From f0d2f15362f02444c5d7ffd5a5eb03e4aa54b685 Mon Sep 17 00:00:00 2001 From: Rong Chen Date: Wed, 16 Feb 2022 20:42:39 +0800 Subject: mmc: meson: Fix usage of meson_mmc_post_req() Currently meson_mmc_post_req() is called in meson_mmc_request() right after meson_mmc_start_cmd(). This could lead to DMA unmapping before the request is actually finished. To fix, don't call meson_mmc_post_req() until meson_mmc_request_done(). Signed-off-by: Rong Chen Reviewed-by: Kevin Hilman Fixes: 79ed05e329c3 ("mmc: meson-gx: add support for descriptor chain mode") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220216124239.4007667-1-rong.chen@amlogic.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/meson-gx-mmc.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 8f36536cb1b6..58ab9d90bc8b 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -173,6 +173,8 @@ struct meson_host { int irq; bool vqmmc_enabled; + bool needs_pre_post_req; + }; #define CMD_CFG_LENGTH_MASK GENMASK(8, 0) @@ -663,6 +665,8 @@ static void meson_mmc_request_done(struct mmc_host *mmc, struct meson_host *host = mmc_priv(mmc); host->cmd = NULL; + if (host->needs_pre_post_req) + meson_mmc_post_req(mmc, mrq, 0); mmc_request_done(host->mmc, mrq); } @@ -880,7 +884,7 @@ static int meson_mmc_validate_dram_access(struct mmc_host *mmc, struct mmc_data static void meson_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq) { struct meson_host *host = mmc_priv(mmc); - bool needs_pre_post_req = mrq->data && + host->needs_pre_post_req = mrq->data && !(mrq->data->host_cookie & SD_EMMC_PRE_REQ_DONE); /* @@ -896,22 +900,19 @@ static void meson_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq) } } - if (needs_pre_post_req) { + if (host->needs_pre_post_req) { meson_mmc_get_transfer_mode(mmc, mrq); if (!meson_mmc_desc_chain_mode(mrq->data)) - needs_pre_post_req = false; + host->needs_pre_post_req = false; } - if (needs_pre_post_req) + if (host->needs_pre_post_req) meson_mmc_pre_req(mmc, mrq); /* Stop execution */ writel(0, host->regs + SD_EMMC_START); meson_mmc_start_cmd(mmc, mrq->sbc ?: mrq->cmd); - - if (needs_pre_post_req) - meson_mmc_post_req(mmc, mrq, 0); } static void meson_mmc_read_resp(struct mmc_host *mmc, struct mmc_command *cmd) -- cgit v1.2.3 From 9feaf8b387ee0ece9c1d7add308776b502a35d0c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 28 Feb 2022 20:18:51 -0800 Subject: efi: fix return value of __setup handlers When "dump_apple_properties" is used on the kernel boot command line, it causes an Unknown parameter message and the string is added to init's argument strings: Unknown kernel command line parameters "dump_apple_properties BOOT_IMAGE=/boot/bzImage-517rc6 efivar_ssdt=newcpu_ssdt", will be passed to user space. Run /sbin/init as init process with arguments: /sbin/init dump_apple_properties with environment: HOME=/ TERM=linux BOOT_IMAGE=/boot/bzImage-517rc6 efivar_ssdt=newcpu_ssdt Similarly when "efivar_ssdt=somestring" is used, it is added to the Unknown parameter message and to init's environment strings, polluting them (see examples above). Change the return value of the __setup functions to 1 to indicate that the __setup options have been handled. Fixes: 58c5475aba67 ("x86/efi: Retrieve and assign Apple device properties") Fixes: 475fb4e8b2f4 ("efi / ACPI: load SSTDs from EFI variables") Signed-off-by: Randy Dunlap Reported-by: Igor Zhbanov Link: lore.kernel.org/r/64644a2f-4a20-bab3-1e15-3b2cdd0defe3@omprussia.ru Cc: Ard Biesheuvel Cc: linux-efi@vger.kernel.org Cc: Lukas Wunner Cc: Octavian Purdila Cc: "Rafael J. Wysocki" Cc: Matt Fleming Link: https://lore.kernel.org/r/20220301041851.12459-1-rdunlap@infradead.org Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/apple-properties.c | 2 +- drivers/firmware/efi/efi.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c index 4c3201e290e2..ea84108035eb 100644 --- a/drivers/firmware/efi/apple-properties.c +++ b/drivers/firmware/efi/apple-properties.c @@ -24,7 +24,7 @@ static bool dump_properties __initdata; static int __init dump_properties_enable(char *arg) { dump_properties = true; - return 0; + return 1; } __setup("dump_apple_properties", dump_properties_enable); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 7de3f5b6e8d0..5502e176d51b 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -212,7 +212,7 @@ static int __init efivar_ssdt_setup(char *str) memcpy(efivar_ssdt, str, strlen(str)); else pr_warn("efivar_ssdt: name too long: %s\n", str); - return 0; + return 1; } __setup("efivar_ssdt=", efivar_ssdt_setup); -- cgit v1.2.3 From 48015b632f770c401f3816f144499a39f2884677 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 11 Feb 2022 17:32:37 +1100 Subject: powerpc: Fix STACKTRACE=n build Our skiroot_defconfig doesn't enable FTRACE, and so doesn't get STACKTRACE enabled either. That leads to a build failure since commit 1614b2b11fab ("arch: Make ARCH_STACKWALK independent of STACKTRACE") made stacktrace.c build even when STACKTRACE=n. arch/powerpc/kernel/stacktrace.c: In function ‘handle_backtrace_ipi’: arch/powerpc/kernel/stacktrace.c:171:2: error: implicit declaration of function ‘nmi_cpu_backtrace’ 171 | nmi_cpu_backtrace(regs); | ^~~~~~~~~~~~~~~~~ arch/powerpc/kernel/stacktrace.c: In function ‘arch_trigger_cpumask_backtrace’: arch/powerpc/kernel/stacktrace.c:226:2: error: implicit declaration of function ‘nmi_trigger_cpumask_backtrace’ 226 | nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ This happens because our headers haven't defined arch_trigger_cpumask_backtrace, which causes lib/nmi_backtrace.c not to build nmi_cpu_backtrace(). The code in question doesn't actually depend on STACKTRACE=y, that was just added because arch_trigger_cpumask_backtrace() lived in stacktrace.c for convenience. So drop the dependency on CONFIG_STACKTRACE, that causes lib/nmi_backtrace.c to build nmi_cpu_backtrace() etc. and fixes the build. Fixes: 1614b2b11fab ("arch: Make ARCH_STACKWALK independent of STACKTRACE") [mpe: Cherry pick of 5a72345e6a78 from next into fixes] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220212111349.2806972-1-mpe@ellerman.id.au --- arch/powerpc/include/asm/nmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 160abcb8e9fa..ea0e487f87b1 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -9,7 +9,7 @@ long soft_nmi_interrupt(struct pt_regs *regs); static inline void arch_touch_nmi_watchdog(void) {} #endif -#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE) +#ifdef CONFIG_NMI_IPI extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace -- cgit v1.2.3 From 1760fdb6fe9f796fbdb9b4106b3e0bbacc16b55c Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 4 Mar 2022 11:56:56 +0100 Subject: mmc: core: Restore (almost) the busy polling for MMC_SEND_OP_COND Commit 76bfc7ccc2fa ("mmc: core: adjust polling interval for CMD1"), significantly decreased the polling period from ~10-12ms into just a couple of us. The purpose was to decrease the total time spent in the busy polling loop, but unfortunate it has lead to problems, that causes eMMC cards to never gets out busy and thus fails to be initialized. To fix the problem, but also to try to keep some of the new improved behaviour, let's start by using a polling period of 1-2ms, which then increases for each loop, according to common polling loop in __mmc_poll_for_busy(). Reported-by: Jean Rene Dawin Reported-by: H. Nikolaus Schaller Cc: Huijin Park Fixes: 76bfc7ccc2fa ("mmc: core: adjust polling interval for CMD1") Signed-off-by: Ulf Hansson Tested-by: Jean Rene Dawin Tested-by: H. Nikolaus Schaller Link: https://lore.kernel.org/r/20220304105656.149281-1-ulf.hansson@linaro.org --- drivers/mmc/core/block.c | 2 +- drivers/mmc/core/mmc.c | 2 +- drivers/mmc/core/mmc_ops.c | 13 +++++++++---- drivers/mmc/core/mmc_ops.h | 3 ++- drivers/mmc/core/sd.c | 2 +- 5 files changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8d718aa56d33..4e67c1403cc9 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1908,7 +1908,7 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) cb_data.card = card; cb_data.status = 0; - err = __mmc_poll_for_busy(card->host, MMC_BLK_TIMEOUT_MS, + err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS, &mmc_blk_busy_cb, &cb_data); /* diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index bbbbcaf70a59..8421519c2a98 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1962,7 +1962,7 @@ static int mmc_sleep(struct mmc_host *host) goto out_release; } - err = __mmc_poll_for_busy(host, timeout_ms, &mmc_sleep_busy_cb, host); + err = __mmc_poll_for_busy(host, 0, timeout_ms, &mmc_sleep_busy_cb, host); out_release: mmc_retune_release(host); diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index d63d1c735335..180d7e9d3400 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -21,6 +21,8 @@ #define MMC_BKOPS_TIMEOUT_MS (120 * 1000) /* 120s */ #define MMC_SANITIZE_TIMEOUT_MS (240 * 1000) /* 240s */ +#define MMC_OP_COND_PERIOD_US (1 * 1000) /* 1ms */ +#define MMC_OP_COND_TIMEOUT_MS 1000 /* 1s */ static const u8 tuning_blk_pattern_4bit[] = { 0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc, @@ -232,7 +234,9 @@ int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr) cmd.arg = mmc_host_is_spi(host) ? 0 : ocr; cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R3 | MMC_CMD_BCR; - err = __mmc_poll_for_busy(host, 1000, &__mmc_send_op_cond_cb, &cb_data); + err = __mmc_poll_for_busy(host, MMC_OP_COND_PERIOD_US, + MMC_OP_COND_TIMEOUT_MS, + &__mmc_send_op_cond_cb, &cb_data); if (err) return err; @@ -495,13 +499,14 @@ static int mmc_busy_cb(void *cb_data, bool *busy) return 0; } -int __mmc_poll_for_busy(struct mmc_host *host, unsigned int timeout_ms, +int __mmc_poll_for_busy(struct mmc_host *host, unsigned int period_us, + unsigned int timeout_ms, int (*busy_cb)(void *cb_data, bool *busy), void *cb_data) { int err; unsigned long timeout; - unsigned int udelay = 32, udelay_max = 32768; + unsigned int udelay = period_us ? period_us : 32, udelay_max = 32768; bool expired = false; bool busy = false; @@ -546,7 +551,7 @@ int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms, cb_data.retry_crc_err = retry_crc_err; cb_data.busy_cmd = busy_cmd; - return __mmc_poll_for_busy(host, timeout_ms, &mmc_busy_cb, &cb_data); + return __mmc_poll_for_busy(host, 0, timeout_ms, &mmc_busy_cb, &cb_data); } EXPORT_SYMBOL_GPL(mmc_poll_for_busy); diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h index 9c813b851d0b..09ffbc00908b 100644 --- a/drivers/mmc/core/mmc_ops.h +++ b/drivers/mmc/core/mmc_ops.h @@ -41,7 +41,8 @@ int mmc_can_ext_csd(struct mmc_card *card); int mmc_switch_status(struct mmc_card *card, bool crc_err_fatal); bool mmc_prepare_busy_cmd(struct mmc_host *host, struct mmc_command *cmd, unsigned int timeout_ms); -int __mmc_poll_for_busy(struct mmc_host *host, unsigned int timeout_ms, +int __mmc_poll_for_busy(struct mmc_host *host, unsigned int period_us, + unsigned int timeout_ms, int (*busy_cb)(void *cb_data, bool *busy), void *cb_data); int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms, diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index bd87012c220c..bfbfed30dc4d 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -1672,7 +1672,7 @@ static int sd_poweroff_notify(struct mmc_card *card) cb_data.card = card; cb_data.reg_buf = reg_buf; - err = __mmc_poll_for_busy(card->host, SD_POWEROFF_NOTIFY_TIMEOUT_MS, + err = __mmc_poll_for_busy(card->host, 0, SD_POWEROFF_NOTIFY_TIMEOUT_MS, &sd_busy_poweroff_notify_cb, &cb_data); out: -- cgit v1.2.3 From 804f468853179b9b58af05c153c411931aa5b310 Mon Sep 17 00:00:00 2001 From: Jouni Högander Date: Fri, 25 Feb 2022 09:02:28 +0200 Subject: drm/i915/psr: Set "SF Partial Frame Enable" also on full update Currently we are observing occasional screen flickering when PSR2 selective fetch is enabled. More specifically glitch seems to happen on full frame update when cursor moves to coords x = -1 or y = -1. According to Bspec SF Single full frame should not be set if SF Partial Frame Enable is not set. This happened to be true for ADLP as PSR2_MAN_TRK_CTL_ENABLE is always set and for ADL_P it's actually "SF Partial Frame Enable" (Bit 31). Setting "SF Partial Frame Enable" bit also on full update seems to fix screen flickering. Also make code more clear by setting PSR2_MAN_TRK_CTL_ENABLE only if not on ADL_P. Bit 31 has different meaning in ADL_P. Bspec: 49274 v2: Fix Mihai Harpau email address v3: Modify commit message and remove unnecessary comment Tested-by: Lyude Paul Fixes: 7f6002e58025 ("drm/i915/display: Enable PSR2 selective fetch by default") Reported-by: Lyude Paul Cc: Mihai Harpau Cc: José Roberto de Souza Cc: Ville Syrjälä Bugzilla: https://gitlab.freedesktop.org/drm/intel/-/issues/5077 Signed-off-by: Jouni Högander Reviewed-by: José Roberto de Souza Signed-off-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20220225070228.855138-1-jouni.hogander@intel.com (cherry picked from commit 8d5516d18b323cf7274d1cf5fe76f4a691f879c6) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_psr.c | 16 ++++++++++++++-- drivers/gpu/drm/i915/i915_reg.h | 1 + 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index a1a663f362e7..00279e8c2775 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1406,6 +1406,13 @@ static inline u32 man_trk_ctl_single_full_frame_bit_get(struct drm_i915_private PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME; } +static inline u32 man_trk_ctl_partial_frame_bit_get(struct drm_i915_private *dev_priv) +{ + return IS_ALDERLAKE_P(dev_priv) ? + ADLP_PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE : + PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE; +} + static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -1510,7 +1517,13 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - u32 val = PSR2_MAN_TRK_CTL_ENABLE; + u32 val = 0; + + if (!IS_ALDERLAKE_P(dev_priv)) + val = PSR2_MAN_TRK_CTL_ENABLE; + + /* SF partial frame enable has to be set even on full update */ + val |= man_trk_ctl_partial_frame_bit_get(dev_priv); if (full_update) { /* @@ -1530,7 +1543,6 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, } else { drm_WARN_ON(crtc_state->uapi.crtc->dev, clip->y1 % 4 || clip->y2 % 4); - val |= PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE; val |= PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1 / 4 + 1); val |= PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2 / 4 + 1); } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index c2bb33febb68..902e4c802a12 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4829,6 +4829,7 @@ enum { #define ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(val) REG_FIELD_PREP(ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK, val) #define ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK REG_GENMASK(12, 0) #define ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(val) REG_FIELD_PREP(ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK, val) +#define ADLP_PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE REG_BIT(31) #define ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME REG_BIT(14) #define ADLP_PSR2_MAN_TRK_CTL_SF_CONTINUOS_FULL_FRAME REG_BIT(13) -- cgit v1.2.3 From 9470c29faa91c804aa04de4c10634bf02462bfa5 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Mon, 28 Feb 2022 19:14:36 +0100 Subject: drm/sun4i: mixer: Fix P010 and P210 format numbers It turns out that DE3 manual has inverted YUV and YVU format numbers for P010 and P210. Invert them. This was tested by playing video decoded to P010 and additionally confirmed by looking at BSP driver source. Fixes: 169ca4b38932 ("drm/sun4i: Add separate DE3 VI layer formats") Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20220228181436.1424550-1-jernej.skrabec@gmail.com --- drivers/gpu/drm/sun4i/sun8i_mixer.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h index 145833a9d82d..5b3fbee18671 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.h +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h @@ -111,10 +111,10 @@ /* format 13 is semi-planar YUV411 VUVU */ #define SUN8I_MIXER_FBFMT_YUV411 14 /* format 15 doesn't exist */ -/* format 16 is P010 YVU */ -#define SUN8I_MIXER_FBFMT_P010_YUV 17 -/* format 18 is P210 YVU */ -#define SUN8I_MIXER_FBFMT_P210_YUV 19 +#define SUN8I_MIXER_FBFMT_P010_YUV 16 +/* format 17 is P010 YVU */ +#define SUN8I_MIXER_FBFMT_P210_YUV 18 +/* format 19 is P210 YVU */ /* format 20 is packed YVU444 10-bit */ /* format 21 is packed YUV444 10-bit */ -- cgit v1.2.3 From a82c25c366b0963d33ddf699196e6cf57f6d89b1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Mar 2022 13:52:11 +0100 Subject: Revert "netfilter: nat: force port remap to prevent shadowing well-known ports" This reverts commit 878aed8db324bec64f3c3f956e64d5ae7375a5de. This change breaks existing setups where conntrack is used with asymmetric paths. In these cases, the NAT transformation occurs on the syn-ack instead of the syn: 1. SYN x:12345 -> y -> 443 // sent by initiator, receiverd by responder 2. SYNACK y:443 -> x:12345 // First packet seen by conntrack, as sent by responder 3. tuple_force_port_remap() gets called, sees: 'tcp from 443 to port 12345 NAT' -> pick a new source port, inititor receives 4. SYNACK y:$RANDOM -> x:12345 // connection is never established While its possible to avoid the breakage with NOTRACK rules, a kernel update should not break working setups. An alternative to the revert is to augment conntrack to tag mid-stream connections plus more code in the nat core to skip NAT for such connections, however, this leads to more interaction/integration between conntrack and NAT. Therefore, revert, users will need to add explicit nat rules to avoid port shadowing. Link: https://lore.kernel.org/netfilter-devel/20220302105908.GA5852@breakpoint.cc/#R Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2051413 Signed-off-by: Florian Westphal --- net/netfilter/nf_nat_core.c | 43 ++-------------------------- tools/testing/selftests/netfilter/nft_nat.sh | 5 ++-- 2 files changed, 5 insertions(+), 43 deletions(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 2d06a66899b2..ffcf6529afc3 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -494,38 +494,6 @@ another_round: goto another_round; } -static bool tuple_force_port_remap(const struct nf_conntrack_tuple *tuple) -{ - u16 sp, dp; - - switch (tuple->dst.protonum) { - case IPPROTO_TCP: - sp = ntohs(tuple->src.u.tcp.port); - dp = ntohs(tuple->dst.u.tcp.port); - break; - case IPPROTO_UDP: - case IPPROTO_UDPLITE: - sp = ntohs(tuple->src.u.udp.port); - dp = ntohs(tuple->dst.u.udp.port); - break; - default: - return false; - } - - /* IANA: System port range: 1-1023, - * user port range: 1024-49151, - * private port range: 49152-65535. - * - * Linux default ephemeral port range is 32768-60999. - * - * Enforce port remapping if sport is significantly lower - * than dport to prevent NAT port shadowing, i.e. - * accidental match of 'new' inbound connection vs. - * existing outbound one. - */ - return sp < 16384 && dp >= 32768; -} - /* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING, * we change the source to map into the range. For NF_INET_PRE_ROUTING * and NF_INET_LOCAL_OUT, we change the destination to map into the @@ -539,17 +507,11 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, struct nf_conn *ct, enum nf_nat_manip_type maniptype) { - bool random_port = range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL; const struct nf_conntrack_zone *zone; struct net *net = nf_ct_net(ct); zone = nf_ct_zone(ct); - if (maniptype == NF_NAT_MANIP_SRC && - !random_port && - !ct->local_origin) - random_port = tuple_force_port_remap(orig_tuple); - /* 1) If this srcip/proto/src-proto-part is currently mapped, * and that same mapping gives a unique tuple within the given * range, use that. @@ -558,7 +520,8 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, * So far, we don't do local source mappings, so multiple * manips not an issue. */ - if (maniptype == NF_NAT_MANIP_SRC && !random_port) { + if (maniptype == NF_NAT_MANIP_SRC && + !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { /* try the original tuple first */ if (in_range(orig_tuple, range)) { if (!nf_nat_used_tuple(orig_tuple, ct)) { @@ -582,7 +545,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, */ /* Only bother mapping if it's not already in range and unique */ - if (!random_port) { + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) && l4proto_in_range(tuple, maniptype, diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 79fe627b9e81..eb8543b9a5c4 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -880,9 +880,8 @@ EOF return $ksft_skip fi - # test default behaviour. Packet from ns1 to ns0 is not redirected - # due to automatic port translation. - test_port_shadow "default" "ROUTER" + # test default behaviour. Packet from ns1 to ns0 is redirected to ns2. + test_port_shadow "default" "CLIENT" # test packet filter based mitigation: prevent forwarding of # packets claiming to come from the service port. -- cgit v1.2.3 From 5adf349439d29f92467e864f728dfc23180f3ef9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 3 Mar 2022 12:23:23 +0100 Subject: x86/module: Fix the paravirt vs alternative order Ever since commit 4e6292114c74 ("x86/paravirt: Add new features for paravirt patching") there is an ordering dependency between patching paravirt ops and patching alternatives, the module loader still violates this. Fixes: 4e6292114c74 ("x86/paravirt: Add new features for paravirt patching") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Reviewed-by: Miroslav Benes Cc: Link: https://lore.kernel.org/r/20220303112825.068773913@infradead.org --- arch/x86/kernel/module.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 95fa745e310a..96d7c27b7093 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -273,6 +273,14 @@ int module_finalize(const Elf_Ehdr *hdr, retpolines = s; } + /* + * See alternative_instructions() for the ordering rules between the + * various patching types. + */ + if (para) { + void *pseg = (void *)para->sh_addr; + apply_paravirt(pseg, pseg + para->sh_size); + } if (retpolines) { void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); @@ -290,11 +298,6 @@ int module_finalize(const Elf_Ehdr *hdr, tseg, tseg + text->sh_size); } - if (para) { - void *pseg = (void *)para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } - /* make jump label nops */ jump_label_apply_nops(me); -- cgit v1.2.3 From ee0a4dc9f317fb9a97f20037d219802ca8de939b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Mar 2022 17:28:38 +0100 Subject: Revert "netfilter: conntrack: tag conntracks picked up in local out hook" This was a prerequisite for the ill-fated "netfilter: nat: force port remap to prevent shadowing well-known ports". As this has been reverted, this change can be backed out too. Signed-off-by: Florian Westphal --- include/net/netfilter/nf_conntrack.h | 1 - net/netfilter/nf_conntrack_core.c | 3 --- 2 files changed, 4 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 8731d5bcb47d..b08b70989d2c 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -97,7 +97,6 @@ struct nf_conn { unsigned long status; u16 cpu; - u16 local_origin:1; possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d6aa5b47031e..bf1e17c678f1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1748,9 +1748,6 @@ resolve_normal_ct(struct nf_conn *tmpl, return 0; if (IS_ERR(h)) return PTR_ERR(h); - - ct = nf_ct_tuplehash_to_ctrack(h); - ct->local_origin = state->hook == NF_INET_LOCAL_OUT; } ct = nf_ct_tuplehash_to_ctrack(h); -- cgit v1.2.3 From 7228918b34615ef6317edcd9a058a057bc54aa32 Mon Sep 17 00:00:00 2001 From: Ross Philipson Date: Wed, 23 Feb 2022 21:07:35 -0500 Subject: x86/boot: Fix memremap of setup_indirect structures As documented, the setup_indirect structure is nested inside the setup_data structures in the setup_data list. The code currently accesses the fields inside the setup_indirect structure but only the sizeof(struct setup_data) is being memremapped. No crash occurred but this is just due to how the area is remapped under the covers. Properly memremap both the setup_data and setup_indirect structures in these cases before accessing them. Fixes: b3c72fc9a78e ("x86/boot: Introduce setup_indirect") Signed-off-by: Ross Philipson Signed-off-by: Borislav Petkov Reviewed-by: Daniel Kiper Cc: Link: https://lore.kernel.org/r/1645668456-22036-2-git-send-email-ross.philipson@oracle.com --- arch/x86/kernel/e820.c | 41 +++++++++++++++++------- arch/x86/kernel/kdebugfs.c | 37 ++++++++++++++++------ arch/x86/kernel/ksysfs.c | 77 ++++++++++++++++++++++++++++++++++++---------- arch/x86/kernel/setup.c | 34 +++++++++++++++----- arch/x86/mm/ioremap.c | 24 ++++++++++++--- 5 files changed, 166 insertions(+), 47 deletions(-) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index bc0657f0deed..f267205f2d5a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -995,8 +995,10 @@ early_param("memmap", parse_memmap_opt); */ void __init e820__reserve_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; if (!pa_data) @@ -1004,6 +1006,14 @@ void __init e820__reserve_setup_data(void) while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("e820: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* @@ -1015,18 +1025,27 @@ void __init e820__reserve_setup_data(void) sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - e820__range_update(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("e820: failed to memremap indirect setup_data\n"); + return; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + e820__range_update(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + e820__range_update_kexec(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + } } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + pa_data = pa_next; + early_memunmap(data, len); } e820__update_table(e820_table); diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 64b6da95af98..e2e89bebcbc3 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -88,11 +88,13 @@ create_setup_data_node(struct dentry *parent, int no, static int __init create_setup_data_nodes(struct dentry *parent) { + struct setup_indirect *indirect; struct setup_data_node *node; struct setup_data *data; - int error; + u64 pa_data, pa_next; struct dentry *d; - u64 pa_data; + int error; + u32 len; int no = 0; d = debugfs_create_dir("setup_data", parent); @@ -112,12 +114,29 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = -ENOMEM; goto err_dir; } - - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - node->paddr = ((struct setup_indirect *)data->data)->addr; - node->type = ((struct setup_indirect *)data->data)->type; - node->len = ((struct setup_indirect *)data->data)->len; + pa_next = data->next; + + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) { + kfree(node); + error = -ENOMEM; + goto err_dir; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + node->paddr = indirect->addr; + node->type = indirect->type; + node->len = indirect->len; + } else { + node->paddr = pa_data; + node->type = data->type; + node->len = data->len; + } } else { node->paddr = pa_data; node->type = data->type; @@ -125,7 +144,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) } create_setup_data_node(d, no, node); - pa_data = data->next; + pa_data = pa_next; memunmap(data); no++; diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index d0a19121c6a4..257892fcefa7 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -91,26 +91,41 @@ static int get_setup_data_paddr(int nr, u64 *paddr) static int __init get_setup_data_size(int nr, size_t *size) { - int i = 0; + u64 pa_data = boot_params.hdr.setup_data, pa_next; + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data = boot_params.hdr.setup_data; + int i = 0; + u32 len; while (pa_data) { data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; + pa_next = data->next; + if (nr == i) { - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - *size = ((struct setup_indirect *)data->data)->len; - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + *size = indirect->len; + else + *size = data->len; + } else { *size = data->len; + } memunmap(data); return 0; } - pa_data = data->next; + pa_data = pa_next; memunmap(data); i++; } @@ -120,9 +135,11 @@ static int __init get_setup_data_size(int nr, size_t *size) static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret; u64 paddr; - struct setup_data *data; + u32 len; ret = kobj_to_setup_data_nr(kobj, &nr); if (ret) @@ -135,10 +152,20 @@ static ssize_t type_show(struct kobject *kobj, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT) - ret = sprintf(buf, "0x%x\n", ((struct setup_indirect *)data->data)->type); - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + ret = sprintf(buf, "0x%x\n", indirect->type); + } else { ret = sprintf(buf, "0x%x\n", data->type); + } + memunmap(data); return ret; } @@ -149,9 +176,10 @@ static ssize_t setup_data_data_read(struct file *fp, char *buf, loff_t off, size_t count) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret = 0; u64 paddr, len; - struct setup_data *data; void *p; ret = kobj_to_setup_data_nr(kobj, &nr); @@ -165,10 +193,27 @@ static ssize_t setup_data_data_read(struct file *fp, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } else { + /* + * Even though this is technically undefined, return + * the data as though it is a normal setup_data struct. + * This will at least allow it to be inspected. + */ + paddr += sizeof(*data); + len = data->len; + } } else { paddr += sizeof(*data); len = data->len; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f7a132eb794d..90d7e1788c91 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -369,21 +369,41 @@ static void __init parse_setup_data(void) static void __init memblock_x86_reserve_range_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("setup: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + memblock_reserve(pa_data, sizeof(*data) + data->len); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - memblock_reserve(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("setup: failed to memremap indirect setup_data\n"); + return; + } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + memblock_reserve(indirect->addr, indirect->len); + } + + pa_data = pa_next; + early_memunmap(data, len); } } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 026031b3b782..ab666c4cd357 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -615,6 +615,7 @@ static bool memremap_is_efi_data(resource_size_t phys_addr, static bool memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; @@ -627,6 +628,10 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, data = memremap(paddr, sizeof(*data), MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap setup_data entry\n"); + return false; + } paddr_next = data->next; len = data->len; @@ -636,10 +641,21 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, return true; } - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + memunmap(data); + data = memremap(paddr, sizeof(*data) + len, + MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } } memunmap(data); -- cgit v1.2.3 From 445c1470b6ef96440e7cfc42dfc160f5004fd149 Mon Sep 17 00:00:00 2001 From: Ross Philipson Date: Wed, 23 Feb 2022 21:07:36 -0500 Subject: x86/boot: Add setup_indirect support in early_memremap_is_setup_data() The x86 boot documentation describes the setup_indirect structures and how they are used. Only one of the two functions in ioremap.c that needed to be modified to be aware of the introduction of setup_indirect functionality was updated. Adds comparable support to the other function where it was missing. Fixes: b3c72fc9a78e ("x86/boot: Introduce setup_indirect") Signed-off-by: Ross Philipson Signed-off-by: Borislav Petkov Reviewed-by: Daniel Kiper Cc: Link: https://lore.kernel.org/r/1645668456-22036-3-git-send-email-ross.philipson@oracle.com --- arch/x86/mm/ioremap.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index ab666c4cd357..17a492c27306 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -676,22 +676,51 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; paddr = boot_params.hdr.setup_data; while (paddr) { - unsigned int len; + unsigned int len, size; if (phys_addr == paddr) return true; data = early_memremap_decrypted(paddr, sizeof(*data)); + if (!data) { + pr_warn("failed to early memremap setup_data entry\n"); + return false; + } + + size = sizeof(*data); paddr_next = data->next; len = data->len; - early_memunmap(data, sizeof(*data)); + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) { + early_memunmap(data, sizeof(*data)); + return true; + } + + if (data->type == SETUP_INDIRECT) { + size += len; + early_memunmap(data, sizeof(*data)); + data = early_memremap_decrypted(paddr, size); + if (!data) { + pr_warn("failed to early memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } + } + + early_memunmap(data, size); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) return true; -- cgit v1.2.3 From f0cfe17bcc1dd2f0872966b554a148e888833ee9 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Wed, 9 Mar 2022 14:13:02 +0100 Subject: tracing/osnoise: Do not unregister events twice Nicolas reported that using: # trace-cmd record -e all -M 10 -p osnoise --poll Resulted in the following kernel warning: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1217 at kernel/tracepoint.c:404 tracepoint_probe_unregister+0x280/0x370 [...] CPU: 0 PID: 1217 Comm: trace-cmd Not tainted 5.17.0-rc6-next-20220307-nico+ #19 RIP: 0010:tracepoint_probe_unregister+0x280/0x370 [...] CR2: 00007ff919b29497 CR3: 0000000109da4005 CR4: 0000000000170ef0 Call Trace: osnoise_workload_stop+0x36/0x90 tracing_set_tracer+0x108/0x260 tracing_set_trace_write+0x94/0xd0 ? __check_object_size.part.0+0x10a/0x150 ? selinux_file_permission+0x104/0x150 vfs_write+0xb5/0x290 ksys_write+0x5f/0xe0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7ff919a18127 [...] ---[ end trace 0000000000000000 ]--- The warning complains about an attempt to unregister an unregistered tracepoint. This happens on trace-cmd because it first stops tracing, and then switches the tracer to nop. Which is equivalent to: # cd /sys/kernel/tracing/ # echo osnoise > current_tracer # echo 0 > tracing_on # echo nop > current_tracer The osnoise tracer stops the workload when no trace instance is actually collecting data. This can be caused both by disabling tracing or disabling the tracer itself. To avoid unregistering events twice, use the existing trace_osnoise_callback_enabled variable to check if the events (and the workload) are actually active before trying to deactivate them. Link: https://lore.kernel.org/all/c898d1911f7f9303b7e14726e7cc9678fbfb4a0e.camel@redhat.com/ Link: https://lkml.kernel.org/r/938765e17d5a781c2df429a98f0b2e7cc317b022.1646823913.git.bristot@kernel.org Cc: stable@vger.kernel.org Cc: Marcelo Tosatti Fixes: 2fac8d6486d5 ("tracing/osnoise: Allow multiple instances of the same tracer") Reported-by: Nicolas Saenz Julienne Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_osnoise.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index cfddb30e65ab..2aa3efdca755 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -2200,6 +2200,17 @@ static void osnoise_workload_stop(void) if (osnoise_has_registered_instances()) return; + /* + * If callbacks were already disabled in a previous stop + * call, there is no need to disable then again. + * + * For instance, this happens when tracing is stopped via: + * echo 0 > tracing_on + * echo nop > current_tracer. + */ + if (!trace_osnoise_callback_enabled) + return; + trace_osnoise_callback_enabled = false; /* * Make sure that ftrace_nmi_enter/exit() see -- cgit v1.2.3 From caf4c86bf136845982c5103b2661751b40c474c0 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Mon, 7 Mar 2022 19:07:40 +0100 Subject: tracing/osnoise: Force quiescent states while tracing At the moment running osnoise on a nohz_full CPU or uncontested FIFO priority and a PREEMPT_RCU kernel might have the side effect of extending grace periods too much. This will entice RCU to force a context switch on the wayward CPU to end the grace period, all while introducing unwarranted noise into the tracer. This behaviour is unavoidable as overly extending grace periods might exhaust the system's memory. This same exact problem is what extended quiescent states (EQS) were created for, conversely, rcu_momentary_dyntick_idle() emulates them by performing a zero duration EQS. So let's make use of it. In the common case rcu_momentary_dyntick_idle() is fairly inexpensive: atomically incrementing a local per-CPU counter and doing a store. So it shouldn't affect osnoise's measurements (which has a 1us granularity), so we'll call it unanimously. The uncommon case involve calling rcu_momentary_dyntick_idle() after having the osnoise process: - Receive an expedited quiescent state IPI with preemption disabled or during an RCU critical section. (activates rdp->cpu_no_qs.b.exp code-path). - Being preempted within in an RCU critical section and having the subsequent outermost rcu_read_unlock() called with interrupts disabled. (t->rcu_read_unlock_special.b.blocked code-path). Neither of those are possible at the moment, and are unlikely to be in the future given the osnoise's loop design. On top of this, the noise generated by the situations described above is unavoidable, and if not exposed by rcu_momentary_dyntick_idle() will be eventually seen in subsequent rcu_read_unlock() calls or schedule operations. Link: https://lkml.kernel.org/r/20220307180740.577607-1-nsaenzju@redhat.com Cc: stable@vger.kernel.org Fixes: bce29ac9ce0b ("trace: Add osnoise tracer") Signed-off-by: Nicolas Saenz Julienne Acked-by: Paul E. McKenney Acked-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_osnoise.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 2aa3efdca755..5e3c62a08fc0 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1386,6 +1386,26 @@ static int run_osnoise(void) osnoise_stop_tracing(); } + /* + * In some cases, notably when running on a nohz_full CPU with + * a stopped tick PREEMPT_RCU has no way to account for QSs. + * This will eventually cause unwarranted noise as PREEMPT_RCU + * will force preemption as the means of ending the current + * grace period. We avoid this problem by calling + * rcu_momentary_dyntick_idle(), which performs a zero duration + * EQS allowing PREEMPT_RCU to end the current grace period. + * This call shouldn't be wrapped inside an RCU critical + * section. + * + * Note that in non PREEMPT_RCU kernels QSs are handled through + * cond_resched() + */ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) { + local_irq_disable(); + rcu_momentary_dyntick_idle(); + local_irq_enable(); + } + /* * For the non-preemptive kernel config: let threads runs, if * they so wish. -- cgit v1.2.3 From 78cbc6513217b00be6a9904415ef7ff3619eb035 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Mon, 7 Mar 2022 08:43:03 +0800 Subject: ftrace: Fix some W=1 warnings in kernel doc comments Clean up the following clang-w1 warning: kernel/trace/ftrace.c:7827: warning: Function parameter or member 'ops' not described in 'unregister_ftrace_function'. kernel/trace/ftrace.c:7805: warning: Function parameter or member 'ops' not described in 'register_ftrace_function'. Link: https://lkml.kernel.org/r/20220307004303.26399-1-jiapeng.chong@linux.alibaba.com Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a4b462b6f944..6105b7036482 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7790,7 +7790,7 @@ int ftrace_is_dead(void) /** * register_ftrace_function - register a function for profiling - * @ops - ops structure that holds the function for profiling. + * @ops: ops structure that holds the function for profiling. * * Register a function to be called by all functions in the * kernel. @@ -7817,7 +7817,7 @@ EXPORT_SYMBOL_GPL(register_ftrace_function); /** * unregister_ftrace_function - unregister a function for profiling. - * @ops - ops structure that holds the function to unregister + * @ops: ops structure that holds the function to unregister * * Unregister a function that was added to be called by ftrace profiling. */ -- cgit v1.2.3 From 9a564bccb78a76740ea9d75a259942df8143d02c Mon Sep 17 00:00:00 2001 From: Haimin Zhang Date: Tue, 8 Mar 2022 11:20:28 +0800 Subject: af_key: add __GFP_ZERO flag for compose_sadb_supported in function pfkey_register Add __GFP_ZERO flag for compose_sadb_supported in function pfkey_register to initialize the buffer of supp_skb to fix a kernel-info-leak issue. 1) Function pfkey_register calls compose_sadb_supported to request a sk_buff. 2) compose_sadb_supported calls alloc_sbk to allocate a sk_buff, but it doesn't zero it. 3) If auth_len is greater 0, then compose_sadb_supported treats the memory as a struct sadb_supported and begins to initialize. But it just initializes the field sadb_supported_len and field sadb_supported_exttype without field sadb_supported_reserved. Reported-by: TCS Robot Signed-off-by: Haimin Zhang Signed-off-by: Steffen Klassert --- net/key/af_key.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/key/af_key.c b/net/key/af_key.c index 9bf52a09b5ff..fd51db3be91c 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1699,7 +1699,7 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad xfrm_probe_algs(); - supp_skb = compose_sadb_supported(hdr, GFP_KERNEL); + supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<sadb_msg_satype); -- cgit v1.2.3 From 95932ab2ea07b79cdb33121e2f40ccda9e6a73b5 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 10 Mar 2022 15:52:11 +0800 Subject: vhost: allow batching hint without size Commit e2ae38cf3d91 ("vhost: fix hung thread due to erroneous iotlb entries") tries to reject the IOTLB message whose size is zero. But the size is not necessarily meaningful, one example is the batching hint, so the commit breaks that. Fixing this be reject zero size message only if the message is used to update/invalidate the IOTLB. Fixes: e2ae38cf3d91 ("vhost: fix hung thread due to erroneous iotlb entries") Reported-by: Eli Cohen Cc: Anirudh Rayabharam Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20220310075211.4801-1-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin Tested-by: Eli Cohen --- drivers/vhost/vhost.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 082380c03a3e..1768362115c6 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1170,7 +1170,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, goto done; } - if (msg.size == 0) { + if ((msg.type == VHOST_IOTLB_UPDATE || + msg.type == VHOST_IOTLB_INVALIDATE) && + msg.size == 0) { ret = -EINVAL; goto done; } -- cgit v1.2.3 From c80ee64a8020ef1a6a92109798080786829b8994 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 11 Feb 2022 00:49:43 +0800 Subject: riscv: alternative only works on !XIP_KERNEL The alternative mechanism needs runtime code patching, it can't work on XIP_KERNEL. And the errata workarounds are implemented via the alternative mechanism. So add !XIP_KERNEL dependency for alternative and erratas. Signed-off-by: Jisheng Zhang Fixes: 44c922572952 ("RISC-V: enable XIP") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig.erratas | 1 + arch/riscv/Kconfig.socs | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.erratas index b44d6ecdb46e..0aacd7052585 100644 --- a/arch/riscv/Kconfig.erratas +++ b/arch/riscv/Kconfig.erratas @@ -2,6 +2,7 @@ menu "CPU errata selection" config RISCV_ERRATA_ALTERNATIVE bool "RISC-V alternative scheme" + depends on !XIP_KERNEL default y help This Kconfig allows the kernel to automatically patch the diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6ec44a22278a..c112ab2a9052 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -14,8 +14,8 @@ config SOC_SIFIVE select CLK_SIFIVE select CLK_SIFIVE_PRCI select SIFIVE_PLIC - select RISCV_ERRATA_ALTERNATIVE - select ERRATA_SIFIVE + select RISCV_ERRATA_ALTERNATIVE if !XIP_KERNEL + select ERRATA_SIFIVE if !XIP_KERNEL help This enables support for SiFive SoC platform hardware. -- cgit v1.2.3 From 0966d385830de3470b7131db8e86c0c5bc9c52dc Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Wed, 23 Feb 2022 20:12:57 +0100 Subject: riscv: Fix auipc+jalr relocation range checks RISC-V can do PC-relative jumps with a 32bit range using the following two instructions: auipc t0, imm20 ; t0 = PC + imm20 * 2^12 jalr ra, t0, imm12 ; ra = PC + 4, PC = t0 + imm12 Crucially both the 20bit immediate imm20 and the 12bit immediate imm12 are treated as two's-complement signed values. For this reason the immediates are usually calculated like this: imm20 = (offset + 0x800) >> 12 imm12 = offset & 0xfff ..where offset is the signed offset from the auipc instruction. When the 11th bit of offset is 0 the addition of 0x800 doesn't change the top 20 bits and imm12 considered positive. When the 11th bit is 1 the carry of the addition by 0x800 means imm20 is one higher, but since imm12 is then considered negative the two's complement representation means it all cancels out nicely. However, this addition by 0x800 (2^11) means an offset greater than or equal to 2^31 - 2^11 would overflow so imm20 is considered negative and result in a backwards jump. Similarly the lower range of offset is also moved down by 2^11 and hence the true 32bit range is [-2^31 - 2^11, 2^31 - 2^11) Signed-off-by: Emil Renner Berthing Fixes: e2c0cdfba7f6 ("RISC-V: User-facing API") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/module.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 68a9e3d1fe16..4a48287513c3 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -13,6 +13,19 @@ #include #include +/* + * The auipc+jalr instruction pair can reach any PC-relative offset + * in the range [-2^31 - 2^11, 2^31 - 2^11) + */ +static bool riscv_insn_valid_32bit_offset(ptrdiff_t val) +{ +#ifdef CONFIG_32BIT + return true; +#else + return (-(1L << 31) - (1L << 11)) <= val && val < ((1L << 31) - (1L << 11)); +#endif +} + static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v) { if (v != (u32)v) { @@ -95,7 +108,7 @@ static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location, ptrdiff_t offset = (void *)v - (void *)location; s32 hi20; - if (offset != (s32)offset) { + if (!riscv_insn_valid_32bit_offset(offset)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", me->name, (long long)v, location); @@ -197,10 +210,9 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location, Elf_Addr v) { ptrdiff_t offset = (void *)v - (void *)location; - s32 fill_v = offset; u32 hi20, lo12; - if (offset != fill_v) { + if (!riscv_insn_valid_32bit_offset(offset)) { /* Only emit the plt entry if offset over 32-bit range */ if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { offset = module_emit_plt_entry(me, v); @@ -224,10 +236,9 @@ static int apply_r_riscv_call_rela(struct module *me, u32 *location, Elf_Addr v) { ptrdiff_t offset = (void *)v - (void *)location; - s32 fill_v = offset; u32 hi20, lo12; - if (offset != fill_v) { + if (!riscv_insn_valid_32bit_offset(offset)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", me->name, (long long)v, location); -- cgit v1.2.3 From c993ee0f9f81caf5767a50d1faeba39a0dc82af2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:23:31 +0000 Subject: watch_queue: Fix filter limit check In watch_queue_set_filter(), there are a couple of places where we check that the filter type value does not exceed what the type_filter bitmap can hold. One place calculates the number of bits by: if (tf[i].type >= sizeof(wfilter->type_filter) * 8) which is fine, but the second does: if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG) which is not. This can lead to a couple of out-of-bounds writes due to a too-large type: (1) __set_bit() on wfilter->type_filter (2) Writing more elements in wfilter->filters[] than we allocated. Fix this by just using the proper WATCH_TYPE__NR instead, which is the number of types we actually know about. The bug may cause an oops looking something like: BUG: KASAN: slab-out-of-bounds in watch_queue_set_filter+0x659/0x740 Write of size 4 at addr ffff88800d2c66bc by task watch_queue_oob/611 ... Call Trace: dump_stack_lvl+0x45/0x59 print_address_description.constprop.0+0x1f/0x150 ... kasan_report.cold+0x7f/0x11b ... watch_queue_set_filter+0x659/0x740 ... __x64_sys_ioctl+0x127/0x190 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae Allocated by task 611: kasan_save_stack+0x1e/0x40 __kasan_kmalloc+0x81/0xa0 watch_queue_set_filter+0x23a/0x740 __x64_sys_ioctl+0x127/0x190 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88800d2c66a0 which belongs to the cache kmalloc-32 of size 32 The buggy address is located 28 bytes inside of 32-byte region [ffff88800d2c66a0, ffff88800d2c66c0) Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/watch_queue.h | 3 ++- kernel/watch_queue.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index c994d1b2cdba..3b9a40ae8bdb 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -28,7 +28,8 @@ struct watch_type_filter { struct watch_filter { union { struct rcu_head rcu; - unsigned long type_filter[2]; /* Bitmask of accepted types */ + /* Bitmask of accepted types */ + DECLARE_BITMAP(type_filter, WATCH_TYPE__NR); }; u32 nr_filters; /* Number of filters */ struct watch_type_filter filters[]; diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 9c9eb20dd2c5..427b0318e303 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -320,7 +320,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, tf[i].info_mask & WATCH_INFO_LENGTH) goto err_filter; /* Ignore any unknown types */ - if (tf[i].type >= sizeof(wfilter->type_filter) * 8) + if (tf[i].type >= WATCH_TYPE__NR) continue; nr_filter++; } @@ -336,7 +336,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, q = wfilter->filters; for (i = 0; i < filter.nr_filters; i++) { - if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG) + if (tf[i].type >= WATCH_TYPE__NR) continue; q->type = tf[i].type; -- cgit v1.2.3 From db8facfc9fafacefe8a835416a6b77c838088f8b Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:23:38 +0000 Subject: watch_queue, pipe: Free watchqueue state after clearing pipe ring In free_pipe_info(), free the watchqueue state after clearing the pipe ring as each pipe ring descriptor has a release function, and in the case of a notification message, this is watch_queue_pipe_buf_release() which tries to mark the allocation bitmap that was previously released. Fix this by moving the put of the pipe's ref on the watch queue to after the ring has been cleared. We still need to call watch_queue_clear() before doing that to make sure that the pipe is disconnected from any notification sources first. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- fs/pipe.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index cc28623a67b6..4eb88bc138bb 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -831,10 +831,8 @@ void free_pipe_info(struct pipe_inode_info *pipe) int i; #ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); - put_watch_queue(pipe->watch_queue); - } #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); @@ -844,6 +842,10 @@ void free_pipe_info(struct pipe_inode_info *pipe) if (buf->ops) pipe_buf_release(pipe, buf); } +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) + put_watch_queue(pipe->watch_queue); +#endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); -- cgit v1.2.3 From c1853fbadcba1497f4907971e7107888e0714c81 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:23:46 +0000 Subject: watch_queue: Fix to release page in ->release() When a pipe ring descriptor points to a notification message, the refcount on the backing page is incremented by the generic get function, but the release function, which marks the bitmap, doesn't drop the page ref. Fix this by calling generic_pipe_buf_release() at the end of watch_queue_pipe_buf_release(). Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/watch_queue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 427b0318e303..dfb3a7e28280 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -54,6 +54,7 @@ static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, bit += page->index; set_bit(bit, wqueue->notes_bitmap); + generic_pipe_buf_release(pipe, buf); } // No try_steal function => no stealing -- cgit v1.2.3 From 96a4d8912b28451cd62825fd7caa0e66e091d938 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:24:08 +0000 Subject: watch_queue: Fix to always request a pow-of-2 pipe ring size The pipe ring size must always be a power of 2 as the head and tail pointers are masked off by AND'ing with the size of the ring - 1. watch_queue_set_size(), however, lets you specify any number of notes between 1 and 511. This number is passed through to pipe_resize_ring() without checking/forcing its alignment. Fix this by rounding the number of slots required up to the nearest power of two. The request is meant to guarantee that at least that many notifications can be generated before the queue is full, so rounding down isn't an option, but, alternatively, it may be better to give an error if we aren't allowed to allocate that much ring space. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/watch_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index dfb3a7e28280..4bcd400984a7 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -244,7 +244,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) goto error; } - ret = pipe_resize_ring(pipe, nr_notes); + ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes)); if (ret < 0) goto error; -- cgit v1.2.3 From a66bd7575b5f449ee0ba20cfd21c3bc5b04ef361 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 11 Mar 2022 13:24:15 +0000 Subject: watch_queue: Use the bitmap API when applicable Use bitmap_alloc() to simplify code, improve the semantic and reduce some open-coded arithmetic in allocator arguments. Also change a memset(0xff) into an equivalent bitmap_fill() to keep consistency. Signed-off-by: Christophe JAILLET Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/watch_queue.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 4bcd400984a7..5b516eb2c7cc 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -220,7 +220,6 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) struct page **pages; unsigned long *bitmap; unsigned long user_bufs; - unsigned int bmsize; int ret, i, nr_pages; if (!wqueue) @@ -259,13 +258,11 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE; } - bmsize = (nr_notes + BITS_PER_LONG - 1) / BITS_PER_LONG; - bmsize *= sizeof(unsigned long); - bitmap = kmalloc(bmsize, GFP_KERNEL); + bitmap = bitmap_alloc(nr_notes, GFP_KERNEL); if (!bitmap) goto error_p; - memset(bitmap, 0xff, bmsize); + bitmap_fill(bitmap, nr_notes); wqueue->notes = pages; wqueue->notes_bitmap = bitmap; wqueue->nr_pages = nr_pages; -- cgit v1.2.3 From 3b4c0371928c17af03e8397ac842346624017ce6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:24:22 +0000 Subject: watch_queue: Fix the alloc bitmap size to reflect notes allocated Currently, watch_queue_set_size() sets the number of notes available in wqueue->nr_notes according to the number of notes allocated, but sets the size of the bitmap to the unrounded number of notes originally asked for. Fix this by setting the bitmap size to the number of notes we're actually going to make available (ie. the number allocated). Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/watch_queue.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 5b516eb2c7cc..9c476d2cbac0 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -243,6 +243,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) goto error; } + nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes)); if (ret < 0) goto error; @@ -266,7 +267,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) wqueue->notes = pages; wqueue->notes_bitmap = bitmap; wqueue->nr_pages = nr_pages; - wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; + wqueue->nr_notes = nr_notes; return 0; error_p: -- cgit v1.2.3 From 7ea1a0124b6da246b5bc8c66cddaafd36acf3ecb Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:24:29 +0000 Subject: watch_queue: Free the alloc bitmap when the watch_queue is torn down Free the watch_queue note allocation bitmap when the watch_queue is destroyed. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/watch_queue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 9c476d2cbac0..c12267ccc70e 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -370,6 +370,7 @@ static void __put_watch_queue(struct kref *kref) for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); + bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); if (wfilter) -- cgit v1.2.3 From 2ed147f015af2b48f41c6f0b6746aa9ea85c19f3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:24:36 +0000 Subject: watch_queue: Fix lack of barrier/sync/lock between post and read There's nothing to synchronise post_one_notification() versus pipe_read(). Whilst posting is done under pipe->rd_wait.lock, the reader only takes pipe->mutex which cannot bar notification posting as that may need to be made from contexts that cannot sleep. Fix this by setting pipe->head with a barrier in post_one_notification() and reading pipe->head with a barrier in pipe_read(). If that's not sufficient, the rd_wait.lock will need to be taken, possibly in a ->confirm() op so that it only applies to notifications. The lock would, however, have to be dropped before copy_page_to_iter() is invoked. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- fs/pipe.c | 3 ++- kernel/watch_queue.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index 4eb88bc138bb..2667db9506e2 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -253,7 +253,8 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { - unsigned int head = pipe->head; + /* Read ->head with a barrier vs post_one_notification() */ + unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index c12267ccc70e..37bcd900fd77 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -113,7 +113,7 @@ static bool post_one_notification(struct watch_queue *wqueue, buf->offset = offset; buf->len = len; buf->flags = PIPE_BUF_FLAG_WHOLE; - pipe->head = head + 1; + smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */ if (!test_and_clear_bit(note, wqueue->notes_bitmap)) { spin_unlock_irq(&pipe->rd_wait.lock); -- cgit v1.2.3 From 4edc0760412b0c4ecefc7e02cb855b310b122825 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:24:47 +0000 Subject: watch_queue: Make comment about setting ->defunct more accurate watch_queue_clear() has a comment stating that setting ->defunct to true preventing new additions as well as preventing notifications. Whilst the latter is true, the first bit is superfluous since at the time this function is called, the pipe cannot be accessed to add new event sources. Remove the "new additions" bit from the comment. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/watch_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 37bcd900fd77..00703444a219 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -566,7 +566,7 @@ void watch_queue_clear(struct watch_queue *wqueue) rcu_read_lock(); spin_lock_bh(&wqueue->lock); - /* Prevent new additions and prevent notifications from happening */ + /* Prevent new notifications from being stored. */ wqueue->defunct = true; while (!hlist_empty(&wqueue->watches)) { -- cgit v1.2.3 From a365a65f9ca1ceb9cf1ac29db4a4f51df7c507ad Mon Sep 17 00:00:00 2001 From: Li Huafei Date: Thu, 10 Mar 2022 20:09:15 +0800 Subject: x86/traps: Mark do_int3() NOKPROBE_SYMBOL Since kprobe_int3_handler() is called in do_int3(), probing do_int3() can cause a breakpoint recursion and crash the kernel. Therefore, do_int3() should be marked as NOKPROBE_SYMBOL. Fixes: 21e28290b317 ("x86/traps: Split int3 handler up") Signed-off-by: Li Huafei Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Cc: Link: https://lore.kernel.org/r/20220310120915.63349-1-lihuafei1@huawei.com --- arch/x86/kernel/traps.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c9d566dcf89a..8143693a7ea6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -659,6 +659,7 @@ static bool do_int3(struct pt_regs *regs) return res == NOTIFY_STOP; } +NOKPROBE_SYMBOL(do_int3); static void do_int3_user(struct pt_regs *regs) { -- cgit v1.2.3 From 173ce1ca47c489135b2799f70f550e1319ba36d8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 15:58:21 +0000 Subject: afs: Fix potential thrashing in afs writeback In afs_writepages_region(), if the dirty page we find is undergoing writeback or write to cache, but the sync_mode is WB_SYNC_NONE, we go round the loop trying the same page again and again with no pausing or waiting unless and until another thread manages to clear the writeback and fscache flags. Fix this with three measures: (1) Advance start to after the page we found. (2) Break out of the loop and return if rescheduling is requested. (3) Arbitrarily give up after a maximum of 5 skips. Fixes: 31143d5d515e ("AFS: implement basic file write support") Reported-by: Marc Dionne Signed-off-by: David Howells Tested-by: Marc Dionne Acked-by: Marc Dionne Link: https://lore.kernel.org/r/164692725757.2097000.2060513769492301854.stgit@warthog.procyon.org.uk/ # v1 Signed-off-by: Linus Torvalds --- fs/afs/write.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/afs/write.c b/fs/afs/write.c index 5e9157d0da29..f447c902318d 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -703,7 +703,7 @@ static int afs_writepages_region(struct address_space *mapping, struct folio *folio; struct page *head_page; ssize_t ret; - int n; + int n, skips = 0; _enter("%llx,%llx,", start, end); @@ -754,8 +754,15 @@ static int afs_writepages_region(struct address_space *mapping, #ifdef CONFIG_AFS_FSCACHE folio_wait_fscache(folio); #endif + } else { + start += folio_size(folio); } folio_put(folio); + if (wbc->sync_mode == WB_SYNC_NONE) { + if (skips >= 5 || need_resched()) + break; + skips++; + } continue; } -- cgit v1.2.3 From 413a4a6b0b5553f2423d210f65e98c211b99c3f8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 16:02:18 +0000 Subject: cachefiles: Fix volume coherency attribute A network filesystem may set coherency data on a volume cookie, and if given, cachefiles will store this in an xattr on the directory in the cache corresponding to the volume. The function that sets the xattr just stores the contents of the volume coherency buffer directly into the xattr, with nothing added; the checking function, on the other hand, has a cut'n'paste error whereby it tries to interpret the xattr contents as would be the xattr on an ordinary file (using the cachefiles_xattr struct). This results in a failure to match the coherency data because the buffer ends up being shifted by 18 bytes. Fix this by defining a structure specifically for the volume xattr and making both the setting and checking functions use it. Since the volume coherency doesn't work if used, take the opportunity to insert a reserved field for future use, set it to 0 and check that it is 0. Log mismatch through the appropriate tracepoint. Note that this only affects cifs; 9p, afs, ceph and nfs don't use the volume coherency data at the moment. Fixes: 32e150037dce ("fscache, cachefiles: Store the volume coherency data") Reported-by: Rohith Surabattula Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: Steve French cc: linux-cifs@vger.kernel.org cc: linux-cachefs@redhat.com Signed-off-by: Linus Torvalds --- fs/cachefiles/xattr.c | 23 ++++++++++++++++++++--- include/trace/events/cachefiles.h | 2 ++ 2 files changed, 22 insertions(+), 3 deletions(-) diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 83f41bd0c3a9..35465109d9c4 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -28,6 +28,11 @@ struct cachefiles_xattr { static const char cachefiles_xattr_cache[] = XATTR_USER_PREFIX "CacheFiles.cache"; +struct cachefiles_vol_xattr { + __be32 reserved; /* Reserved, should be 0 */ + __u8 data[]; /* netfs volume coherency data */ +} __packed; + /* * set the state xattr on a cache file */ @@ -185,6 +190,7 @@ void cachefiles_prepare_to_write(struct fscache_cookie *cookie) */ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) { + struct cachefiles_vol_xattr *buf; unsigned int len = volume->vcookie->coherency_len; const void *p = volume->vcookie->coherency; struct dentry *dentry = volume->dentry; @@ -192,10 +198,17 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) _enter("%x,#%d", volume->vcookie->debug_id, len); + len += sizeof(*buf); + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return false; + buf->reserved = cpu_to_be32(0); + memcpy(buf->data, p, len); + ret = cachefiles_inject_write_error(); if (ret == 0) ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, - p, len, 0); + buf, len, 0); if (ret < 0) { trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret, cachefiles_trace_setxattr_error); @@ -209,6 +222,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) cachefiles_coherency_vol_set_ok); } + kfree(buf); _leave(" = %d", ret); return ret == 0; } @@ -218,7 +232,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) */ int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) { - struct cachefiles_xattr *buf; + struct cachefiles_vol_xattr *buf; struct dentry *dentry = volume->dentry; unsigned int len = volume->vcookie->coherency_len; const void *p = volume->vcookie->coherency; @@ -228,6 +242,7 @@ int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) _enter(""); + len += sizeof(*buf); buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -245,7 +260,9 @@ int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) "Failed to read xattr with error %zd", xlen); } why = cachefiles_coherency_vol_check_xattr; - } else if (memcmp(buf->data, p, len) != 0) { + } else if (buf->reserved != cpu_to_be32(0)) { + why = cachefiles_coherency_vol_check_resv; + } else if (memcmp(buf->data, p, len - sizeof(*buf)) != 0) { why = cachefiles_coherency_vol_check_cmp; } else { why = cachefiles_coherency_vol_check_ok; diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index c6f5aa74db89..2c530637e10a 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -56,6 +56,7 @@ enum cachefiles_coherency_trace { cachefiles_coherency_set_ok, cachefiles_coherency_vol_check_cmp, cachefiles_coherency_vol_check_ok, + cachefiles_coherency_vol_check_resv, cachefiles_coherency_vol_check_xattr, cachefiles_coherency_vol_set_fail, cachefiles_coherency_vol_set_ok, @@ -139,6 +140,7 @@ enum cachefiles_error_trace { EM(cachefiles_coherency_set_ok, "SET ok ") \ EM(cachefiles_coherency_vol_check_cmp, "VOL BAD cmp ") \ EM(cachefiles_coherency_vol_check_ok, "VOL OK ") \ + EM(cachefiles_coherency_vol_check_resv, "VOL BAD resv") \ EM(cachefiles_coherency_vol_check_xattr,"VOL BAD xatt") \ EM(cachefiles_coherency_vol_set_fail, "VOL SET fail") \ E_(cachefiles_coherency_vol_set_ok, "VOL SET ok ") -- cgit v1.2.3 From 08999b2489b4c9b939d7483dbd03702ee4576d96 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Fri, 4 Mar 2022 00:38:58 +0200 Subject: x86/sgx: Free backing memory after faulting the enclave page There is a limited amount of SGX memory (EPC) on each system. When that memory is used up, SGX has its own swapping mechanism which is similar in concept but totally separate from the core mm/* code. Instead of swapping to disk, SGX swaps from EPC to normal RAM. That normal RAM comes from a shared memory pseudo-file and can itself be swapped by the core mm code. There is a hierarchy like this: EPC <-> shmem <-> disk After data is swapped back in from shmem to EPC, the shmem backing storage needs to be freed. Currently, the backing shmem is not freed. This effectively wastes the shmem while the enclave is running. The memory is recovered when the enclave is destroyed and the backing storage freed. Sort this out by freeing memory with shmem_truncate_range(), as soon as a page is faulted back to the EPC. In addition, free the memory for PCMD pages as soon as all PCMD's in a page have been marked as unused by zeroing its contents. Cc: stable@vger.kernel.org Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer") Reported-by: Dave Hansen Signed-off-by: Jarkko Sakkinen Signed-off-by: Dave Hansen Link: https://lkml.kernel.org/r/20220303223859.273187-1-jarkko@kernel.org --- arch/x86/kernel/cpu/sgx/encl.c | 57 +++++++++++++++++++++++++++++++++++------- 1 file changed, 48 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 48afe96ae0f0..7c63a1911fae 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,6 +12,30 @@ #include "encls.h" #include "sgx.h" +/* + * Calculate byte offset of a PCMD struct associated with an enclave page. PCMD's + * follow right after the EPC data in the backing storage. In addition to the + * visible enclave pages, there's one extra page slot for SECS, before PCMD + * structs. + */ +static inline pgoff_t sgx_encl_get_backing_page_pcmd_offset(struct sgx_encl *encl, + unsigned long page_index) +{ + pgoff_t epc_end_off = encl->size + sizeof(struct sgx_secs); + + return epc_end_off + page_index * sizeof(struct sgx_pcmd); +} + +/* + * Free a page from the backing storage in the given page index. + */ +static inline void sgx_encl_truncate_backing_page(struct sgx_encl *encl, unsigned long page_index) +{ + struct inode *inode = file_inode(encl->backing); + + shmem_truncate_range(inode, PFN_PHYS(page_index), PFN_PHYS(page_index) + PAGE_SIZE - 1); +} + /* * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC * Pages" in the SDM. @@ -22,9 +46,11 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, { unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; struct sgx_encl *encl = encl_page->encl; + pgoff_t page_index, page_pcmd_off; struct sgx_pageinfo pginfo; struct sgx_backing b; - pgoff_t page_index; + bool pcmd_page_empty; + u8 *pcmd_page; int ret; if (secs_page) @@ -32,14 +58,16 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, else page_index = PFN_DOWN(encl->size); + page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); + ret = sgx_encl_get_backing(encl, page_index, &b); if (ret) return ret; pginfo.addr = encl_page->desc & PAGE_MASK; pginfo.contents = (unsigned long)kmap_atomic(b.contents); - pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) + - b.pcmd_offset; + pcmd_page = kmap_atomic(b.pcmd); + pginfo.metadata = (unsigned long)pcmd_page + b.pcmd_offset; if (secs_page) pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page); @@ -55,11 +83,24 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, ret = -EFAULT; } - kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset)); + memset(pcmd_page + b.pcmd_offset, 0, sizeof(struct sgx_pcmd)); + + /* + * The area for the PCMD in the page was zeroed above. Check if the + * whole page is now empty meaning that all PCMD's have been zeroed: + */ + pcmd_page_empty = !memchr_inv(pcmd_page, 0, PAGE_SIZE); + + kunmap_atomic(pcmd_page); kunmap_atomic((void *)(unsigned long)pginfo.contents); sgx_encl_put_backing(&b, false); + sgx_encl_truncate_backing_page(encl, page_index); + + if (pcmd_page_empty) + sgx_encl_truncate_backing_page(encl, PFN_DOWN(page_pcmd_off)); + return ret; } @@ -579,7 +620,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { - pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5); + pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); struct page *contents; struct page *pcmd; @@ -587,7 +628,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, if (IS_ERR(contents)) return PTR_ERR(contents); - pcmd = sgx_encl_get_backing_page(encl, pcmd_index); + pcmd = sgx_encl_get_backing_page(encl, PFN_DOWN(page_pcmd_off)); if (IS_ERR(pcmd)) { put_page(contents); return PTR_ERR(pcmd); @@ -596,9 +637,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, backing->page_index = page_index; backing->contents = contents; backing->pcmd = pcmd; - backing->pcmd_offset = - (page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) * - sizeof(struct sgx_pcmd); + backing->pcmd_offset = page_pcmd_off & (PAGE_SIZE - 1); return 0; } -- cgit v1.2.3 From 6c7cb60bff7aec24b834343ff433125f469886a3 Mon Sep 17 00:00:00 2001 From: Russell King (Oracle) Date: Fri, 11 Mar 2022 17:13:17 +0000 Subject: ARM: fix Thumb2 regression with Spectre BHB When building for Thumb2, the vectors make use of a local label. Sadly, the Spectre BHB code also uses a local label with the same number which results in the Thumb2 reference pointing at the wrong place. Fix this by changing the number used for the Spectre BHB local label. Fixes: b9baf5c8c5c3 ("ARM: Spectre-BHB workaround") Tested-by: Nathan Chancellor Signed-off-by: Russell King (Oracle) Signed-off-by: Linus Torvalds --- arch/arm/kernel/entry-armv.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 676703cbfe4b..ee3f7a599181 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -1040,9 +1040,9 @@ vector_bhb_loop8_\name: @ bhb workaround mov r0, #8 -1: b . + 4 +3: b . + 4 subs r0, r0, #1 - bne 1b + bne 3b dsb isb b 2b -- cgit v1.2.3 From 68453767131a5deec1e8f9ac92a9042f929e585d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 11 Mar 2022 11:49:12 -0800 Subject: ARM: Spectre-BHB: provide empty stub for non-config When CONFIG_GENERIC_CPU_VULNERABILITIES is not set, references to spectre_v2_update_state() cause a build error, so provide an empty stub for that function when the Kconfig option is not set. Fixes this build error: arm-linux-gnueabi-ld: arch/arm/mm/proc-v7-bugs.o: in function `cpu_v7_bugs_init': proc-v7-bugs.c:(.text+0x52): undefined reference to `spectre_v2_update_state' arm-linux-gnueabi-ld: proc-v7-bugs.c:(.text+0x82): undefined reference to `spectre_v2_update_state' Fixes: b9baf5c8c5c3 ("ARM: Spectre-BHB workaround") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Russell King Cc: Catalin Marinas Cc: linux-arm-kernel@lists.infradead.org Cc: patches@armlinux.org.uk Acked-by: Russell King (Oracle) Signed-off-by: Linus Torvalds --- arch/arm/include/asm/spectre.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/include/asm/spectre.h b/arch/arm/include/asm/spectre.h index d1fa5607d3aa..85f9e538fb32 100644 --- a/arch/arm/include/asm/spectre.h +++ b/arch/arm/include/asm/spectre.h @@ -25,7 +25,13 @@ enum { SPECTRE_V2_METHOD_LOOP8 = BIT(__SPECTRE_V2_METHOD_LOOP8), }; +#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES void spectre_v2_update_state(unsigned int state, unsigned int methods); +#else +static inline void spectre_v2_update_state(unsigned int state, + unsigned int methods) +{} +#endif int spectre_bhb_update_vectors(unsigned int method); -- cgit v1.2.3 From 5e34af4142ffe68f01c8a9acae83300f8911e20c Mon Sep 17 00:00:00 2001 From: Tadeusz Struk Date: Thu, 10 Mar 2022 15:25:38 -0800 Subject: net: ipv6: fix skb_over_panic in __ip6_append_data Syzbot found a kernel bug in the ipv6 stack: LINK: https://syzkaller.appspot.com/bug?id=205d6f11d72329ab8d62a610c44c5e7e25415580 The reproducer triggers it by sending a crafted message via sendmmsg() call, which triggers skb_over_panic, and crashes the kernel: skbuff: skb_over_panic: text:ffffffff84647fb4 len:65575 put:65575 head:ffff888109ff0000 data:ffff888109ff0088 tail:0x100af end:0xfec0 dev: Update the check that prevents an invalid packet with MTU equal to the fregment header size to eat up all the space for payload. The reproducer can be found here: LINK: https://syzkaller.appspot.com/text?tag=ReproC&x=1648c83fb00000 Reported-by: syzbot+e223cf47ec8ae183f2a0@syzkaller.appspotmail.com Signed-off-by: Tadeusz Struk Acked-by: Willem de Bruijn Link: https://lore.kernel.org/r/20220310232538.1044947-1-tadeusz.struk@linaro.org Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4788f6b37053..194832663d85 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1476,8 +1476,8 @@ static int __ip6_append_data(struct sock *sk, sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; - if (mtu < fragheaderlen || - ((mtu - fragheaderlen) & ~7) + fragheaderlen < sizeof(struct frag_hdr)) + if (mtu <= fragheaderlen || + ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr)) goto emsgsize; maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - -- cgit v1.2.3 From 46b348fd2d81a341b15fb3f3f986204b038f5c42 Mon Sep 17 00:00:00 2001 From: Niels Dossche Date: Fri, 11 Mar 2022 00:27:08 +0100 Subject: alx: acquire mutex for alx_reinit in alx_change_mtu alx_reinit has a lockdep assertion that the alx->mtx mutex must be held. alx_reinit is called from two places: alx_reset and alx_change_mtu. alx_reset does acquire alx->mtx before calling alx_reinit. alx_change_mtu does not acquire this mutex, nor do its callers or any path towards alx_change_mtu. Acquire the mutex in alx_change_mtu. The issue was introduced when the fine-grained locking was introduced to the code to replace the RTNL. The same commit also introduced the lockdep assertion. Fixes: 4a5fe57e7751 ("alx: use fine-grained locking instead of RTNL") Signed-off-by: Niels Dossche Link: https://lore.kernel.org/r/20220310232707.44251-1-dossche.niels@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/alx/main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 4ad3fc72e74e..a89b93cb4e26 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1181,8 +1181,11 @@ static int alx_change_mtu(struct net_device *netdev, int mtu) alx->hw.mtu = mtu; alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE); netdev_update_features(netdev); - if (netif_running(netdev)) + if (netif_running(netdev)) { + mutex_lock(&alx->mtx); alx_reinit(alx); + mutex_unlock(&alx->mtx); + } return 0; } -- cgit v1.2.3 From 8e6ed963763fe21429eabfc76c69ce2b0163a3dd Mon Sep 17 00:00:00 2001 From: Jiyong Park Date: Fri, 11 Mar 2022 11:00:16 +0900 Subject: vsock: each transport cycles only on its own sockets When iterating over sockets using vsock_for_each_connected_socket, make sure that a transport filters out sockets that don't belong to the transport. There actually was an issue caused by this; in a nested VM configuration, destroying the nested VM (which often involves the closing of /dev/vhost-vsock if there was h2g connections to the nested VM) kills not only the h2g connections, but also all existing g2h connections to the (outmost) host which are totally unrelated. Tested: Executed the following steps on Cuttlefish (Android running on a VM) [1]: (1) Enter into an `adb shell` session - to have a g2h connection inside the VM, (2) open and then close /dev/vhost-vsock by `exec 3< /dev/vhost-vsock && exec 3<&-`, (3) observe that the adb session is not reset. [1] https://android.googlesource.com/device/google/cuttlefish/ Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Reviewed-by: Stefano Garzarella Acked-by: Michael S. Tsirkin Signed-off-by: Jiyong Park Link: https://lore.kernel.org/r/20220311020017.1509316-1-jiyong@google.com Signed-off-by: Jakub Kicinski --- drivers/vhost/vsock.c | 3 ++- include/net/af_vsock.h | 3 ++- net/vmw_vsock/af_vsock.c | 9 +++++++-- net/vmw_vsock/virtio_transport.c | 7 +++++-- net/vmw_vsock/vmci_transport.c | 5 ++++- 5 files changed, 20 insertions(+), 7 deletions(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 37f0b4274113..e6c9d41db1de 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -753,7 +753,8 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file) /* Iterating over all connections for all CIDs to find orphans is * inefficient. Room for improvement here. */ - vsock_for_each_connected_socket(vhost_vsock_reset_orphans); + vsock_for_each_connected_socket(&vhost_transport.transport, + vhost_vsock_reset_orphans); /* Don't check the owner, because we are in the release path, so we * need to stop the vsock device in any case. diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index ab207677e0a8..f742e50207fb 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -205,7 +205,8 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); void vsock_remove_sock(struct vsock_sock *vsk); -void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)); +void vsock_for_each_connected_socket(struct vsock_transport *transport, + void (*fn)(struct sock *sk)); int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk); bool vsock_find_cid(unsigned int cid); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 38baeb189d4e..f04abf662ec6 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -334,7 +334,8 @@ void vsock_remove_sock(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_remove_sock); -void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)) +void vsock_for_each_connected_socket(struct vsock_transport *transport, + void (*fn)(struct sock *sk)) { int i; @@ -343,8 +344,12 @@ void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)) for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) { struct vsock_sock *vsk; list_for_each_entry(vsk, &vsock_connected_table[i], - connected_table) + connected_table) { + if (vsk->transport != transport) + continue; + fn(sk_vsock(vsk)); + } } spin_unlock_bh(&vsock_table_lock); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index fb3302fff627..5afc194a58bb 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -24,6 +24,7 @@ static struct workqueue_struct *virtio_vsock_workqueue; static struct virtio_vsock __rcu *the_virtio_vsock; static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */ +static struct virtio_transport virtio_transport; /* forward declaration */ struct virtio_vsock { struct virtio_device *vdev; @@ -384,7 +385,8 @@ static void virtio_vsock_event_handle(struct virtio_vsock *vsock, switch (le32_to_cpu(event->id)) { case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET: virtio_vsock_update_guest_cid(vsock); - vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vsock_for_each_connected_socket(&virtio_transport.transport, + virtio_vsock_reset_sock); break; } } @@ -662,7 +664,8 @@ static void virtio_vsock_remove(struct virtio_device *vdev) synchronize_rcu(); /* Reset all connected sockets when the device disappear */ - vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vsock_for_each_connected_socket(&virtio_transport.transport, + virtio_vsock_reset_sock); /* Stop all work handlers to make sure no one is accessing the device, * so we can safely call virtio_reset_device(). diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 7aef34e32bdf..b17dc9745188 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -75,6 +75,8 @@ static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; static int PROTOCOL_OVERRIDE = -1; +static struct vsock_transport vmci_transport; /* forward declaration */ + /* Helper function to convert from a VMCI error code to a VSock error code. */ static s32 vmci_transport_error_to_vsock_error(s32 vmci_error) @@ -882,7 +884,8 @@ static void vmci_transport_qp_resumed_cb(u32 sub_id, const struct vmci_event_data *e_data, void *client_data) { - vsock_for_each_connected_socket(vmci_transport_handle_detach); + vsock_for_each_connected_socket(&vmci_transport, + vmci_transport_handle_detach); } static void vmci_transport_recv_pkt_work(struct work_struct *work) -- cgit v1.2.3 From 3755d35ee1d2454b20b8a1e20d790e56201678a4 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 3 Feb 2022 10:39:22 +0100 Subject: drm/panel: Select DRM_DP_HELPER for DRM_PANEL_EDP As reported in [1], DRM_PANEL_EDP depends on DRM_DP_HELPER. Select the option to fix the build failure. The error message is shown below. arm-linux-gnueabihf-ld: drivers/gpu/drm/panel/panel-edp.o: in function `panel_edp_probe': panel-edp.c:(.text+0xb74): undefined reference to `drm_panel_dp_aux_backlight' make[1]: *** [/builds/linux/Makefile:1222: vmlinux] Error 1 The issue has been reported before, when DisplayPort helpers were hidden behind the option CONFIG_DRM_KMS_HELPER. [2] v2: * fix and expand commit description (Arnd) Signed-off-by: Thomas Zimmermann Fixes: 9d6366e743f3 ("drm: fb_helper: improve CONFIG_FB dependency") Reported-by: Naresh Kamboju Reported-by: Linux Kernel Functional Testing Reviewed-by: Lyude Paul Acked-by: Sam Ravnborg Link: https://lore.kernel.org/dri-devel/CA+G9fYvN0NyaVkRQmA1O6rX7H8PPaZrUAD7=RDy33QY9rUU-9g@mail.gmail.com/ # [1] Link: https://lore.kernel.org/all/20211117062704.14671-1-rdunlap@infradead.org/ # [2] Cc: Thomas Zimmermann Cc: Lyude Paul Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: dri-devel@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20220203093922.20754-1-tzimmermann@suse.de Signed-off-by: Dave Airlie --- drivers/gpu/drm/panel/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index 434c2861bb40..0aec5a10b064 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -106,6 +106,7 @@ config DRM_PANEL_EDP depends on PM select VIDEOMODE_HELPERS select DRM_DP_AUX_BUS + select DRM_DP_HELPER help DRM panel driver for dumb eDP panels that need at most a regulator and a GPIO to be powered up. Optionally a backlight can be attached so -- cgit v1.2.3 From 3ec94eeaff9ad58a76be2232068b4a2546b2f6bb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 21 Dec 2020 12:53:44 -0300 Subject: tools kvm headers arm64: Update KVM headers from the kernel sources To pick the changes from: a5905d6af492ee6a ("KVM: arm64: Allow SMCCC_ARCH_WORKAROUND_3 to be discovered and migrated") That don't causes any changes in tooling (when built on x86), only addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Cc: James Morse Link: https://lore.kernel.org/lkml/YiyhAK6sVPc83FaI@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index b3edde68bc3e..323e251ed37b 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2 + /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) -- cgit v1.2.3 From ec9d50ace39925f7fd0302bf0fad640e2c9826ea Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Jul 2021 13:39:15 -0300 Subject: tools headers cpufeatures: Sync with the kernel sources To pick the changes from: d45476d983240937 ("x86/speculation: Rename RETPOLINE_AMD to RETPOLINE_LFENCE") Its just a comment fixup. This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Borislav Petkov Cc: Peter Zijlstra (Intel) Link: https://lore.kernel.org/lkml/YiyiHatGaJQM7l/Y@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index ab4e53715d8a..65d147974f8d 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ /* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCEs for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ -- cgit v1.2.3 From a7a72631f62445e3671b7cab5ad01f856c1aa90d Mon Sep 17 00:00:00 2001 From: Weiguo Li Date: Fri, 11 Mar 2022 21:06:57 +0800 Subject: perf parse-events: Fix NULL check against wrong variable We did a null check after "tmp->symbol = strdup(...)", but we checked "list->symbol" other than "tmp->symbol". Reviewed-by: John Garry Signed-off-by: Weiguo Li Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/tencent_DF39269807EC9425E24787E6DB632441A405@qq.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9739b05b999e..dfb50a5f83d0 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2193,7 +2193,7 @@ int perf_pmu__test_parse_init(void) for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) { tmp->type = symbols[i].type; tmp->symbol = strdup(symbols[i].symbol); - if (!list->symbol) + if (!tmp->symbol) goto err_free; } -- cgit v1.2.3 From 073a15c3512f6b8d36c0c05992cf31e845f4dfe0 Mon Sep 17 00:00:00 2001 From: Weiguo Li Date: Fri, 11 Mar 2022 21:07:16 +0800 Subject: perf bench: Fix NULL check against wrong variable We did a NULL check after "epollfdp = calloc(...)", but we checked "epollfd" instead of "epollfdp". Signed-off-by: Weiguo Li Acked-by: Davidlohr Bueso Cc: Alexander Shishkin Cc: Davidlohr Bueso Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/tencent_B5D64530EB9C7DBB8D2C88A0C790F1489D0A@qq.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/epoll-ctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 740ae764537e..134612bde0cb 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -106,7 +106,7 @@ static void nest_epollfd(void) printinfo("Nesting level(s): %d\n", nested); epollfdp = calloc(nested, sizeof(int)); - if (!epollfd) + if (!epollfdp) err(EXIT_FAILURE, "calloc"); for (i = 0; i < nested; i++) { -- cgit v1.2.3 From 91c9923a473a694eb1c5c01ab778a77114969707 Mon Sep 17 00:00:00 2001 From: Zhengjun Xing Date: Mon, 7 Mar 2022 23:16:27 +0800 Subject: perf parse: Fix event parser error for hybrid systems This bug happened on hybrid systems when both cpu_core and cpu_atom have the same event name such as "UOPS_RETIRED.MS" while their event terms are different, then during perf stat, the event for cpu_atom will parse fail and then no output for cpu_atom. UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/ It is because event terms in the "head" of parse_events_multi_pmu_add will be changed to event terms for cpu_core after parsing UOPS_RETIRED.MS for cpu_core, then when parsing the same event for cpu_atom, it still uses the event terms for cpu_core, but event terms for cpu_atom are different with cpu_core, the event parses for cpu_atom will fail. This patch fixes it, the event terms should be parsed from the original event. This patch can work for the hybrid systems that have the same event in more than 2 PMUs. It also can work in non-hybrid systems. Before: # perf stat -v -e UOPS_RETIRED.MS -a sleep 1 Using CPUID GenuineIntel-6-97-1 UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ Control descriptor is not initialized UOPS_RETIRED.MS: 2737845 16068518485 16068518485 Performance counter stats for 'system wide': 2,737,845 cpu_core/UOPS_RETIRED.MS/ 1.002553850 seconds time elapsed After: # perf stat -v -e UOPS_RETIRED.MS -a sleep 1 Using CPUID GenuineIntel-6-97-1 UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/ Control descriptor is not initialized UOPS_RETIRED.MS: 1977555 16076950711 16076950711 UOPS_RETIRED.MS: 568684 8038694234 8038694234 Performance counter stats for 'system wide': 1,977,555 cpu_core/UOPS_RETIRED.MS/ 568,684 cpu_atom/UOPS_RETIRED.MS/ 1.004758259 seconds time elapsed Fixes: fb0811535e92c6c1 ("perf parse-events: Allow config on kernel PMU events") Reviewed-by: Kan Liang Signed-off-by: Zhengjun Xing Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220307151627.30049-1-zhengjun.xing@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index dfb50a5f83d0..24997925ae00 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1648,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, { struct parse_events_term *term; struct list_head *list = NULL; + struct list_head *orig_head = NULL; struct perf_pmu *pmu = NULL; int ok = 0; char *config; @@ -1674,7 +1675,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } list_add_tail(&term->list, head); - /* Add it for all PMUs that support the alias */ list = malloc(sizeof(struct list_head)); if (!list) @@ -1687,13 +1687,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { + parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, - pmu->name, head, + pmu->name, orig_head, true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; } + parse_events_terms__delete(orig_head); } } } -- cgit v1.2.3 From ed5f85d4229010235eab1e3d9acf6970d9304963 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 12 Mar 2022 11:05:46 +0100 Subject: netfilter: nf_tables: disable register tracking The register tracking infrastructure is incomplete, it might lead to generating incorrect ruleset bytecode, disable it by now given we are late in the release process. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c86748b3873b..d71a33ae39b3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8260,6 +8260,12 @@ void nf_tables_trans_destroy_flush_work(void) } EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); +static bool nft_expr_reduce(struct nft_regs_track *track, + const struct nft_expr *expr) +{ + return false; +} + static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) { const struct nft_expr *expr, *last; @@ -8307,8 +8313,7 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha nft_rule_for_each_expr(expr, last, rule) { track.cur = expr; - if (expr->ops->reduce && - expr->ops->reduce(&track, expr)) { + if (nft_expr_reduce(&track, expr)) { expr = track.cur; continue; } -- cgit v1.2.3 From 09688c0166e76ce2fb85e86b9d99be8b0084cdf9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Mar 2022 13:23:37 -0700 Subject: Linux 5.17-rc8 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 87f672473523..55a30ca69350 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Superb Owl # *DOCUMENTATION* -- cgit v1.2.3 From a680b1832ced3b5fa7c93484248fd221ea0d614b Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Thu, 10 Mar 2022 18:24:59 -0500 Subject: crypto: qcom-rng - ensure buffer for generate is completely filled The generate function in struct rng_alg expects that the destination buffer is completely filled if the function returns 0. qcom_rng_read() can run into a situation where the buffer is partially filled with randomness and the remaining part of the buffer is zeroed since qcom_rng_generate() doesn't check the return value. This issue can be reproduced by running the following from libkcapi: kcapi-rng -b 9000000 > OUTFILE The generated OUTFILE will have three huge sections that contain all zeros, and this is caused by the code where the test 'val & PRNG_STATUS_DATA_AVAIL' fails. Let's fix this issue by ensuring that qcom_rng_read() always returns with a full buffer if the function returns success. Let's also have qcom_rng_generate() return the correct value. Here's some statistics from the ent project (https://www.fourmilab.ch/random/) that shows information about the quality of the generated numbers: $ ent -c qcom-random-before Value Char Occurrences Fraction 0 606748 0.067416 1 33104 0.003678 2 33001 0.003667 ... 253 � 32883 0.003654 254 � 33035 0.003671 255 � 33239 0.003693 Total: 9000000 1.000000 Entropy = 7.811590 bits per byte. Optimum compression would reduce the size of this 9000000 byte file by 2 percent. Chi square distribution for 9000000 samples is 9329962.81, and randomly would exceed this value less than 0.01 percent of the times. Arithmetic mean value of data bytes is 119.3731 (127.5 = random). Monte Carlo value for Pi is 3.197293333 (error 1.77 percent). Serial correlation coefficient is 0.159130 (totally uncorrelated = 0.0). Without this patch, the results of the chi-square test is 0.01%, and the numbers are certainly not random according to ent's project page. The results improve with this patch: $ ent -c qcom-random-after Value Char Occurrences Fraction 0 35432 0.003937 1 35127 0.003903 2 35424 0.003936 ... 253 � 35201 0.003911 254 � 34835 0.003871 255 � 35368 0.003930 Total: 9000000 1.000000 Entropy = 7.999979 bits per byte. Optimum compression would reduce the size of this 9000000 byte file by 0 percent. Chi square distribution for 9000000 samples is 258.77, and randomly would exceed this value 42.24 percent of the times. Arithmetic mean value of data bytes is 127.5006 (127.5 = random). Monte Carlo value for Pi is 3.141277333 (error 0.01 percent). Serial correlation coefficient is 0.000468 (totally uncorrelated = 0.0). This change was tested on a Nexus 5 phone (msm8974 SoC). Signed-off-by: Brian Masney Fixes: ceec5f5b5988 ("crypto: qcom-rng - Add Qcom prng driver") Cc: stable@vger.kernel.org # 4.19+ Reviewed-by: Bjorn Andersson Reviewed-by: Andrew Halaney Signed-off-by: Herbert Xu --- drivers/crypto/qcom-rng.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c index 99ba8d51d102..11f30fd48c14 100644 --- a/drivers/crypto/qcom-rng.c +++ b/drivers/crypto/qcom-rng.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -43,16 +44,19 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) { unsigned int currsize = 0; u32 val; + int ret; /* read random data from hardware */ do { - val = readl_relaxed(rng->base + PRNG_STATUS); - if (!(val & PRNG_STATUS_DATA_AVAIL)) - break; + ret = readl_poll_timeout(rng->base + PRNG_STATUS, val, + val & PRNG_STATUS_DATA_AVAIL, + 200, 10000); + if (ret) + return ret; val = readl_relaxed(rng->base + PRNG_DATA_OUT); if (!val) - break; + return -EINVAL; if ((max - currsize) >= WORD_SZ) { memcpy(data, &val, WORD_SZ); @@ -61,11 +65,10 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) } else { /* copy only remaining bytes */ memcpy(data, &val, max - currsize); - break; } } while (currsize < max); - return currsize; + return 0; } static int qcom_rng_generate(struct crypto_rng *tfm, @@ -87,7 +90,7 @@ static int qcom_rng_generate(struct crypto_rng *tfm, mutex_unlock(&rng->lock); clk_disable_unprepare(rng->clk); - return 0; + return ret; } static int qcom_rng_seed(struct crypto_rng *tfm, const u8 *seed, -- cgit v1.2.3 From e981bc74aefc6a177b50c16cfa7023599799cf74 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Fri, 11 Mar 2022 13:17:16 +0200 Subject: net: dsa: microchip: add spi_device_id tables Add spi_device_id tables to avoid logs like "SPI driver ksz9477-switch has no spi_device_id". Signed-off-by: Claudiu Beznea Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795_spi.c | 11 +++++++++++ drivers/net/dsa/microchip/ksz9477_spi.c | 12 ++++++++++++ 2 files changed, 23 insertions(+) diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c index 866767b70d65..b0a7dee27ffc 100644 --- a/drivers/net/dsa/microchip/ksz8795_spi.c +++ b/drivers/net/dsa/microchip/ksz8795_spi.c @@ -124,12 +124,23 @@ static const struct of_device_id ksz8795_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, ksz8795_dt_ids); +static const struct spi_device_id ksz8795_spi_ids[] = { + { "ksz8765" }, + { "ksz8794" }, + { "ksz8795" }, + { "ksz8863" }, + { "ksz8873" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, ksz8795_spi_ids); + static struct spi_driver ksz8795_spi_driver = { .driver = { .name = "ksz8795-switch", .owner = THIS_MODULE, .of_match_table = of_match_ptr(ksz8795_dt_ids), }, + .id_table = ksz8795_spi_ids, .probe = ksz8795_spi_probe, .remove = ksz8795_spi_remove, .shutdown = ksz8795_spi_shutdown, diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index e3cb0e6c9f6f..43addeabfc25 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -98,12 +98,24 @@ static const struct of_device_id ksz9477_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, ksz9477_dt_ids); +static const struct spi_device_id ksz9477_spi_ids[] = { + { "ksz9477" }, + { "ksz9897" }, + { "ksz9893" }, + { "ksz9563" }, + { "ksz8563" }, + { "ksz9567" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, ksz9477_spi_ids); + static struct spi_driver ksz9477_spi_driver = { .driver = { .name = "ksz9477-switch", .owner = THIS_MODULE, .of_match_table = of_match_ptr(ksz9477_dt_ids), }, + .id_table = ksz9477_spi_ids, .probe = ksz9477_spi_probe, .remove = ksz9477_spi_remove, .shutdown = ksz9477_spi_shutdown, -- cgit v1.2.3 From 4db4075f92af2b28f415fc979ab626e6b37d67b6 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 10 Mar 2022 11:49:00 +0100 Subject: esp6: fix check on ipv6_skip_exthdr's return value Commit 5f9c55c8066b ("ipv6: check return value of ipv6_skip_exthdr") introduced an incorrect check, which leads to all ESP packets over either TCPv6 or UDPv6 encapsulation being dropped. In this particular case, offset is negative, since skb->data points to the ESP header in the following chain of headers, while skb->network_header points to the IPv6 header: IPv6 | ext | ... | ext | UDP | ESP | ... That doesn't seem to be a problem, especially considering that if we reach esp6_input_done2, we're guaranteed to have a full set of headers available (otherwise the packet would have been dropped earlier in the stack). However, it means that the return value will (intentionally) be negative. We can make the test more specific, as the expected return value of ipv6_skip_exthdr will be the (negated) size of either a UDP header, or a TCP header with possible options. In the future, we should probably either make ipv6_skip_exthdr explicitly accept negative offsets (and adjust its return value for error cases), or make ipv6_skip_exthdr only take non-negative offsets (and audit all callers). Fixes: 5f9c55c8066b ("ipv6: check return value of ipv6_skip_exthdr") Reported-by: Xiumei Mu Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/ipv6/esp6.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index b0ffbcd5432d..55d604c9b3b3 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -812,8 +812,7 @@ int esp6_input_done2(struct sk_buff *skb, int err) struct tcphdr *th; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); - - if (offset < 0) { + if (offset == -1) { err = -EINVAL; goto out; } -- cgit v1.2.3 From 837d9e49402eaf030db55a49f96fc51d73b4b441 Mon Sep 17 00:00:00 2001 From: Kurt Cancemi Date: Sat, 12 Mar 2022 15:15:13 -0500 Subject: net: phy: marvell: Fix invalid comparison in the resume and suspend functions This bug resulted in only the current mode being resumed and suspended when the PHY supported both fiber and copper modes and when the PHY only supported copper mode the fiber mode would incorrectly be attempted to be resumed and suspended. Fixes: 3758be3dc162 ("Marvell phy: add functions to suspend and resume both interfaces: fiber and copper links.") Signed-off-by: Kurt Cancemi Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20220312201512.326047-1-kurt@x64architecture.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/marvell.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 2429db614b59..2702faf7b0f6 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1687,8 +1687,8 @@ static int marvell_suspend(struct phy_device *phydev) int err; /* Suspend the fiber mode first */ - if (!linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, - phydev->supported)) { + if (linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + phydev->supported)) { err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE); if (err < 0) goto error; @@ -1722,8 +1722,8 @@ static int marvell_resume(struct phy_device *phydev) int err; /* Resume the fiber mode first */ - if (!linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, - phydev->supported)) { + if (linkmode_test_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + phydev->supported)) { err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE); if (err < 0) goto error; -- cgit v1.2.3 From 0f8946ae704ac6880c590beb91bc3a732595a28a Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Sat, 12 Mar 2022 23:41:40 +0100 Subject: net: mdio: mscc-miim: fix duplicate debugfs entry This driver can have up to two regmaps. If the second one is registered its debugfs entry will have the same name as the first one and the following error will be printed: [ 3.833521] debugfs: Directory 'e200413c.mdio' with parent 'regmap' already present! Give the second regmap a name to avoid this. Fixes: a27a76282837 ("net: mdio: mscc-miim: convert to a regmap implementation") Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20220312224140.4173930-1-michael@walle.cc Signed-off-by: Jakub Kicinski --- drivers/net/mdio/mdio-mscc-miim.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index 7d2abaf2b2c9..64fb76c1e395 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -187,6 +187,13 @@ static const struct regmap_config mscc_miim_regmap_config = { .reg_stride = 4, }; +static const struct regmap_config mscc_miim_phy_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .name = "phy", +}; + int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, const char *name, struct regmap *mii_regmap, int status_offset) { @@ -250,7 +257,7 @@ static int mscc_miim_probe(struct platform_device *pdev) } phy_regmap = devm_regmap_init_mmio(&pdev->dev, phy_regs, - &mscc_miim_regmap_config); + &mscc_miim_phy_regmap_config); if (IS_ERR(phy_regmap)) { dev_err(&pdev->dev, "Unable to create phy register regmap\n"); return PTR_ERR(phy_regmap); -- cgit v1.2.3 From c700525fcc06b05adfea78039de02628af79e07a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 12 Mar 2022 15:29:58 -0800 Subject: net/packet: fix slab-out-of-bounds access in packet_recvmsg() syzbot found that when an AF_PACKET socket is using PACKET_COPY_THRESH and mmap operations, tpacket_rcv() is queueing skbs with garbage in skb->cb[], triggering a too big copy [1] Presumably, users of af_packet using mmap() already gets correct metadata from the mapped buffer, we can simply make sure to clear 12 bytes that might be copied to user space later. BUG: KASAN: stack-out-of-bounds in memcpy include/linux/fortify-string.h:225 [inline] BUG: KASAN: stack-out-of-bounds in packet_recvmsg+0x56c/0x1150 net/packet/af_packet.c:3489 Write of size 165 at addr ffffc9000385fb78 by task syz-executor233/3631 CPU: 0 PID: 3631 Comm: syz-executor233 Not tainted 5.17.0-rc7-syzkaller-02396-g0b3660695e80 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0xf/0x336 mm/kasan/report.c:255 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:459 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x13d/0x180 mm/kasan/generic.c:189 memcpy+0x39/0x60 mm/kasan/shadow.c:66 memcpy include/linux/fortify-string.h:225 [inline] packet_recvmsg+0x56c/0x1150 net/packet/af_packet.c:3489 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] sock_recvmsg net/socket.c:962 [inline] ____sys_recvmsg+0x2c4/0x600 net/socket.c:2632 ___sys_recvmsg+0x127/0x200 net/socket.c:2674 __sys_recvmsg+0xe2/0x1a0 net/socket.c:2704 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7fdfd5954c29 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 41 15 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffcf8e71e48 EFLAGS: 00000246 ORIG_RAX: 000000000000002f RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007fdfd5954c29 RDX: 0000000000000000 RSI: 0000000020000500 RDI: 0000000000000005 RBP: 0000000000000000 R08: 000000000000000d R09: 000000000000000d R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffcf8e71e60 R13: 00000000000f4240 R14: 000000000000c1ff R15: 00007ffcf8e71e54 addr ffffc9000385fb78 is located in stack of task syz-executor233/3631 at offset 32 in frame: ____sys_recvmsg+0x0/0x600 include/linux/uio.h:246 this frame has 1 object: [32, 160) 'addr' Memory state around the buggy address: ffffc9000385fa80: 00 04 f3 f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 ffffc9000385fb00: 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 >ffffc9000385fb80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 f3 ^ ffffc9000385fc00: f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 f1 ffffc9000385fc80: f1 f1 f1 00 f2 f2 f2 00 f2 f2 f2 00 00 00 00 00 ================================================================== Fixes: 0fb375fb9b93 ("[AF_PACKET]: Allow for > 8 byte hardware addresses.") Signed-off-by: Eric Dumazet Reported-by: syzbot Link: https://lore.kernel.org/r/20220312232958.3535620-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/packet/af_packet.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ab87f22cc7ec..a7273af2d900 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2317,8 +2317,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, copy_skb = skb_get(skb); skb_head = skb->data; } - if (copy_skb) + if (copy_skb) { + memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, + sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); + } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { @@ -3462,6 +3465,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { + const size_t max_len = min(sizeof(skb->cb), + sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled @@ -3484,6 +3489,10 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, msg->msg_namelen = sizeof(struct sockaddr_ll); } } + if (WARN_ON_ONCE(copy_len > max_len)) { + copy_len = max_len; + msg->msg_namelen = copy_len; + } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } -- cgit v1.2.3 From 0f74b29a4f53627376cf5a5fb7b0b3fa748a0b2b Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Mon, 14 Mar 2022 09:34:48 +0800 Subject: atm: eni: Add check for dma_map_single As the potential failure of the dma_map_single(), it should be better to check it and return error if fails. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jiasheng Jiang Signed-off-by: David S. Miller --- drivers/atm/eni.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 422753d52244..a31ffe16e626 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -1112,6 +1112,8 @@ DPRINTK("iovcnt = %d\n",skb_shinfo(skb)->nr_frags); skb_data3 = skb->data[3]; paddr = dma_map_single(&eni_dev->pci_dev->dev,skb->data,skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(&eni_dev->pci_dev->dev, paddr)) + return enq_next; ENI_PRV_PADDR(skb) = paddr; /* prepare DMA queue entries */ j = 0; -- cgit v1.2.3 From 56e337f2cf1326323844927a04e9dbce9a244835 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 15 Mar 2022 17:52:05 +0100 Subject: Revert "gpio: Revert regression in sysfs-gpio (gpiolib.c)" This reverts commit fc328a7d1fcce263db0b046917a66f3aa6e68719. This commit - while attempting to fix a regression - has caused a number of other problems. As the fallout from it is more significant than the initial problem itself, revert it for now before we find a correct solution. Link: https://lore.kernel.org/all/20220314192522.GA3031157@roeck-us.net/ Link: https://lore.kernel.org/stable/20220314155509.552218-1-michael@walle.cc/ Link: https://lore.kernel.org/all/20211217153555.9413-1-marcelo.jimenez@gmail.com/ Signed-off-by: Bartosz Golaszewski Reported-and-bisected-by: Guenter Roeck Reported-by: Michael Walle Cc: Thorsten Leemhuis Cc: Marcelo Roberto Jimenez Signed-off-by: Linus Torvalds --- drivers/gpio/gpiolib.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index defb7c464b87..6630d92e30ad 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1701,6 +1701,11 @@ static inline void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gc) */ int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset) { +#ifdef CONFIG_PINCTRL + if (list_empty(&gc->gpiodev->pin_ranges)) + return 0; +#endif + return pinctrl_gpio_request(gc->gpiodev->base + offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_request); @@ -1712,6 +1717,11 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_request); */ void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset) { +#ifdef CONFIG_PINCTRL + if (list_empty(&gc->gpiodev->pin_ranges)) + return; +#endif + pinctrl_gpio_free(gc->gpiodev->base + offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_free); -- cgit v1.2.3 From e9c14b59ea2ec19afe22d60b07583b7e08c74290 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Mar 2022 15:28:19 -0700 Subject: Add Paolo Abeni to networking maintainers Growing the network maintainers team from 2 to 3. Signed-off-by: David S. Miller Link: https://lore.kernel.org/r/20220314222819.958428-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e127c2fb08a7..cd0f68d4a34a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13376,6 +13376,7 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" M: Jakub Kicinski +M: Paolo Abeni L: netdev@vger.kernel.org S: Maintained Q: https://patchwork.kernel.org/project/netdevbpf/list/ @@ -13422,6 +13423,7 @@ F: tools/testing/selftests/drivers/net/dsa/ NETWORKING [GENERAL] M: "David S. Miller" M: Jakub Kicinski +M: Paolo Abeni L: netdev@vger.kernel.org S: Maintained Q: https://patchwork.kernel.org/project/netdevbpf/list/ -- cgit v1.2.3 From f153546913bada41a811722f2c6d17c3243a0333 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Mon, 7 Mar 2022 18:47:39 +0100 Subject: ice: fix NULL pointer dereference in ice_update_vsi_tx_ring_stats() It is possible to do NULL pointer dereference in routine that updates Tx ring stats. Currently only stats and bytes are updated when ring pointer is valid, but later on ring is accessed to propagate gathered Tx stats onto VSI stats. Change the existing logic to move to next ring when ring is NULL. Fixes: e72bba21355d ("ice: split ice_ring onto Tx/Rx separate structs") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Maciej Fijalkowski Acked-by: Alexander Lobakin Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 493942e910be..d4a7c39fd078 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5962,8 +5962,9 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, u64 pkts = 0, bytes = 0; ring = READ_ONCE(rings[i]); - if (ring) - ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); + if (!ring) + continue; + ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); vsi_stats->tx_packets += pkts; vsi_stats->tx_bytes += bytes; vsi->tx_restart += ring->tx_stats.restart_q; -- cgit v1.2.3 From 1b4ae7d925c6569fff27313b4d84171b11510893 Mon Sep 17 00:00:00 2001 From: Sudheer Mogilappagari Date: Thu, 10 Mar 2022 10:46:52 -0800 Subject: ice: destroy flow director filter mutex after releasing VSIs Currently fdir_fltr_lock is accessed in ice_vsi_release_all() function after it is destroyed. Instead destroy mutex after ice_vsi_release_all. Fixes: 40319796b732 ("ice: Add flow director support for channel mode") Signed-off-by: Sudheer Mogilappagari Tested-by: Bharathi Sreenivas Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d4a7c39fd078..b7e8744b0c0a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4880,7 +4880,6 @@ static void ice_remove(struct pci_dev *pdev) ice_devlink_unregister_params(pf); set_bit(ICE_DOWN, pf->state); - mutex_destroy(&(&pf->hw)->fdir_fltr_lock); ice_deinit_lag(pf); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) ice_ptp_release(pf); @@ -4888,6 +4887,7 @@ static void ice_remove(struct pci_dev *pdev) ice_remove_arfs(pf); ice_setup_mc_magic_wake(pf); ice_vsi_release_all(pf); + mutex_destroy(&(&pf->hw)->fdir_fltr_lock); ice_set_wake(pf); ice_free_irq_msix_misc(pf); ice_for_each_vsi(pf, i) { -- cgit v1.2.3 From 16b2dd8cdf6f4e0597c34899de74b4d012b78188 Mon Sep 17 00:00:00 2001 From: Przemyslaw Patynowski Date: Wed, 9 Mar 2022 16:37:39 +0100 Subject: iavf: Fix double free in iavf_reset_task Fix double free possibility in iavf_disable_vf, as crit_lock is freed in caller, iavf_reset_task. Add kernel-doc for iavf_disable_vf. Remove mutex_unlock in iavf_disable_vf. Without this patch there is double free scenario, when calling iavf_reset_task. Fixes: e85ff9c631e1 ("iavf: Fix deadlock in iavf_reset_task") Signed-off-by: Przemyslaw Patynowski Suggested-by: Dan Carpenter Signed-off-by: Mateusz Palczewski Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8e644e9ed8da..45570e3f782e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2541,6 +2541,13 @@ restart_watchdog: queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2); } +/** + * iavf_disable_vf - disable VF + * @adapter: board private structure + * + * Set communication failed flag and free all resources. + * NOTE: This function is expected to be called with crit_lock being held. + **/ static void iavf_disable_vf(struct iavf_adapter *adapter) { struct iavf_mac_filter *f, *ftmp; @@ -2595,7 +2602,6 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); adapter->netdev->flags &= ~IFF_UP; - mutex_unlock(&adapter->crit_lock); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); -- cgit v1.2.3 From 886e44c9298a6b428ae046e2fa092ca52e822e6a Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Mon, 14 Mar 2022 10:01:25 +0800 Subject: hv_netvsc: Add check for kvmalloc_array As the potential failure of the kvmalloc_array(), it should be better to check and restore the 'data' if fails in order to avoid the dereference of the NULL pointer. Fixes: 6ae746711263 ("hv_netvsc: Add per-cpu ethtool stats for netvsc") Signed-off-by: Jiasheng Jiang Link: https://lore.kernel.org/r/20220314020125.2365084-1-jiasheng@iscas.ac.cn Signed-off-by: Jakub Kicinski --- drivers/net/hyperv/netvsc_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 3646469433b1..fde1c492ca02 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1587,6 +1587,9 @@ static void netvsc_get_ethtool_stats(struct net_device *dev, pcpu_sum = kvmalloc_array(num_possible_cpus(), sizeof(struct netvsc_ethtool_pcpu_stats), GFP_KERNEL); + if (!pcpu_sum) + return; + netvsc_get_pcpu_stats(dev, pcpu_sum); for_each_present_cpu(cpu) { struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu]; -- cgit v1.2.3 From 462ccc35a750f335c8456cde9120b8b593fff60f Mon Sep 17 00:00:00 2001 From: Rafael J. Wysocki Date: Wed, 16 Mar 2022 11:23:05 +0100 Subject: Revert "ACPI: scan: Do not add device IDs from _CID if _HID is not valid" Revert commit e38f9ff63e6d ("ACPI: scan: Do not add device IDs from _CID if _HID is not valid"), because it has introduced regressions on multiple systems, even though it only has effect on clearly invalid firmware. Reported-by: Pierre-Louis Bossart Signed-off-by: Rafael J. Wysocki --- drivers/acpi/scan.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 1331756d4cfc..8b2e5ef15559 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1377,11 +1377,11 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp, if (info->valid & ACPI_VALID_HID) { acpi_add_id(pnp, info->hardware_id.string); pnp->type.platform_id = 1; - if (info->valid & ACPI_VALID_CID) { - cid_list = &info->compatible_id_list; - for (i = 0; i < cid_list->count; i++) - acpi_add_id(pnp, cid_list->ids[i].string); - } + } + if (info->valid & ACPI_VALID_CID) { + cid_list = &info->compatible_id_list; + for (i = 0; i < cid_list->count; i++) + acpi_add_id(pnp, cid_list->ids[i].string); } if (info->valid & ACPI_VALID_ADR) { pnp->bus_address = info->address; -- cgit v1.2.3 From 45b4eb7ee6aa1a55a50831b328aa5f46ac3a7187 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Tue, 15 Mar 2022 17:54:55 +0200 Subject: Revert "ath10k: drop beacon and probe response which leak from other channel" This reverts commit 3bf2537ec2e33310b431b53fd84be8833736c256. I was reported privately that this commit breaks AP and mesh mode on QCA9984 (firmware 10.4-3.9.0.2-00156). So revert the commit to fix the regression. There was a conflict due to cfg80211 API changes but that was easy to fix. Fixes: 3bf2537ec2e3 ("ath10k: drop beacon and probe response which leak from other channel") Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220315155455.20446-1-kvalo@kernel.org --- drivers/net/wireless/ath/ath10k/wmi.c | 33 +-------------------------------- 1 file changed, 1 insertion(+), 32 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 62c453a21e49..7c1c2658cb5f 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -2611,36 +2611,9 @@ int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb) ath10k_mac_handle_beacon(ar, skb); if (ieee80211_is_beacon(hdr->frame_control) || - ieee80211_is_probe_resp(hdr->frame_control)) { - struct ieee80211_mgmt *mgmt = (void *)skb->data; - enum cfg80211_bss_frame_type ftype; - u8 *ies; - int ies_ch; - + ieee80211_is_probe_resp(hdr->frame_control)) status->boottime_ns = ktime_get_boottime_ns(); - if (!ar->scan_channel) - goto drop; - - ies = mgmt->u.beacon.variable; - - if (ieee80211_is_beacon(mgmt->frame_control)) - ftype = CFG80211_BSS_FTYPE_BEACON; - else - ftype = CFG80211_BSS_FTYPE_PRESP; - - ies_ch = cfg80211_get_ies_channel_number(mgmt->u.beacon.variable, - skb_tail_pointer(skb) - ies, - sband->band, ftype); - - if (ies_ch > 0 && ies_ch != channel) { - ath10k_dbg(ar, ATH10K_DBG_MGMT, - "channel mismatched ds channel %d scan channel %d\n", - ies_ch, channel); - goto drop; - } - } - ath10k_dbg(ar, ATH10K_DBG_MGMT, "event mgmt rx skb %pK len %d ftype %02x stype %02x\n", skb, skb->len, @@ -2654,10 +2627,6 @@ int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb) ieee80211_rx_ni(ar->hw, skb); return 0; - -drop: - dev_kfree_skb(skb); - return 0; } static int freq_to_idx(struct ath10k *ar, int freq) -- cgit v1.2.3 From 4ee06de7729d795773145692e246a06448b1eb7a Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 15 Mar 2022 10:20:08 +0100 Subject: net: handle ARPHRD_PIMREG in dev_is_mac_header_xmit() This kind of interface doesn't have a mac header. This patch fixes bpf_redirect() to a PIM interface. Fixes: 27b29f63058d ("bpf: add bpf_redirect() helper") Signed-off-by: Nicolas Dichtel Link: https://lore.kernel.org/r/20220315092008.31423-1-nicolas.dichtel@6wind.com Signed-off-by: Jakub Kicinski --- include/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index b712217f7030..1ed52441972f 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -52,6 +52,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: + case ARPHRD_PIMREG: return false; default: return true; -- cgit v1.2.3 From cb0b430b4e3acc88c85e0ad2e25f2a25a5765262 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Wed, 16 Mar 2022 08:26:02 +0000 Subject: net: dsa: Add missing of_node_put() in dsa_port_parse_of The device_node pointer is returned by of_parse_phandle() with refcount incremented. We should use of_node_put() on it when done. Fixes: 6d4e5c570c2d ("net: dsa: get port type at parse time") Signed-off-by: Miaoqian Lin Link: https://lore.kernel.org/r/20220316082602.10785-1-linmq006@gmail.com Signed-off-by: Paolo Abeni --- net/dsa/dsa2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 074e4a69a728..88e2808019b4 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1436,6 +1436,7 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) const char *user_protocol; master = of_find_net_device_by_node(ethernet); + of_node_put(ethernet); if (!master) return -EPROBE_DEFER; -- cgit v1.2.3 From f1858c277ba40172005b76a31e6bb931bfc19d9c Mon Sep 17 00:00:00 2001 From: Juerg Haefliger Date: Wed, 16 Mar 2022 16:18:35 +0100 Subject: net: phy: mscc: Add MODULE_FIRMWARE macros The driver requires firmware so define MODULE_FIRMWARE so that modinfo provides the details. Fixes: fa164e40c53b ("net: phy: mscc: split the driver into separate files") Signed-off-by: Juerg Haefliger Link: https://lore.kernel.org/r/20220316151835.88765-1-juergh@canonical.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/mscc/mscc_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index ebfeeb3c67c1..7e3017e7a1c0 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -2685,3 +2685,6 @@ MODULE_DEVICE_TABLE(mdio, vsc85xx_tbl); MODULE_DESCRIPTION("Microsemi VSC85xx PHY driver"); MODULE_AUTHOR("Nagaraju Lakkaraju"); MODULE_LICENSE("Dual MIT/GPL"); + +MODULE_FIRMWARE(MSCC_VSC8584_REVB_INT8051_FW); +MODULE_FIRMWARE(MSCC_VSC8574_REVB_INT8051_FW); -- cgit v1.2.3 From 424e7834e293936a54fcf05173f2884171adc5a3 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Wed, 16 Mar 2022 14:46:13 -0700 Subject: bnx2x: fix built-in kernel driver load failure Commit b7a49f73059f ("bnx2x: Utilize firmware 7.13.21.0") added request_firmware() logic in probe() which caused load failure when firmware file is not present in initrd (below), as access to firmware file is not feasible during probe. Direct firmware load for bnx2x/bnx2x-e2-7.13.15.0.fw failed with error -2 Direct firmware load for bnx2x/bnx2x-e2-7.13.21.0.fw failed with error -2 This patch fixes this issue by - 1. Removing request_firmware() logic from the probe() such that .ndo_open() handle it as it used to handle it earlier 2. Given request_firmware() is removed from probe(), so driver has to relax FW version comparisons a bit against the already loaded FW version (by some other PFs of same adapter) to allow different compatible/close enough FWs with which multiple PFs may run with (in different environments), as the given PF who is in probe flow has no idea now with which firmware file version it is going to initialize the device in ndo_open() Link: https://lore.kernel.org/all/46f2d9d9-ae7f-b332-ddeb-b59802be2bab@molgen.mpg.de/ Reported-by: Paul Menzel Tested-by: Paul Menzel Fixes: b7a49f73059f ("bnx2x: Utilize firmware 7.13.21.0") Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Link: https://lore.kernel.org/r/20220316214613.6884-1-manishc@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 2 -- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 28 ++++++++++++++---------- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 15 ++----------- 3 files changed, 19 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index a19dd6797070..2209d99b3404 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -2533,6 +2533,4 @@ void bnx2x_register_phc(struct bnx2x *bp); * Meant for implicit re-load flows. */ int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp); -int bnx2x_init_firmware(struct bnx2x *bp); -void bnx2x_release_firmware(struct bnx2x *bp); #endif /* bnx2x.h */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 8d36ebbf08e1..5729a5ab059d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2364,24 +2364,30 @@ int bnx2x_compare_fw_ver(struct bnx2x *bp, u32 load_code, bool print_err) /* is another pf loaded on this engine? */ if (load_code != FW_MSG_CODE_DRV_LOAD_COMMON_CHIP && load_code != FW_MSG_CODE_DRV_LOAD_COMMON) { - /* build my FW version dword */ - u32 my_fw = (bp->fw_major) + (bp->fw_minor << 8) + - (bp->fw_rev << 16) + (bp->fw_eng << 24); + u8 loaded_fw_major, loaded_fw_minor, loaded_fw_rev, loaded_fw_eng; + u32 loaded_fw; /* read loaded FW from chip */ - u32 loaded_fw = REG_RD(bp, XSEM_REG_PRAM); + loaded_fw = REG_RD(bp, XSEM_REG_PRAM); - DP(BNX2X_MSG_SP, "loaded fw %x, my fw %x\n", - loaded_fw, my_fw); + loaded_fw_major = loaded_fw & 0xff; + loaded_fw_minor = (loaded_fw >> 8) & 0xff; + loaded_fw_rev = (loaded_fw >> 16) & 0xff; + loaded_fw_eng = (loaded_fw >> 24) & 0xff; + + DP(BNX2X_MSG_SP, "loaded fw 0x%x major 0x%x minor 0x%x rev 0x%x eng 0x%x\n", + loaded_fw, loaded_fw_major, loaded_fw_minor, loaded_fw_rev, loaded_fw_eng); /* abort nic load if version mismatch */ - if (my_fw != loaded_fw) { + if (loaded_fw_major != BCM_5710_FW_MAJOR_VERSION || + loaded_fw_minor != BCM_5710_FW_MINOR_VERSION || + loaded_fw_eng != BCM_5710_FW_ENGINEERING_VERSION || + loaded_fw_rev < BCM_5710_FW_REVISION_VERSION_V15) { if (print_err) - BNX2X_ERR("bnx2x with FW %x was already loaded which mismatches my %x FW. Aborting\n", - loaded_fw, my_fw); + BNX2X_ERR("loaded FW incompatible. Aborting\n"); else - BNX2X_DEV_INFO("bnx2x with FW %x was already loaded which mismatches my %x FW, possibly due to MF UNDI\n", - loaded_fw, my_fw); + BNX2X_DEV_INFO("loaded FW incompatible, possibly due to MF UNDI\n"); + return -EBUSY; } } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index eedb48d945ed..c19b072f3a23 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12319,15 +12319,6 @@ static int bnx2x_init_bp(struct bnx2x *bp) bnx2x_read_fwinfo(bp); - if (IS_PF(bp)) { - rc = bnx2x_init_firmware(bp); - - if (rc) { - bnx2x_free_mem_bp(bp); - return rc; - } - } - func = BP_FUNC(bp); /* need to reset chip if undi was active */ @@ -12340,7 +12331,6 @@ static int bnx2x_init_bp(struct bnx2x *bp) rc = bnx2x_prev_unload(bp); if (rc) { - bnx2x_release_firmware(bp); bnx2x_free_mem_bp(bp); return rc; } @@ -13409,7 +13399,7 @@ do { \ (u8 *)bp->arr, len); \ } while (0) -int bnx2x_init_firmware(struct bnx2x *bp) +static int bnx2x_init_firmware(struct bnx2x *bp) { const char *fw_file_name, *fw_file_name_v15; struct bnx2x_fw_file_hdr *fw_hdr; @@ -13509,7 +13499,7 @@ request_firmware_exit: return rc; } -void bnx2x_release_firmware(struct bnx2x *bp) +static void bnx2x_release_firmware(struct bnx2x *bp) { kfree(bp->init_ops_offsets); kfree(bp->init_ops); @@ -14026,7 +14016,6 @@ static int bnx2x_init_one(struct pci_dev *pdev, return 0; init_one_freemem: - bnx2x_release_firmware(bp); bnx2x_free_mem_bp(bp); init_one_exit: -- cgit v1.2.3 From 0f643c88c8d240eba0ea25c2e095a46515ff46e9 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Wed, 16 Mar 2022 18:28:12 -0700 Subject: net: bcmgenet: skip invalid partial checksums The RXCHK block will return a partial checksum of 0 if it encounters a problem while receiving a packet. Since a 1's complement sum can only produce this result if no bits are set in the received data stream it is fair to treat it as an invalid partial checksum and not pass it up the stack. Fixes: 810155397890 ("net: bcmgenet: use CHECKSUM_COMPLETE for NETIF_F_RXCSUM") Signed-off-by: Doug Berger Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20220317012812.1313196-1-opendmb@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 87f1056e29ff..2da804f84b48 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2287,8 +2287,10 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, dma_length_status = status->length_status; if (dev->features & NETIF_F_RXCSUM) { rx_csum = (__force __be16)(status->rx_csum & 0xffff); - skb->csum = (__force __wsum)ntohs(rx_csum); - skb->ip_summed = CHECKSUM_COMPLETE; + if (rx_csum) { + skb->csum = (__force __wsum)ntohs(rx_csum); + skb->ip_summed = CHECKSUM_COMPLETE; + } } /* DMA flags and length are still valid no matter how -- cgit v1.2.3 From 8e0341aefcc9133f3f48683873284b169581315b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Mar 2022 21:21:17 +0200 Subject: net: mscc: ocelot: fix backwards compatibility with single-chain tc-flower offload ACL rules can be offloaded to VCAP IS2 either through chain 0, or, since the blamed commit, through a chain index whose number encodes a specific PAG (Policy Action Group) and lookup number. The chain number is translated through ocelot_chain_to_pag() into a PAG, and through ocelot_chain_to_lookup() into a lookup number. The problem with the blamed commit is that the above 2 functions don't have special treatment for chain 0. So ocelot_chain_to_pag(0) returns filter->pag = 224, which is in fact -32, but the "pag" field is an u8. So we end up programming the hardware with VCAP IS2 entries having a PAG of 224. But the way in which the PAG works is that it defines a subset of VCAP IS2 filters which should match on a packet. The default PAG is 0, and previous VCAP IS1 rules (which we offload using 'goto') can modify it. So basically, we are installing filters with a PAG on which no packet will ever match. This is the hardware equivalent of adding filters to a chain which has no 'goto' to it. Restore the previous functionality by making ACL filters offloaded to chain 0 go to PAG 0 and lookup number 0. The choice of PAG is clearly correct, but the choice of lookup number isn't "as before" (which was to leave the lookup a "don't care"). However, lookup 0 should be fine, since even though there are ACL actions (policers) which have a requirement to be used in a specific lookup, that lookup is 0. Fixes: 226e9cd82a96 ("net: mscc: ocelot: only install TCAM entries into a specific lookup and PAG") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20220316192117.2568261-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot_flower.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 949858891973..fdb4d7e7296c 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -60,6 +60,12 @@ static int ocelot_chain_to_block(int chain, bool ingress) */ static int ocelot_chain_to_lookup(int chain) { + /* Backwards compatibility with older, single-chain tc-flower + * offload support in Ocelot + */ + if (chain == 0) + return 0; + return (chain / VCAP_LOOKUP) % 10; } @@ -68,7 +74,15 @@ static int ocelot_chain_to_lookup(int chain) */ static int ocelot_chain_to_pag(int chain) { - int lookup = ocelot_chain_to_lookup(chain); + int lookup; + + /* Backwards compatibility with older, single-chain tc-flower + * offload support in Ocelot + */ + if (chain == 0) + return 0; + + lookup = ocelot_chain_to_lookup(chain); /* calculate PAG value as chain index relative to the first PAG */ return chain - VCAP_IS2_CHAIN(lookup, 0); -- cgit v1.2.3 From b04683ff8f0823b869c219c78ba0d974bddea0b5 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 17 Mar 2022 11:45:24 +0100 Subject: iavf: Fix hang during reboot/shutdown Recent commit 974578017fc1 ("iavf: Add waiting so the port is initialized in remove") adds a wait-loop at the beginning of iavf_remove() to ensure that port initialization is finished prior unregistering net device. This causes a regression in reboot/shutdown scenario because in this case callback iavf_shutdown() is called and this callback detaches the device, makes it down if it is running and sets its state to __IAVF_REMOVE. Later shutdown callback of associated PF driver (e.g. ice_shutdown) is called. That callback calls among other things sriov_disable() that calls indirectly iavf_remove() (see stack trace below). As the adapter state is already __IAVF_REMOVE then the mentioned loop is end-less and shutdown process hangs. The patch fixes this by checking adapter's state at the beginning of iavf_remove() and skips the rest of the function if the adapter is already in remove state (shutdown is in progress). Reproducer: 1. Create VF on PF driven by ice or i40e driver 2. Ensure that the VF is bound to iavf driver 3. Reboot [52625.981294] sysrq: SysRq : Show Blocked State [52625.988377] task:reboot state:D stack: 0 pid:17359 ppid: 1 f2 [52625.996732] Call Trace: [52625.999187] __schedule+0x2d1/0x830 [52626.007400] schedule+0x35/0xa0 [52626.010545] schedule_hrtimeout_range_clock+0x83/0x100 [52626.020046] usleep_range+0x5b/0x80 [52626.023540] iavf_remove+0x63/0x5b0 [iavf] [52626.027645] pci_device_remove+0x3b/0xc0 [52626.031572] device_release_driver_internal+0x103/0x1f0 [52626.036805] pci_stop_bus_device+0x72/0xa0 [52626.040904] pci_stop_and_remove_bus_device+0xe/0x20 [52626.045870] pci_iov_remove_virtfn+0xba/0x120 [52626.050232] sriov_disable+0x2f/0xe0 [52626.053813] ice_free_vfs+0x7c/0x340 [ice] [52626.057946] ice_remove+0x220/0x240 [ice] [52626.061967] ice_shutdown+0x16/0x50 [ice] [52626.065987] pci_device_shutdown+0x34/0x60 [52626.070086] device_shutdown+0x165/0x1c5 [52626.074011] kernel_restart+0xe/0x30 [52626.077593] __do_sys_reboot+0x1d2/0x210 [52626.093815] do_syscall_64+0x5b/0x1a0 [52626.097483] entry_SYSCALL_64_after_hwframe+0x65/0xca Fixes: 974578017fc1 ("iavf: Add waiting so the port is initialized in remove") Signed-off-by: Ivan Vecera Link: https://lore.kernel.org/r/20220317104524.2802848-1-ivecera@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/iavf/iavf_main.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 45570e3f782e..0e178a0a59c5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4620,6 +4620,13 @@ static void iavf_remove(struct pci_dev *pdev) struct iavf_hw *hw = &adapter->hw; int err; + /* When reboot/shutdown is in progress no need to do anything + * as the adapter is already REMOVE state that was set during + * iavf_shutdown() callback. + */ + if (adapter->state == __IAVF_REMOVE) + return; + set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); /* Wait until port initialization is complete. * There are flows where register/unregister netdev may race. -- cgit v1.2.3 From 029c4628b2eb2ca969e9bf979b05dc18d8d5575e Mon Sep 17 00:00:00 2001 From: Guo Ziliang Date: Wed, 16 Mar 2022 16:15:03 -0700 Subject: mm: swap: get rid of livelock in swapin readahead In our testing, a livelock task was found. Through sysrq printing, same stack was found every time, as follows: __swap_duplicate+0x58/0x1a0 swapcache_prepare+0x24/0x30 __read_swap_cache_async+0xac/0x220 read_swap_cache_async+0x58/0xa0 swapin_readahead+0x24c/0x628 do_swap_page+0x374/0x8a0 __handle_mm_fault+0x598/0xd60 handle_mm_fault+0x114/0x200 do_page_fault+0x148/0x4d0 do_translation_fault+0xb0/0xd4 do_mem_abort+0x50/0xb0 The reason for the livelock is that swapcache_prepare() always returns EEXIST, indicating that SWAP_HAS_CACHE has not been cleared, so that it cannot jump out of the loop. We suspect that the task that clears the SWAP_HAS_CACHE flag never gets a chance to run. We try to lower the priority of the task stuck in a livelock so that the task that clears the SWAP_HAS_CACHE flag will run. The results show that the system returns to normal after the priority is lowered. In our testing, multiple real-time tasks are bound to the same core, and the task in the livelock is the highest priority task of the core, so the livelocked task cannot be preempted. Although cond_resched() is used by __read_swap_cache_async, it is an empty function in the preemptive system and cannot achieve the purpose of releasing the CPU. A high-priority task cannot release the CPU unless preempted by a higher-priority task. But when this task is already the highest priority task on this core, other tasks will not be able to be scheduled. So we think we should replace cond_resched() with schedule_timeout_uninterruptible(1), schedule_timeout_interruptible will call set_current_state first to set the task state, so the task will be removed from the running queue, so as to achieve the purpose of giving up the CPU and prevent it from running in kernel mode for too long. (akpm: ugly hack becomes uglier. But it fixes the issue in a backportable-to-stable fashion while we hopefully work on something better) Link: https://lkml.kernel.org/r/20220221111749.1928222-1-cgel.zte@gmail.com Signed-off-by: Guo Ziliang Reported-by: Zeal Robot Reviewed-by: Ran Xiaokai Reviewed-by: Jiang Xuexin Reviewed-by: Yang Yang Acked-by: Hugh Dickins Cc: Naoya Horiguchi Cc: Michal Hocko Cc: Minchan Kim Cc: Johannes Weiner Cc: Roger Quadros Cc: Ziliang Guo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/swap_state.c b/mm/swap_state.c index 8d4104242100..ee67164531c0 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -478,7 +478,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * __read_swap_cache_async(), which has set SWAP_HAS_CACHE * in swap_map, but not yet added its page to swap cache. */ - cond_resched(); + schedule_timeout_uninterruptible(1); } /* -- cgit v1.2.3 From 8208257d2d04d4953a8cb9f1426d245a95c4fea2 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Wed, 16 Mar 2022 16:15:06 -0700 Subject: configs/debug: restore DEBUG_INFO=y for overriding Previously, I failed to realize that Kees' patch [1] has not been merged into the mainline yet, and dropped DEBUG_INFO=y too eagerly from the mainline. As the results, "make debug.config" won't be able to flip DEBUG_INFO=n from the existing .config. This should close the gaps of a few weeks before Kees' patch is there, and work regardless of their merging status anyway. Link: https://lore.kernel.org/all/20220125075126.891825-1-keescook@chromium.org/ [1] Link: https://lkml.kernel.org/r/20220308153524.8618-1-quic_qiancai@quicinc.com Signed-off-by: Qian Cai Reported-by: Daniel Thompson Reviewed-by: Daniel Thompson Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/configs/debug.config | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index 07df6d93c4df..e8db8d938661 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -16,6 +16,7 @@ CONFIG_SYMBOLIC_ERRNAME=y # # Compile-time checks and compiler options # +CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_FRAME_WARN=2048 -- cgit v1.2.3 From 7b0b1332cfdb94489836b67d088a779699f8e47e Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Wed, 16 Mar 2022 16:15:09 -0700 Subject: ocfs2: fix crash when initialize filecheck kobj fails Once s_root is set, genric_shutdown_super() will be called if fill_super() fails. That means, we will call ocfs2_dismount_volume() twice in such case, which can lead to kernel crash. Fix this issue by initializing filecheck kobj before setting s_root. Link: https://lkml.kernel.org/r/20220310081930.86305-1-joseph.qi@linux.alibaba.com Fixes: 5f483c4abb50 ("ocfs2: add kobject for online file check") Signed-off-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/super.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 2772dec9dcea..8bde30fa5387 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1105,17 +1105,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) goto read_super_error; } - root = d_make_root(inode); - if (!root) { - status = -ENOMEM; - mlog_errno(status); - goto read_super_error; - } - - sb->s_root = root; - - ocfs2_complete_mount_recovery(osb); - osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj); if (!osb->osb_dev_kset) { @@ -1133,6 +1122,17 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) goto read_super_error; } + root = d_make_root(inode); + if (!root) { + status = -ENOMEM; + mlog_errno(status); + goto read_super_error; + } + + sb->s_root = root; + + ocfs2_complete_mount_recovery(osb); + if (ocfs2_mount_local(osb)) snprintf(nodestr, sizeof(nodestr), "local"); else -- cgit v1.2.3 From 1c4debc443ef7037dcb7c4f08c33b9caebd21d2e Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Wed, 16 Mar 2022 16:15:12 -0700 Subject: selftests: vm: fix clang build error multiple output files When building the vm selftests using clang, some errors are seen due to having headers in the compilation command: clang -Wall -I ../../../../usr/include -no-pie gup_test.c ../../../../mm/gup_test.h -lrt -lpthread -o .../tools/testing/selftests/vm/gup_test clang: error: cannot specify -o when generating multiple output files make[1]: *** [../lib.mk:146: .../tools/testing/selftests/vm/gup_test] Error 1 Rework to add the header files to LOCAL_HDRS before including ../lib.mk, since the dependency is evaluated in '$(OUTPUT)/%:%.c $(LOCAL_HDRS)' in file lib.mk. Link: https://lkml.kernel.org/r/20220304000645.1888133-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed Cc: Shuah Khan Cc: Nathan Chancellor Cc: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/Makefile | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 1607322a112c..a14b5b800897 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for vm selftests +LOCAL_HDRS += $(selfdir)/vm/local_config.h $(top_srcdir)/mm/gup_test.h + include local_config.mk uname_M := $(shell uname -m 2>/dev/null || echo not) @@ -140,10 +142,6 @@ endif $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap -$(OUTPUT)/gup_test: ../../../../mm/gup_test.h - -$(OUTPUT)/hmm-tests: local_config.h - # HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. $(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS) -- cgit v1.2.3