a7380de31ae874 upstream.

The naked attribute is known to confuse some old gcc versions when function arguments aren't explicitly listed as inline assembly operands despite the gcc documentation. That resulted in commit 9a40ac86152c ("ARM: 6164/1: Add kto and kfrom to input operands list.").

Yet that commit has problems of its own by having assembly operand constraints completely wrong. If the generated code has been OK since then, it is due to luck rather than correctness. So this patch also provides proper assembly operand constraints, and removes two instances of redundant register usages in the implementation while at it.

Inspection of the generated code with this patch doesn't show any obvious quality degradation either, so not relying on __naked at all will make the code less fragile, and avoid some issues with clang.

The only remaining __naked instances (excluding the kprobes test cases) are exynos_pm_power_up_setup(), tc2_pm_power_up_setup() and

cci_enable_port_for_self(. But in the first two cases, only the function address is used by the compiler with no chance of inlining it by mistake, and the third case is called from assembly code only. And the fact that no stack is available when the corresponding code is executed does warrant the __naked usage in those cases.

Signed-off-by: Nicolas Pitre nico@linaro.org Reviewed-by: Stefan Agner stefan@agner.ch Tested-by: Stefan Agner stefan@agner.ch Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Anders Roxell anders.roxell@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/mm/copypage-fa.c | 35 ++++++-------- arch/arm/mm/copypage-feroceon.c | 98 +++++++++++++++++++--------------------- arch/arm/mm/copypage-v4mc.c | 19 +++---- arch/arm/mm/copypage-v4wb.c | 41 ++++++++-------- arch/arm/mm/copypage-v4wt.c | 37 +++++++-------- arch/arm/mm/copypage-xsc3.c | 71 ++++++++++++---------------- arch/arm/mm/copypage-xscale.c | 71 ++++++++++++++-------------- 7 files changed, 178 insertions(+), 194 deletions(-)

--- a/arch/arm/mm/copypage-fa.c +++ b/arch/arm/mm/copypage-fa.c @@ -17,26 +17,25 @@ /* * Faraday optimised copy_user_page */ -static void __naked -fa_copy_user_page(void *kto, const void *kfrom) +static void fa_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %0 @ 1\n\ -1: ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - subs r2, r2, #1 @ 1\n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + subs %2, %2, #1 @ 1\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "I" (PAGE_SIZE / 32)); + mcr p15, 0, %2, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 32) + : "r3", "r4", "ip", "lr"); }

void fa_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-feroceon.c +++ b/arch/arm/mm/copypage-feroceon.c @@ -13,58 +13,56 @@ #include <linux/init.h> #include <linux/highmem.h>

-static void __naked -feroceon_copy_user_page(void *kto, const void *kfrom) +static void feroceon_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4-r9, lr} \n\ - mov ip, %2 \n\ -1: mov lr, r1 \n\ - ldmia r1!, {r2 - r9} \n\ - pld [lr, #32] \n\ - pld [lr, #64] \n\ - pld [lr, #96] \n\ - pld [lr, #128] \n\ - pld [lr, #160] \n\ - pld [lr, #192] \n\ - pld [lr, #224] \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - subs ip, ip, #(32 * 8) \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r2 - r7, ip, lr} \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ + pld [%1, #128] \n\ + pld [%1, #160] \n\ + pld [%1, #192] \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + subs %2, %2, #(32 * 8) \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ bne 1b \n\ - mcr p15, 0, ip, c7, c10, 4 @ drain WB\n\ - ldmfd sp!, {r4-r9, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE)); + mcr p15, 0, %2, c7, c10, 4 @ drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE) + : "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr"); }

void feroceon_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -40,12 +40,11 @@ static DEFINE_RAW_SPINLOCK(minicache_loc * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { - asm volatile( - "stmfd sp!, {r4, lr} @ 2\n\ - mov r4, %2 @ 1\n\ + int tmp; + + asm volatile ("\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ 1: mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ @@ -55,13 +54,13 @@ mc_copy_user_page(void *from, void *to) mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ - subs r4, r4, #1 @ 1\n\ + subs %2, %2, #1 @ 1\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmneia %0!, {r2, r3, ip, lr} @ 4\n\ - bne 1b @ 1\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64)); + bne 1b @ " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r2", "r3", "ip", "lr"); }

void v4_mc_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-v4wb.c +++ b/arch/arm/mm/copypage-v4wb.c @@ -22,29 +22,28 @@ * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -v4wb_copy_user_page(void *kto, const void *kfrom) +static void v4wb_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r1, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %1, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); }

void v4wb_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-v4wt.c +++ b/arch/arm/mm/copypage-v4wt.c @@ -20,27 +20,26 @@ * dirty data in the cache. However, we do have to ensure that * subsequent reads are up to date. */ -static void __naked -v4wt_copy_user_page(void *kto, const void *kfrom) +static void v4wt_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c7, 0 @ flush ID cache\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %2, c7, c7, 0 @ flush ID cache" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); }

void v4wt_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-xsc3.c +++ b/arch/arm/mm/copypage-xsc3.c @@ -21,53 +21,46 @@

/* * XSC3 optimised copy_user_highpage - * r0 = destination - * r1 = source * * The source page may have some clean entries in the cache already, but we * can safely ignore them - break_cow() will flush them out of the cache * if we eventually end up using our copied page. * */ -static void __naked -xsc3_mc_copy_user_page(void *kto, const void *kfrom) +static void xsc3_mc_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r1, #64] \n\ - pld [r1, #96] \n\ + int tmp; + + asm volatile ("\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%1, #64] \n\ + pld [%1, #96] \n\ \n\ -2: ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - subs lr, lr, #1 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ +2: ldrd r2, [%1], #8 \n\ + ldrd r4, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, [%0], #8 \n\ + ldrd r2, [%1], #8 \n\ + strd r4, [%0], #8 \n\ + ldrd r4, [%1], #8 \n\ + strd r2, [%0], #8 \n\ + strd r4, [%0], #8 \n\ + ldrd r2, [%1], #8 \n\ + ldrd r4, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, [%0], #8 \n\ + ldrd r2, [%1], #8 \n\ + subs %2, %2, #1 \n\ + strd r4, [%0], #8 \n\ + ldrd r4, [%1], #8 \n\ + strd r2, [%0], #8 \n\ + strd r4, [%0], #8 \n\ bgt 1b \n\ - beq 2b \n\ - \n\ - ldmfd sp!, {r4, r5, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5"); }

void xsc3_mc_copy_user_highpage(struct page *to, struct page *from, @@ -85,8 +78,6 @@ void xsc3_mc_copy_user_highpage(struct p

/* * XScale optimised clear_user_page - * r0 = destination - * r1 = virtual user address of ultimate destination page */ void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr) { --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -36,52 +36,51 @@ static DEFINE_RAW_SPINLOCK(minicache_loc * Dcache aliasing issue. The writes will be forwarded to the write buffer, * and merged as appropriate. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { + int tmp; + /* * Strangely enough, best performance is achieved * when prefetching destination as well. (NP) */ - asm volatile( - "stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - pld [r0, #0] \n\ - pld [r0, #32] \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r0, #64] \n\ - pld [r0, #96] \n\ - pld [r1, #64] \n\ - pld [r1, #96] \n\ -2: ldrd r2, [r0], #8 \n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + asm volatile ("\ + pld [%0, #0] \n\ + pld [%0, #32] \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%0, #64] \n\ + pld [%0, #96] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ +2: ldrd r2, [%0], #8 \n\ + ldrd r4, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, [%1], #8 \n\ + ldrd r2, [%0], #8 \n\ + strd r4, [%1], #8 \n\ + ldrd r4, [%0], #8 \n\ + strd r2, [%1], #8 \n\ + strd r4, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - ldrd r2, [r0], #8 \n\ + ldrd r2, [%0], #8 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + ldrd r4, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, [%1], #8 \n\ + ldrd r2, [%0], #8 \n\ + strd r4, [%1], #8 \n\ + ldrd r4, [%0], #8 \n\ + strd r2, [%1], #8 \n\ + strd r4, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - subs lr, lr, #1 \n\ + subs %2, %2, #1 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ bgt 1b \n\ - beq 2b \n\ - ldmfd sp!, {r4, r5, pc} " - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5", "ip"); }

void xscale_mc_copy_user_highpage(struct page *to, struct page *from,

From: Nathan Chancellor nathan@kernel.org

commit a02dcde595f7cbd240ccd64de96034ad91cffc40 upstream.

A new warning in clang points out a few places in this driver where a bitwise OR is being used with boolean types:

drivers/input/touchscreen.c:81:17: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical] data_present = touchscreen_get_prop_u32(dev, "touchscreen-min-x", ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

This use of a bitwise OR is intentional, as bitwise operations do not short circuit, which allows all the calls to touchscreen_get_prop_u32() to happen so that the last parameter is initialized while coalescing the results of the calls to make a decision after they are all evaluated.

To make this clearer to the compiler, use the '|=' operator to assign the result of each touchscreen_get_prop_u32() call to data_present, which keeps the meaning of the code the same but makes it obvious that every one of these calls is expected to happen.

Signed-off-by: Nathan Chancellor nathan@kernel.org Reported-by: Nick Desaulniers ndesaulniers@google.com Reviewed-by: Nick Desaulniers ndesaulniers@google.com Link: https://lore.kernel.org/r/20211014205757.3474635-1-nathan@kernel.org Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Anders Roxell anders.roxell@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/input/touchscreen/of_touchscreen.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)

--- a/drivers/input/touchscreen/of_touchscreen.c +++ b/drivers/input/touchscreen/of_touchscreen.c @@ -79,8 +79,8 @@ void touchscreen_parse_properties(struct data_present = touchscreen_get_prop_u32(dev, "touchscreen-size-x", input_abs_get_max(input, axis) + 1, - &maximum) | - touchscreen_get_prop_u32(dev, "touchscreen-fuzz-x", + &maximum); + data_present |= touchscreen_get_prop_u32(dev, "touchscreen-fuzz-x", input_abs_get_fuzz(input, axis), &fuzz); if (data_present) @@ -90,8 +90,8 @@ void touchscreen_parse_properties(struct data_present = touchscreen_get_prop_u32(dev, "touchscreen-size-y", input_abs_get_max(input, axis) + 1, - &maximum) | - touchscreen_get_prop_u32(dev, "touchscreen-fuzz-y", + &maximum); + data_present |= touchscreen_get_prop_u32(dev, "touchscreen-fuzz-y", input_abs_get_fuzz(input, axis), &fuzz); if (data_present) @@ -101,11 +101,11 @@ void touchscreen_parse_properties(struct data_present = touchscreen_get_prop_u32(dev, "touchscreen-max-pressure", input_abs_get_max(input, axis), - &maximum) | - touchscreen_get_prop_u32(dev, - "touchscreen-fuzz-pressure", - input_abs_get_fuzz(input, axis), - &fuzz); + &maximum); + data_present |= touchscreen_get_prop_u32(dev, + "touchscreen-fuzz-pressure", + input_abs_get_fuzz(input, axis), + &fuzz); if (data_present) touchscreen_set_params(input, axis, maximum, fuzz);

From: Juergen Gross jgross@suse.com

commit b27d47950e481f292c0a5ad57357edb9d95d03ba upstream.

The Xen netfront driver is still vulnerable for an attack via excessive number of events sent by the backend. Fix that by using lateeoi event channels.

For being able to detect the case of no rx responses being added while the carrier is down a new lock is needed in order to update and test rsp_cons and the number of seen unconsumed responses atomically.

This is part of XSA-391

Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/xen-netfront.c | 125 +++++++++++++++++++++++++++++++++------------ 1 file changed, 94 insertions(+), 31 deletions(-)

--- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -141,6 +141,9 @@ struct netfront_queue { struct sk_buff *rx_skbs[NET_RX_RING_SIZE]; grant_ref_t gref_rx_head; grant_ref_t grant_rx_ref[NET_RX_RING_SIZE]; + + unsigned int rx_rsp_unconsumed; + spinlock_t rx_cons_lock; };

struct netfront_info { @@ -365,12 +368,13 @@ static int xennet_open(struct net_device return 0; }

-static void xennet_tx_buf_gc(struct netfront_queue *queue) +static bool xennet_tx_buf_gc(struct netfront_queue *queue) { RING_IDX cons, prod; unsigned short id; struct sk_buff *skb; bool more_to_do; + bool work_done = false; const struct device *dev = &queue->info->netdev->dev;

BUG_ON(!netif_carrier_ok(queue->info->netdev)); @@ -387,6 +391,8 @@ static void xennet_tx_buf_gc(struct netf for (cons = queue->tx.rsp_cons; cons != prod; cons++) { struct xen_netif_tx_response txrsp;

+ work_done = true; + RING_COPY_RESPONSE(&queue->tx, cons, &txrsp); if (txrsp.status == XEN_NETIF_RSP_NULL) continue; @@ -430,11 +436,13 @@ static void xennet_tx_buf_gc(struct netf

xennet_maybe_wake_tx(queue);

- return; + return work_done;

err: queue->info->broken = true; dev_alert(dev, "Disabled for further use\n"); + + return work_done; }

struct xennet_gnttab_make_txreq { @@ -754,6 +762,16 @@ static int xennet_close(struct net_devic return 0; }

+static void xennet_set_rx_rsp_cons(struct netfront_queue *queue, RING_IDX val) +{ + unsigned long flags; + + spin_lock_irqsave(&queue->rx_cons_lock, flags); + queue->rx.rsp_cons = val; + queue->rx_rsp_unconsumed = RING_HAS_UNCONSUMED_RESPONSES(&queue->rx); + spin_unlock_irqrestore(&queue->rx_cons_lock, flags); +} + static void xennet_move_rx_slot(struct netfront_queue *queue, struct sk_buff *skb, grant_ref_t ref) { @@ -805,7 +823,7 @@ static int xennet_get_extras(struct netf xennet_move_rx_slot(queue, skb, ref); } while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);

- queue->rx.rsp_cons = cons; + xennet_set_rx_rsp_cons(queue, cons); return err; }

@@ -885,7 +903,7 @@ next: }

if (unlikely(err)) - queue->rx.rsp_cons = cons + slots; + xennet_set_rx_rsp_cons(queue, cons + slots);

return err; } @@ -939,7 +957,8 @@ static int xennet_fill_frags(struct netf __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { - queue->rx.rsp_cons = ++cons + skb_queue_len(list); + xennet_set_rx_rsp_cons(queue, + ++cons + skb_queue_len(list)); kfree_skb(nskb); return -ENOENT; } @@ -952,7 +971,7 @@ static int xennet_fill_frags(struct netf kfree_skb(nskb); }

- queue->rx.rsp_cons = cons; + xennet_set_rx_rsp_cons(queue, cons);

return 0; } @@ -1073,7 +1092,9 @@ err:

if (unlikely(xennet_set_skb_gso(skb, gso))) { __skb_queue_head(&tmpq, skb); - queue->rx.rsp_cons += skb_queue_len(&tmpq); + xennet_set_rx_rsp_cons(queue, + queue->rx.rsp_cons + + skb_queue_len(&tmpq)); goto err; } } @@ -1097,7 +1118,8 @@ err:

__skb_queue_tail(&rxq, skb);

- i = ++queue->rx.rsp_cons; + i = queue->rx.rsp_cons + 1; + xennet_set_rx_rsp_cons(queue, i); work_done++; }

@@ -1281,40 +1303,79 @@ static int xennet_set_features(struct ne return 0; }

-static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id) +static bool xennet_handle_tx(struct netfront_queue *queue, unsigned int *eoi) { - struct netfront_queue *queue = dev_id; unsigned long flags;

- if (queue->info->broken) - return IRQ_HANDLED; + if (unlikely(queue->info->broken)) + return false;

spin_lock_irqsave(&queue->tx_lock, flags); - xennet_tx_buf_gc(queue); + if (xennet_tx_buf_gc(queue)) + *eoi = 0; spin_unlock_irqrestore(&queue->tx_lock, flags);

+ return true; +} + +static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id) +{ + unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS; + + if (likely(xennet_handle_tx(dev_id, &eoiflag))) + xen_irq_lateeoi(irq, eoiflag); + return IRQ_HANDLED; }

-static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id) +static bool xennet_handle_rx(struct netfront_queue *queue, unsigned int *eoi) { - struct netfront_queue *queue = dev_id; - struct net_device *dev = queue->info->netdev; + unsigned int work_queued; + unsigned long flags; + + if (unlikely(queue->info->broken)) + return false;

- if (queue->info->broken) - return IRQ_HANDLED; + spin_lock_irqsave(&queue->rx_cons_lock, flags); + work_queued = RING_HAS_UNCONSUMED_RESPONSES(&queue->rx); + if (work_queued > queue->rx_rsp_unconsumed) { + queue->rx_rsp_unconsumed = work_queued; + *eoi = 0; + } else if (unlikely(work_queued < queue->rx_rsp_unconsumed)) { + const struct device *dev = &queue->info->netdev->dev; + + spin_unlock_irqrestore(&queue->rx_cons_lock, flags); + dev_alert(dev, "RX producer index going backwards\n"); + dev_alert(dev, "Disabled for further use\n"); + queue->info->broken = true; + return false; + } + spin_unlock_irqrestore(&queue->rx_cons_lock, flags);

- if (likely(netif_carrier_ok(dev) && - RING_HAS_UNCONSUMED_RESPONSES(&queue->rx))) + if (likely(netif_carrier_ok(queue->info->netdev) && work_queued)) napi_schedule(&queue->napi);

+ return true; +} + +static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id) +{ + unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS; + + if (likely(xennet_handle_rx(dev_id, &eoiflag))) + xen_irq_lateeoi(irq, eoiflag); + return IRQ_HANDLED; }

static irqreturn_t xennet_interrupt(int irq, void *dev_id) { - xennet_tx_interrupt(irq, dev_id); - xennet_rx_interrupt(irq, dev_id); + unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS; + + if (xennet_handle_tx(dev_id, &eoiflag) && + xennet_handle_rx(dev_id, &eoiflag)) + xen_irq_lateeoi(irq, eoiflag); + return IRQ_HANDLED; }

@@ -1546,9 +1607,10 @@ static int setup_netfront_single(struct if (err < 0) goto fail;

- err = bind_evtchn_to_irqhandler(queue->tx_evtchn, - xennet_interrupt, - 0, queue->info->netdev->name, queue); + err = bind_evtchn_to_irqhandler_lateeoi(queue->tx_evtchn, + xennet_interrupt, 0, + queue->info->netdev->name, + queue); if (err < 0) goto bind_fail; queue->rx_evtchn = queue->tx_evtchn; @@ -1576,18 +1638,18 @@ static int setup_netfront_split(struct n

snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name), "%s-tx", queue->name); - err = bind_evtchn_to_irqhandler(queue->tx_evtchn, - xennet_tx_interrupt, - 0, queue->tx_irq_name, queue); + err = bind_evtchn_to_irqhandler_lateeoi(queue->tx_evtchn, + xennet_tx_interrupt, 0, + queue->tx_irq_name, queue); if (err < 0) goto bind_tx_fail; queue->tx_irq = err;

snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name), "%s-rx", queue->name); - err = bind_evtchn_to_irqhandler(queue->rx_evtchn, - xennet_rx_interrupt, - 0, queue->rx_irq_name, queue); + err = bind_evtchn_to_irqhandler_lateeoi(queue->rx_evtchn, + xennet_rx_interrupt, 0, + queue->rx_irq_name, queue); if (err < 0) goto bind_rx_fail; queue->rx_irq = err; @@ -1689,6 +1751,7 @@ static int xennet_init_queue(struct netf

spin_lock_init(&queue->tx_lock); spin_lock_init(&queue->rx_lock); + spin_lock_init(&queue->rx_cons_lock);

setup_timer(&queue->rx_refill_timer, rx_refill_timeout, (unsigned long)queue);

From: Juergen Gross jgross@suse.com

commit 6032046ec4b70176d247a71836186d47b25d1684 upstream.

Commit 1d5d48523900a4b ("xen-netback: require fewer guest Rx slots when not using GSO") introduced a security problem in netback, as an interface would only be regarded to be stalled if no slot is available in the rx queue ring page. In case the SKB at the head of the queued requests will need more than one rx slot and only one slot is free the stall detection logic will never trigger, as the test for that is only looking for at least one slot to be free.

Fix that by testing for the needed number of slots instead of only one slot being available.

In order to not have to take the rx queue lock that often, store the number of needed slots in the queue data. As all SKB dequeue operations happen in the rx queue kernel thread this is safe, as long as the number of needed slots is accessed via READ/WRITE_ONCE() only and updates are always done with the rx queue lock held.

Add a small helper for obtaining the number of free slots.

This is part of XSA-392

Fixes: 1d5d48523900a4b ("xen-netback: require fewer guest Rx slots when not using GSO") Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/xen-netback/common.h | 1 drivers/net/xen-netback/rx.c | 65 ++++++++++++++++++++++++--------------- 2 files changed, 42 insertions(+), 24 deletions(-)

--- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -203,6 +203,7 @@ struct xenvif_queue { /* Per-queue data unsigned int rx_queue_max; unsigned int rx_queue_len; unsigned long last_rx_time; + unsigned int rx_slots_needed; bool stalled;

struct xenvif_copy_state rx_copy; --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -33,28 +33,36 @@ #include <xen/xen.h> #include <xen/events.h>

-static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue) +/* + * Update the needed ring page slots for the first SKB queued. + * Note that any call sequence outside the RX thread calling this function + * needs to wake up the RX thread via a call of xenvif_kick_thread() + * afterwards in order to avoid a race with putting the thread to sleep. + */ +static void xenvif_update_needed_slots(struct xenvif_queue *queue, + const struct sk_buff *skb) { - RING_IDX prod, cons; - struct sk_buff *skb; - int needed; - unsigned long flags; + unsigned int needed = 0;

- spin_lock_irqsave(&queue->rx_queue.lock, flags); - - skb = skb_peek(&queue->rx_queue); - if (!skb) { - spin_unlock_irqrestore(&queue->rx_queue.lock, flags); - return false; + if (skb) { + needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE); + if (skb_is_gso(skb)) + needed++; + if (skb->sw_hash) + needed++; }

- needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE); - if (skb_is_gso(skb)) - needed++; - if (skb->sw_hash) - needed++; + WRITE_ONCE(queue->rx_slots_needed, needed); +}

- spin_unlock_irqrestore(&queue->rx_queue.lock, flags); +static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + unsigned int needed; + + needed = READ_ONCE(queue->rx_slots_needed); + if (!needed) + return false;

do { prod = queue->rx.sring->req_prod; @@ -80,6 +88,9 @@ void xenvif_rx_queue_tail(struct xenvif_

spin_lock_irqsave(&queue->rx_queue.lock, flags);

+ if (skb_queue_empty(&queue->rx_queue)) + xenvif_update_needed_slots(queue, skb); + __skb_queue_tail(&queue->rx_queue, skb);

queue->rx_queue_len += skb->len; @@ -100,6 +111,8 @@ static struct sk_buff *xenvif_rx_dequeue

skb = __skb_dequeue(&queue->rx_queue); if (skb) { + xenvif_update_needed_slots(queue, skb_peek(&queue->rx_queue)); + queue->rx_queue_len -= skb->len; if (queue->rx_queue_len < queue->rx_queue_max) { struct netdev_queue *txq; @@ -474,27 +487,31 @@ void xenvif_rx_action(struct xenvif_queu xenvif_rx_copy_flush(queue); }

-static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue) +static RING_IDX xenvif_rx_queue_slots(const struct xenvif_queue *queue) { RING_IDX prod, cons;

prod = queue->rx.sring->req_prod; cons = queue->rx.req_cons;

+ return prod - cons; +} + +static bool xenvif_rx_queue_stalled(const struct xenvif_queue *queue) +{ + unsigned int needed = READ_ONCE(queue->rx_slots_needed); + return !queue->stalled && - prod - cons < 1 && + xenvif_rx_queue_slots(queue) < needed && time_after(jiffies, queue->last_rx_time + queue->vif->stall_timeout); }

static bool xenvif_rx_queue_ready(struct xenvif_queue *queue) { - RING_IDX prod, cons; - - prod = queue->rx.sring->req_prod; - cons = queue->rx.req_cons; + unsigned int needed = READ_ONCE(queue->rx_slots_needed);

- return queue->stalled && prod - cons >= 1; + return queue->stalled && xenvif_rx_queue_slots(queue) >= needed; }

bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread)