From ab9177d83c040eba58387914077ebca56f14fae6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2024 22:08:54 +0100 Subject: wifi: mac80211: don't use rate mask for scanning The rate mask is intended for use during operation, and can be set to only have masks for the currently active band. As such, it cannot be used for scanning which can be on other bands as well. Simply ignore the rate masks during scanning to avoid warnings from incorrect settings. Reported-by: syzbot+fdc5123366fb9c3fdc6d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=fdc5123366fb9c3fdc6d Co-developed-by: Dmitry Antipov Signed-off-by: Dmitry Antipov Tested-by: Dmitry Antipov Link: https://msgid.link/20240326220854.9594cbb418ca.I7f86c0ba1f98cf7e27c2bacf6c2d417200ecea5c@changeid Signed-off-by: Johannes Berg --- include/net/mac80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 353488ab94a2..2d7f87bc5324 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -953,6 +953,8 @@ enum mac80211_tx_info_flags { * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment + * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted + * due to scanning, not in normal operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is @@ -973,6 +975,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), + IEEE80211_TX_CTRL_SCAN_TX = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; -- cgit v1.2.3 From ed09f81eeaa8f9265e1787282cb283f10285c259 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Sat, 6 Apr 2024 15:01:09 +0200 Subject: firmware: qcom: uefisecapp: Fix memory related IO errors and crashes It turns out that while the QSEECOM APP_SEND command has specific fields for request and response buffers, uefisecapp expects them both to be in a single memory region. Failure to adhere to this has (so far) resulted in either no response being written to the response buffer (causing an EIO to be emitted down the line), the SCM call to fail with EINVAL (i.e., directly from TZ/firmware), or the device to be hard-reset. While this issue can be triggered deterministically, in the current form it seems to happen rather sporadically (which is why it has gone unnoticed during earlier testing). This is likely due to the two kzalloc() calls (for request and response) being directly after each other. Which means that those likely return consecutive regions most of the time, especially when not much else is going on in the system. Fix this by allocating a single memory region for both request and response buffers, properly aligning both structs inside it. This unfortunately also means that the qcom_scm_qseecom_app_send() interface needs to be restructured, as it should no longer map the DMA regions separately. Therefore, move the responsibility of DMA allocation (or mapping) to the caller. Fixes: 759e7a2b62eb ("firmware: Add support for Qualcomm UEFI Secure Application") Cc: stable@vger.kernel.org # 6.7 Tested-by: Johan Hovold Reviewed-by: Johan Hovold Signed-off-by: Maximilian Luz Tested-by: Konrad Dybcio # X13s Link: https://lore.kernel.org/r/20240406130125.1047436-1-luzmaximilian@gmail.com Signed-off-by: Bjorn Andersson --- drivers/firmware/qcom/qcom_qseecom_uefisecapp.c | 137 ++++++++++++++++-------- drivers/firmware/qcom/qcom_scm.c | 37 ++----- include/linux/firmware/qcom/qcom_qseecom.h | 55 +++++++++- include/linux/firmware/qcom/qcom_scm.h | 10 +- 4 files changed, 153 insertions(+), 86 deletions(-) (limited to 'include') diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c index 32188f098ef3..bc550ad0dbe0 100644 --- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c +++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c @@ -221,6 +221,19 @@ struct qsee_rsp_uefi_query_variable_info { * alignment of 8 bytes (64 bits) for GUIDs. Our definition of efi_guid_t, * however, has an alignment of 4 byte (32 bits). So far, this seems to work * fine here. See also the comment on the typedef of efi_guid_t. + * + * Note: It looks like uefisecapp is quite picky about how the memory passed to + * it is structured and aligned. In particular the request/response setup used + * for QSEE_CMD_UEFI_GET_VARIABLE. While qcom_qseecom_app_send(), in theory, + * accepts separate buffers/addresses for the request and response parts, in + * practice, however, it seems to expect them to be both part of a larger + * contiguous block. We initially allocated separate buffers for the request + * and response but this caused the QSEE_CMD_UEFI_GET_VARIABLE command to + * either not write any response to the response buffer or outright crash the + * device. Therefore, we now allocate a single contiguous block of DMA memory + * for both and properly align the data using the macros below. In particular, + * request and response structs are aligned at 8 byte (via __reqdata_offs()), + * following the driver that this has been reverse-engineered from. */ #define qcuefi_buf_align_fields(fields...) \ ({ \ @@ -244,6 +257,12 @@ struct qsee_rsp_uefi_query_variable_info { #define __array_offs(type, count, offset) \ __field_impl(sizeof(type) * (count), __alignof__(type), offset) +#define __array_offs_aligned(type, count, align, offset) \ + __field_impl(sizeof(type) * (count), align, offset) + +#define __reqdata_offs(size, offset) \ + __array_offs_aligned(u8, size, 8, offset) + #define __array(type, count) __array_offs(type, count, NULL) #define __field_offs(type, offset) __array_offs(type, 1, offset) #define __field(type) __array_offs(type, 1, NULL) @@ -277,10 +296,15 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e unsigned long buffer_size = *data_size; efi_status_t efi_status = EFI_SUCCESS; unsigned long name_length; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t guid_offs; size_t name_offs; size_t req_size; size_t rsp_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name || !guid) @@ -304,17 +328,19 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e __array(u8, buffer_size) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(rsp_size, &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(rsp_size, GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_GET_VARIABLE; req_data->data_size = buffer_size; @@ -332,7 +358,9 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e memcpy(((void *)req_data) + req_data->guid_offset, guid, req_data->guid_size); - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, rsp_size); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -407,9 +435,7 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e memcpy(data, ((void *)rsp_data) + rsp_data->data_offset, rsp_data->data_size); out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -422,10 +448,15 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e struct qsee_rsp_uefi_set_variable *rsp_data; efi_status_t efi_status = EFI_SUCCESS; unsigned long name_length; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t name_offs; size_t guid_offs; size_t data_offs; size_t req_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name || !guid) @@ -450,17 +481,19 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e __array_offs(u8, data_size, &data_offs) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(sizeof(*rsp_data), &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_SET_VARIABLE; req_data->attributes = attributes; @@ -483,8 +516,9 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e if (data_size) memcpy(((void *)req_data) + req_data->data_offset, data, req_data->data_size); - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, - sizeof(*rsp_data)); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, sizeof(*rsp_data)); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -507,9 +541,7 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e } out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -521,10 +553,15 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, struct qsee_req_uefi_get_next_variable *req_data; struct qsee_rsp_uefi_get_next_variable *rsp_data; efi_status_t efi_status = EFI_SUCCESS; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t guid_offs; size_t name_offs; size_t req_size; size_t rsp_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name_size || !name || !guid) @@ -545,17 +582,19 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, __array(*name, *name_size / sizeof(*name)) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(rsp_size, &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(rsp_size, GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_GET_NEXT_VARIABLE; req_data->guid_offset = guid_offs; @@ -572,7 +611,9 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, goto out_free; } - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, rsp_size); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -645,9 +686,7 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, } out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -659,26 +698,34 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, struct qsee_req_uefi_query_variable_info *req_data; struct qsee_rsp_uefi_query_variable_info *rsp_data; efi_status_t efi_status = EFI_SUCCESS; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; + size_t req_offs; + size_t rsp_offs; int status; - req_data = kzalloc(sizeof(*req_data), GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(sizeof(*req_data), &req_offs) + __reqdata_offs(sizeof(*rsp_data), &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_QUERY_VARIABLE_INFO; req_data->attributes = attr; req_data->length = sizeof(*req_data); - status = qcom_qseecom_app_send(qcuefi->client, req_data, sizeof(*req_data), rsp_data, - sizeof(*rsp_data)); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, sizeof(*req_data), + cmd_buf_dma + rsp_offs, sizeof(*rsp_data)); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -711,9 +758,7 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, *max_variable_size = rsp_data->max_variable_size; out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c index 520de9b5633a..90283f160a22 100644 --- a/drivers/firmware/qcom/qcom_scm.c +++ b/drivers/firmware/qcom/qcom_scm.c @@ -1576,9 +1576,9 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); /** * qcom_scm_qseecom_app_send() - Send to and receive data from a given QSEE app. * @app_id: The ID of the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given ID and read back @@ -1589,33 +1589,13 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); * * Return: Zero on success, nonzero on failure. */ -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size) +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { struct qcom_scm_qseecom_resp res = {}; struct qcom_scm_desc desc = {}; - dma_addr_t req_phys; - dma_addr_t rsp_phys; int status; - /* Map request buffer */ - req_phys = dma_map_single(__scm->dev, req, req_size, DMA_TO_DEVICE); - status = dma_mapping_error(__scm->dev, req_phys); - if (status) { - dev_err(__scm->dev, "qseecom: failed to map request buffer\n"); - return status; - } - - /* Map response buffer */ - rsp_phys = dma_map_single(__scm->dev, rsp, rsp_size, DMA_FROM_DEVICE); - status = dma_mapping_error(__scm->dev, rsp_phys); - if (status) { - dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE); - dev_err(__scm->dev, "qseecom: failed to map response buffer\n"); - return status; - } - - /* Set up SCM call data */ desc.owner = QSEECOM_TZ_OWNER_TZ_APPS; desc.svc = QSEECOM_TZ_SVC_APP_ID_PLACEHOLDER; desc.cmd = QSEECOM_TZ_CMD_APP_SEND; @@ -1623,18 +1603,13 @@ int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, QCOM_SCM_RW, QCOM_SCM_VAL, QCOM_SCM_RW, QCOM_SCM_VAL); desc.args[0] = app_id; - desc.args[1] = req_phys; + desc.args[1] = req; desc.args[2] = req_size; - desc.args[3] = rsp_phys; + desc.args[3] = rsp; desc.args[4] = rsp_size; - /* Perform call */ status = qcom_scm_qseecom_call(&desc, &res); - /* Unmap buffers */ - dma_unmap_single(__scm->dev, rsp_phys, rsp_size, DMA_FROM_DEVICE); - dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE); - if (status) return status; diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 5c28298a98be..366243ee9609 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -10,6 +10,7 @@ #define __QCOM_QSEECOM_H #include +#include #include #include @@ -24,12 +25,57 @@ struct qseecom_client { u32 app_id; }; +/** + * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. + * @client: The QSEECOM client device. + * + * Returns the SCM device under which the provided QSEECOM client device + * operates. This function is intended to be used for DMA allocations. + */ +static inline struct device *qseecom_scm_dev(struct qseecom_client *client) +{ + return client->aux_dev.dev.parent->parent; +} + +/** + * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. + * @client: The QSEECOM client to allocate the memory for. + * @size: The number of bytes to allocate. + * @dma_handle: Pointer to where the DMA address should be stored. + * @gfp: Allocation flags. + * + * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for + * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. + */ +static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); +} + +/** + * dma_free_coherent() - Free QSEECOM DMA memory. + * @client: The QSEECOM client for which the memory has been allocated. + * @size: The number of bytes allocated. + * @cpu_addr: Virtual memory address to free. + * @dma_handle: DMA memory address to free. + * + * Wrapper function for dma_free_coherent(), freeing memory previously + * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for + * details. + */ +static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, + void *cpu_addr, dma_addr_t dma_handle) +{ + return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); +} + /** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -43,8 +89,9 @@ struct qseecom_client { * * Return: Zero on success, nonzero on failure. */ -static inline int qcom_qseecom_app_send(struct qseecom_client *client, void *req, size_t req_size, - void *rsp, size_t rsp_size) +static inline int qcom_qseecom_app_send(struct qseecom_client *client, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size); } diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index ccaf28846054..aaa19f93ac43 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -118,8 +118,8 @@ bool qcom_scm_lmh_dcvsh_available(void); #ifdef CONFIG_QCOM_QSEECOM int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id); -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size); +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size); #else /* CONFIG_QCOM_QSEECOM */ @@ -128,9 +128,9 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) return -EINVAL; } -static inline int qcom_scm_qseecom_app_send(u32 app_id, void *req, - size_t req_size, void *rsp, - size_t rsp_size) +static inline int qcom_scm_qseecom_app_send(u32 app_id, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return -EINVAL; } -- cgit v1.2.3 From 32cf5a4eda464d76d553ee3f1b06c4d33d796c52 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 19 Apr 2024 11:51:12 -0400 Subject: Revert "svcrdma: Add Write chunk WRs to the RPC's Send WR chain" Performance regression reported with NFS/RDMA using Omnipath, bisected to commit e084ee673c77 ("svcrdma: Add Write chunk WRs to the RPC's Send WR chain"). Tracing on the server reports: nfsd-7771 [060] 1758.891809: svcrdma_sq_post_err: cq.id=205 cid=226 sc_sq_avail=13643/851 status=-12 sq_post_err reports ENOMEM, and the rdma->sc_sq_avail (13643) is larger than rdma->sc_sq_depth (851). The number of available Send Queue entries is always supposed to be smaller than the Send Queue depth. That seems like a Send Queue accounting bug in svcrdma. As it's getting to be late in the 6.9-rc cycle, revert this commit. It can be revisited in a subsequent kernel release. Link: https://bugzilla.kernel.org/show_bug.cgi?id=218743 Fixes: e084ee673c77 ("svcrdma: Add Write chunk WRs to the RPC's Send WR chain") Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 13 ++---- net/sunrpc/xprtrdma/svc_rdma_rw.c | 86 +++++++++-------------------------- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 5 +- 3 files changed, 26 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24cd199dd6f3..d33bab33099a 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -210,7 +210,6 @@ struct svc_rdma_recv_ctxt { */ struct svc_rdma_write_info { struct svcxprt_rdma *wi_rdma; - struct list_head wi_list; const struct svc_rdma_chunk *wi_chunk; @@ -239,10 +238,7 @@ struct svc_rdma_send_ctxt { struct ib_cqe sc_cqe; struct xdr_buf sc_hdrbuf; struct xdr_stream sc_stream; - - struct list_head sc_write_info_list; struct svc_rdma_write_info sc_reply_info; - void *sc_xprt_buf; int sc_page_count; int sc_cur_sge_no; @@ -274,14 +270,11 @@ extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma, extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma, struct svc_rdma_chunk_ctxt *cc, enum dma_data_direction dir); -extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt); extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt); -extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma, - const struct svc_rdma_pcl *write_pcl, - struct svc_rdma_send_ctxt *sctxt, - const struct xdr_buf *xdr); +extern int svc_rdma_send_write_list(struct svcxprt_rdma *rdma, + const struct svc_rdma_recv_ctxt *rctxt, + const struct xdr_buf *xdr); extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma, const struct svc_rdma_pcl *write_pcl, const struct svc_rdma_pcl *reply_pcl, diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index f2a100c4c81f..40797114d50a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -230,28 +230,6 @@ static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) queue_work(svcrdma_wq, &info->wi_work); } -/** - * svc_rdma_write_chunk_release - Release Write chunk I/O resources - * @rdma: controlling transport - * @ctxt: Send context that is being released - */ -void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt) -{ - struct svc_rdma_write_info *info; - struct svc_rdma_chunk_ctxt *cc; - - while (!list_empty(&ctxt->sc_write_info_list)) { - info = list_first_entry(&ctxt->sc_write_info_list, - struct svc_rdma_write_info, wi_list); - list_del(&info->wi_list); - - cc = &info->wi_cc; - svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); - svc_rdma_write_info_free(info); - } -} - /** * svc_rdma_reply_chunk_release - Release Reply chunk I/O resources * @rdma: controlling transport @@ -308,11 +286,13 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_chunk_ctxt *cc = container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe); + struct svc_rdma_write_info *info = + container_of(cc, struct svc_rdma_write_info, wi_cc); switch (wc->status) { case IB_WC_SUCCESS: trace_svcrdma_wc_write(&cc->cc_cid); - return; + break; case IB_WC_WR_FLUSH_ERR: trace_svcrdma_wc_write_flush(wc, &cc->cc_cid); break; @@ -320,11 +300,12 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_write_err(wc, &cc->cc_cid); } - /* The RDMA Write has flushed, so the client won't get - * some of the outgoing RPC message. Signal the loss - * to the client by closing the connection. - */ - svc_xprt_deferred_close(&rdma->sc_xprt); + svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); + + if (unlikely(wc->status != IB_WC_SUCCESS)) + svc_xprt_deferred_close(&rdma->sc_xprt); + + svc_rdma_write_info_free(info); } /** @@ -620,19 +601,13 @@ static int svc_rdma_xb_write(const struct xdr_buf *xdr, void *data) return xdr->len; } -/* Link Write WRs for @chunk onto @sctxt's WR chain. - */ -static int svc_rdma_prepare_write_chunk(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *sctxt, - const struct svc_rdma_chunk *chunk, - const struct xdr_buf *xdr) +static int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, + const struct svc_rdma_chunk *chunk, + const struct xdr_buf *xdr) { struct svc_rdma_write_info *info; struct svc_rdma_chunk_ctxt *cc; - struct ib_send_wr *first_wr; struct xdr_buf payload; - struct list_head *pos; - struct ib_cqe *cqe; int ret; if (xdr_buf_subsegment(xdr, &payload, chunk->ch_position, @@ -648,25 +623,10 @@ static int svc_rdma_prepare_write_chunk(struct svcxprt_rdma *rdma, if (ret != payload.len) goto out_err; - ret = -EINVAL; - if (unlikely(cc->cc_sqecount > rdma->sc_sq_depth)) - goto out_err; - - first_wr = sctxt->sc_wr_chain; - cqe = &cc->cc_cqe; - list_for_each(pos, &cc->cc_rwctxts) { - struct svc_rdma_rw_ctxt *rwc; - - rwc = list_entry(pos, struct svc_rdma_rw_ctxt, rw_list); - first_wr = rdma_rw_ctx_wrs(&rwc->rw_ctx, rdma->sc_qp, - rdma->sc_port_num, cqe, first_wr); - cqe = NULL; - } - sctxt->sc_wr_chain = first_wr; - sctxt->sc_sqecount += cc->cc_sqecount; - list_add(&info->wi_list, &sctxt->sc_write_info_list); - trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount); + ret = svc_rdma_post_chunk_ctxt(rdma, cc); + if (ret < 0) + goto out_err; return 0; out_err: @@ -675,27 +635,25 @@ out_err: } /** - * svc_rdma_prepare_write_list - Construct WR chain for sending Write list + * svc_rdma_send_write_list - Send all chunks on the Write list * @rdma: controlling RDMA transport - * @write_pcl: Write list provisioned by the client - * @sctxt: Send WR resources + * @rctxt: Write list provisioned by the client * @xdr: xdr_buf containing an RPC Reply message * * Returns zero on success, or a negative errno if one or more * Write chunks could not be sent. */ -int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma, - const struct svc_rdma_pcl *write_pcl, - struct svc_rdma_send_ctxt *sctxt, - const struct xdr_buf *xdr) +int svc_rdma_send_write_list(struct svcxprt_rdma *rdma, + const struct svc_rdma_recv_ctxt *rctxt, + const struct xdr_buf *xdr) { struct svc_rdma_chunk *chunk; int ret; - pcl_for_each_chunk(chunk, write_pcl) { + pcl_for_each_chunk(chunk, &rctxt->rc_write_pcl) { if (!chunk->ch_payload_length) break; - ret = svc_rdma_prepare_write_chunk(rdma, sctxt, chunk, xdr); + ret = svc_rdma_send_write_chunk(rdma, chunk, xdr); if (ret < 0) return ret; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index dfca39abd16c..bb5436b719e0 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -142,7 +142,6 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma) ctxt->sc_send_wr.sg_list = ctxt->sc_sges; ctxt->sc_send_wr.send_flags = IB_SEND_SIGNALED; ctxt->sc_cqe.done = svc_rdma_wc_send; - INIT_LIST_HEAD(&ctxt->sc_write_info_list); ctxt->sc_xprt_buf = buffer; xdr_buf_init(&ctxt->sc_hdrbuf, ctxt->sc_xprt_buf, rdma->sc_max_req_size); @@ -228,7 +227,6 @@ static void svc_rdma_send_ctxt_release(struct svcxprt_rdma *rdma, struct ib_device *device = rdma->sc_cm_id->device; unsigned int i; - svc_rdma_write_chunk_release(rdma, ctxt); svc_rdma_reply_chunk_release(rdma, ctxt); if (ctxt->sc_page_count) @@ -1015,8 +1013,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) if (!p) goto put_ctxt; - ret = svc_rdma_prepare_write_list(rdma, &rctxt->rc_write_pcl, sctxt, - &rqstp->rq_res); + ret = svc_rdma_send_write_list(rdma, rctxt, &rqstp->rq_res); if (ret < 0) goto put_ctxt; -- cgit v1.2.3 From 98a821546b3919a10a58faa12ebe5e9a55cd638e Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 15 Apr 2024 19:10:47 +0800 Subject: vDPA: code clean for vhost_vdpa uapi This commit cleans up the uapi for vhost_vdpa by better naming some of the enums which report blk information to user space, and they are not in any official releases yet. Fixes: 1ac61ddfee93 ("vDPA: report virtio-blk flush info to user space") Fixes: ae1374b7f72c ("vDPA: report virtio-block read-only info to user space") Fixes: 330b8aea6924 ("vDPA: report virtio-block max segment size to user space") Signed-off-by: Zhu Lingshan Message-Id: <20240415111047.1047774-1-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 6 +++--- include/uapi/linux/vdpa.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index b246067e074b..6cb96a1e8b7d 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -967,7 +967,7 @@ vdpa_dev_blk_seg_size_config_fill(struct sk_buff *msg, u64 features, val_u32 = __virtio32_to_cpu(true, config->size_max); - return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, val_u32); + return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SIZE_MAX, val_u32); } /* fill the block size*/ @@ -1089,7 +1089,7 @@ static int vdpa_dev_blk_ro_config_fill(struct sk_buff *msg, u64 features) u8 ro; ro = ((features & BIT_ULL(VIRTIO_BLK_F_RO)) == 0) ? 0 : 1; - if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, ro)) + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_READ_ONLY, ro)) return -EMSGSIZE; return 0; @@ -1100,7 +1100,7 @@ static int vdpa_dev_blk_flush_config_fill(struct sk_buff *msg, u64 features) u8 flush; flush = ((features & BIT_ULL(VIRTIO_BLK_F_FLUSH)) == 0) ? 0 : 1; - if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_FLUSH, flush)) + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_FLUSH, flush)) return -EMSGSIZE; return 0; diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 43c51698195c..842bf1201ac4 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -57,7 +57,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_FEATURES, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ - VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_SIZE_MAX, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, /* u16 */ @@ -70,8 +70,8 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ - VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, /* u8 */ - VDPA_ATTR_DEV_BLK_CFG_FLUSH, /* u8 */ + VDPA_ATTR_DEV_BLK_READ_ONLY, /* u8 */ + VDPA_ATTR_DEV_BLK_FLUSH, /* u8 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 3584718cf2ec7e79b6814f2596dcf398c5fb2eca Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 21 Apr 2024 17:52:48 +0000 Subject: net: fix sk_memory_allocated_{add|sub} vs softirqs Jonathan Heathcote reported a regression caused by blamed commit on aarch64 architecture. x86 happens to have irq-safe __this_cpu_add_return() and __this_cpu_sub(), but this is not generic. I think my confusion came from "struct sock" argument, because these helpers are called with a locked socket. But the memory accounting is per-proto (and per-cpu after the blamed commit). We might cleanup these helpers later to directly accept a "struct proto *proto" argument. Switch to this_cpu_add_return() and this_cpu_xchg() operations, and get rid of preempt_disable()/preempt_enable() pairs. Fast path becomes a bit faster as a result :) Many thanks to Jonathan Heathcote for his awesome report and investigations. Fixes: 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated") Reported-by: Jonathan Heathcote Closes: https://lore.kernel.org/netdev/VI1PR01MB42407D7947B2EA448F1E04EFD10D2@VI1PR01MB4240.eurprd01.prod.exchangelabs.com/ Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Shakeel Butt Link: https://lore.kernel.org/r/20240421175248.1692552-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index f57bfd8a2ad2..b4b553df7870 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1410,32 +1410,34 @@ sk_memory_allocated(const struct sock *sk) #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) extern int sysctl_mem_pcpu_rsv; +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} + static inline void -sk_memory_allocated_add(struct sock *sk, int amt) +sk_memory_allocated_add(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve >= READ_ONCE(sysctl_mem_pcpu_rsv)) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } static inline void -sk_memory_allocated_sub(struct sock *sk, int amt) +sk_memory_allocated_sub(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve <= -READ_ONCE(sysctl_mem_pcpu_rsv)) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 -- cgit v1.2.3 From 2e7ed5f5e69b6fe93dd3c6b651d041e0a7a456d1 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 5 Apr 2024 16:40:33 -0400 Subject: Bluetooth: hci_sync: Use advertised PHYs on hci_le_ext_create_conn_sync The extended advertising reports do report the PHYs so this store then in hci_conn so it can be later used in hci_le_ext_create_conn_sync to narrow the PHYs to be scanned since the controller will also perform a scan having a smaller set of PHYs shall reduce the time it takes to find and connect peers. Fixes: 288c90224eec ("Bluetooth: Enable all supported LE PHY by default") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 4 +++- net/bluetooth/hci_conn.c | 6 ++++-- net/bluetooth/hci_event.c | 20 ++++++++++++-------- net/bluetooth/hci_sync.c | 9 ++++++--- net/bluetooth/l2cap_core.c | 2 +- 5 files changed, 26 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 56fb42df44a3..02af7d7013da 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -738,6 +738,8 @@ struct hci_conn { __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; __u16 le_per_adv_data_len; __u16 le_per_adv_data_offset; + __u8 le_adv_phy; + __u8 le_adv_sec_phy; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; @@ -1512,7 +1514,7 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role); + u16 conn_timeout, u8 role, u8 phy, u8 sec_phy); void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3ad74f76983b..05346250f719 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1263,7 +1263,7 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role) + u16 conn_timeout, u8 role, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct smp_irk *irk; @@ -1326,6 +1326,8 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, conn->dst_type = dst_type; conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; + conn->le_adv_phy = phy; + conn->le_adv_sec_phy = sec_phy; err = hci_connect_le_sync(hdev, conn); if (err) { @@ -2273,7 +2275,7 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, le = hci_connect_le(hdev, dst, dst_type, false, BT_SECURITY_LOW, HCI_LE_CONN_TIMEOUT, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, 0, 0); else le = hci_connect_le_scan(hdev, dst, dst_type, BT_SECURITY_LOW, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index a8b8cfebe018..4d70402e295f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6038,7 +6038,7 @@ static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, void *data, static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, bool addr_resolved, - u8 adv_type) + u8 adv_type, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct hci_conn_params *params; @@ -6093,7 +6093,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, conn = hci_connect_le(hdev, addr, addr_type, addr_resolved, BT_SECURITY_LOW, hdev->def_le_autoconnect_timeout, - HCI_ROLE_MASTER); + HCI_ROLE_MASTER, phy, sec_phy); if (!IS_ERR(conn)) { /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned * by higher layer that tried to connect, if no then @@ -6128,8 +6128,9 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len, - bool ext_adv, bool ctl_time, u64 instant) + u8 direct_addr_type, u8 phy, u8 sec_phy, s8 rssi, + u8 *data, u8 len, bool ext_adv, bool ctl_time, + u64 instant) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -6217,7 +6218,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * for advertising reports) and is already verified to be RPA above. */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, - type); + type, phy, sec_phy); if (!ext_adv && conn && type == LE_ADV_IND && len <= max_adv_len(hdev)) { /* Store report for later inclusion by @@ -6363,7 +6364,8 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, - info->bdaddr_type, NULL, 0, rssi, + info->bdaddr_type, NULL, 0, + HCI_ADV_PHY_1M, 0, rssi, info->data, info->length, false, false, instant); } else { @@ -6448,6 +6450,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, info->bdaddr_type, NULL, 0, + info->primary_phy, + info->secondary_phy, info->rssi, info->data, info->length, !(evt_type & LE_EXT_ADV_LEGACY_PDU), false, instant); @@ -6730,8 +6734,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, &info->direct_addr, - info->direct_addr_type, info->rssi, NULL, 0, - false, false, instant); + info->direct_addr_type, HCI_ADV_PHY_1M, 0, + info->rssi, NULL, 0, false, false, instant); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c5d8799046cc..4c707eb64e6f 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6346,7 +6346,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen = sizeof(*cp); - if (scan_1m(hdev)) { + if (scan_1m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_1M || + conn->le_adv_sec_phy == HCI_ADV_PHY_1M)) { cp->phys |= LE_SCAN_PHY_1M; set_ext_conn_params(conn, p); @@ -6354,7 +6355,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_2m(hdev)) { + if (scan_2m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_2M || + conn->le_adv_sec_phy == HCI_ADV_PHY_2M)) { cp->phys |= LE_SCAN_PHY_2M; set_ext_conn_params(conn, p); @@ -6362,7 +6364,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_coded(hdev)) { + if (scan_coded(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_CODED || + conn->le_adv_sec_phy == HCI_ADV_PHY_CODED)) { cp->phys |= LE_SCAN_PHY_CODED; set_ext_conn_params(conn, p); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index dc0897408793..84fc70862d78 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7018,7 +7018,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) hcon = hci_connect_le(hdev, dst, dst_type, false, chan->sec_level, timeout, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, 0, 0); else hcon = hci_connect_le_scan(hdev, dst, dst_type, chan->sec_level, timeout, -- cgit v1.2.3 From a9a830a676a9a93c5020f5c61236166931fa4266 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 15 Apr 2024 13:41:01 -0400 Subject: Bluetooth: hci_event: Fix sending HCI_OP_READ_ENC_KEY_SIZE The code shall always check if HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE has been set before attempting to use HCI_OP_READ_ENC_KEY_SIZE. Fixes: c569242cd492 ("Bluetooth: hci_event: set the conn encrypted before conn establishes") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 4 ++++ net/bluetooth/hci_event.c | 5 ++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 02af7d7013da..e8f581f3f3ce 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1907,6 +1907,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) +#define read_key_size_capable(dev) \ + ((dev)->commands[20] & 0x10 && \ + !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) + /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4d70402e295f..4a27e4a17a67 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3218,7 +3218,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, if (key) { set_bit(HCI_CONN_ENCRYPT, &conn->flags); - if (!(hdev->commands[20] & 0x10)) { + if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; } else { cp.handle = cpu_to_le16(conn->handle); @@ -3666,8 +3666,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, * controller really supports it. If it doesn't, assume * the default size (16). */ - if (!(hdev->commands[20] & 0x10) || - test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) { + if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; goto notify; } -- cgit v1.2.3 From 12bbaae7635a56049779db3bef6e7140d9aa5f67 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 21 Mar 2024 14:24:40 +0000 Subject: mm: create FOLIO_FLAG_FALSE and FOLIO_TYPE_OPS macros Following the separation of FOLIO_FLAGS from PAGEFLAGS, separate FOLIO_FLAG_FALSE from PAGEFLAG_FALSE and FOLIO_TYPE_OPS from PAGE_TYPE_OPS. Link: https://lkml.kernel.org/r/20240321142448.1645400-3-willy@infradead.org Fixes: 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Miaohe Lin Cc: Muchun Song Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 70 +++++++++++++++++++++++++++++++--------------- 1 file changed, 47 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 652d77805e99..dc1607f1415e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -458,30 +458,51 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) +#define FOLIO_TEST_FLAG_FALSE(name) \ +static inline bool folio_test_##name(const struct folio *folio) \ +{ return false; } +#define FOLIO_SET_FLAG_NOOP(name) \ +static inline void folio_set_##name(struct folio *folio) { } +#define FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void folio_clear_##name(struct folio *folio) { } +#define __FOLIO_SET_FLAG_NOOP(name) \ +static inline void __folio_set_##name(struct folio *folio) { } +#define __FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void __folio_clear_##name(struct folio *folio) { } +#define FOLIO_TEST_SET_FLAG_FALSE(name) \ +static inline bool folio_test_set_##name(struct folio *folio) \ +{ return false; } +#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ +static inline bool folio_test_clear_##name(struct folio *folio) \ +{ return false; } + +#define FOLIO_FLAG_FALSE(name) \ +FOLIO_TEST_FLAG_FALSE(name) \ +FOLIO_SET_FLAG_NOOP(name) \ +FOLIO_CLEAR_FLAG_NOOP(name) + #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ +FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_set_##lname(struct folio *folio) { } \ +FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_clear_##lname(struct folio *folio) { } \ +FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void __folio_clear_##lname(struct folio *folio) { } \ +__FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ -static inline bool folio_test_set_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ -static inline bool folio_test_clear_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ @@ -977,35 +998,38 @@ static inline int page_has_type(const struct page *page) return page_type_has_type(page->page_type); } +#define FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline bool folio_test_##fname(const struct folio *folio)\ +{ \ + return folio_test_type(folio, PG_##lname); \ +} \ +static __always_inline void __folio_set_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ + folio->page.page_type &= ~PG_##lname; \ +} \ +static __always_inline void __folio_clear_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ + folio->page.page_type |= PG_##lname; \ +} + #define PAGE_TYPE_OPS(uname, lname, fname) \ +FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ -static __always_inline int folio_test_##fname(const struct folio *folio)\ -{ \ - return folio_test_type(folio, PG_##lname); \ -} \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ -static __always_inline void __folio_set_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ - folio->page.page_type &= ~PG_##lname; \ -} \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ -} \ -static __always_inline void __folio_clear_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ -} \ +} /* * PageBuddy() indicates that the page is free and in the buddy system -- cgit v1.2.3 From fd1a745ce03e37945674c14833870a9af0882e2d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 21 Mar 2024 14:24:42 +0000 Subject: mm: support page_mapcount() on page_has_type() pages Return 0 for pages which can't be mapped. This matches how page_mapped() works. It is more convenient for users to not have to filter out these pages. Link: https://lkml.kernel.org/r/20240321142448.1645400-5-willy@infradead.org Fixes: 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Miaohe Lin Cc: Muchun Song Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- fs/proc/page.c | 7 ++----- include/linux/mm.h | 8 +++++--- include/linux/page-flags.h | 4 ++-- 3 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/proc/page.c b/fs/proc/page.c index 195b077c0fac..9223856c934b 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -67,7 +67,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, */ ppage = pfn_to_online_page(pfn); - if (!ppage || PageSlab(ppage) || page_has_type(ppage)) + if (!ppage) pcount = 0; else pcount = page_mapcount(ppage); @@ -124,11 +124,8 @@ u64 stable_page_flags(struct page *page) /* * pseudo flags for the well known (anonymous) memory mapped pages - * - * Note that page->_mapcount is overloaded in SLAB, so the - * simple test in page_mapped() is not enough. */ - if (!PageSlab(page) && page_mapped(page)) + if (page_mapped(page)) u |= 1 << KPF_MMAP; if (PageAnon(page)) u |= 1 << KPF_ANON; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b0ee64225de..b6bdaa18b9e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1223,14 +1223,16 @@ static inline void page_mapcount_reset(struct page *page) * a large folio, it includes the number of times this page is mapped * as part of that folio. * - * The result is undefined for pages which cannot be mapped into userspace. - * For example SLAB or special types of pages. See function page_has_type(). - * They use this field in struct page differently. + * Will report 0 for pages which cannot be mapped into userspace, eg + * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < 0) + mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index dc1607f1415e..35a0087d0910 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -971,12 +971,12 @@ static inline bool is_page_hwpoison(struct page *page) * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of page_mapcount() won't be + * low bits so that an underflow or overflow of _mapcount won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of page_mapcount */ +/* Reserve 0x0000007f to catch underflows of _mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 -- cgit v1.2.3 From d99e3140a4d33e26066183ff727d8f02f56bec64 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 21 Mar 2024 14:24:43 +0000 Subject: mm: turn folio_test_hugetlb into a PageType The current folio_test_hugetlb() can be fooled by a concurrent folio split into returning true for a folio which has never belonged to hugetlbfs. This can't happen if the caller holds a refcount on it, but we have a few places (memory-failure, compaction, procfs) which do not and should not take a speculative reference. Since hugetlb pages do not use individual page mapcounts (they are always fully mapped and use the entire_mapcount field to record the number of mappings), the PageType field is available now that page_mapcount() ignores the value in this field. In compaction and with CONFIG_DEBUG_VM enabled, the current implementation can result in an oops, as reported by Luis. This happens since 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") effectively added some VM_BUG_ON() checks in the PageHuge() testing path. [willy@infradead.org: update vmcoreinfo] Link: https://lkml.kernel.org/r/ZgGZUvsdhaT1Va-T@casper.infradead.org Link: https://lkml.kernel.org/r/20240321142448.1645400-6-willy@infradead.org Fixes: 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Reported-by: Luis Chamberlain Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218227 Cc: Miaohe Lin Cc: Muchun Song Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 70 ++++++++++++++++++++---------------------- include/trace/events/mmflags.h | 1 + kernel/vmcore_info.c | 5 ++- mm/hugetlb.c | 22 ++----------- 4 files changed, 39 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 35a0087d0910..4bf1c25fd1dc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,7 +190,6 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_error, - PG_hugetlb = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -876,29 +875,6 @@ TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) #define PG_head_mask ((1UL << PG_head)) -#ifdef CONFIG_HUGETLB_PAGE -int PageHuge(const struct page *page); -SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) -CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) - -/** - * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs - * @folio: The folio to test. - * - * Context: Any context. Caller should have a reference on the folio to - * prevent it from being turned into a tail page. - * Return: True for hugetlbfs folios, false for anon folios or folios - * belonging to other filesystems. - */ -static inline bool folio_test_hugetlb(const struct folio *folio) -{ - return folio_test_large(folio) && - test_bit(PG_hugetlb, const_folio_flags(folio, 1)); -} -#else -TESTPAGEFLAG_FALSE(Huge, hugetlb) -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -954,18 +930,6 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif -/* - * Check if a page is currently marked HWPoisoned. Note that this check is - * best effort only and inherently racy: there is no way to synchronize with - * failing hardware. - */ -static inline bool is_page_hwpoison(struct page *page) -{ - if (PageHWPoison(page)) - return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); -} - /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the @@ -982,6 +946,7 @@ static inline bool is_page_hwpoison(struct page *page) #define PG_offline 0x00000100 #define PG_table 0x00000200 #define PG_guard 0x00000400 +#define PG_hugetlb 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -1076,6 +1041,37 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) +#ifdef CONFIG_HUGETLB_PAGE +FOLIO_TYPE_OPS(hugetlb, hugetlb) +#else +FOLIO_TEST_FLAG_FALSE(hugetlb) +#endif + +/** + * PageHuge - Determine if the page belongs to hugetlbfs + * @page: The page to test. + * + * Context: Any context. + * Return: True for hugetlbfs pages, false for anon pages or pages + * belonging to other filesystems. + */ +static inline bool PageHuge(const struct page *page) +{ + return folio_test_hugetlb(page_folio(page)); +} + +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(struct page *page) +{ + if (PageHWPoison(page)) + return true; + return PageHuge(page) && PageHWPoison(compound_head(page)); +} + extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); @@ -1142,7 +1138,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index d801409b33cf..d55e53ac91bd 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -135,6 +135,7 @@ IF_HAVE_PG_ARCH_X(arch_3) #define DEF_PAGETYPE_NAME(_name) { PG_##_name, __stringify(_name) } #define __def_pagetype_names \ + DEF_PAGETYPE_NAME(hugetlb), \ DEF_PAGETYPE_NAME(offline), \ DEF_PAGETYPE_NAME(guard), \ DEF_PAGETYPE_NAME(table), \ diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index f95516cd45bb..23c125c2e243 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -205,11 +205,10 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_head_mask); #define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(PG_hugetlb); +#define PAGE_HUGETLB_MAPCOUNT_VALUE (~PG_hugetlb) + VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE); #define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif #ifdef CONFIG_KALLSYMS VMCOREINFO_SYMBOL(kallsyms_names); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 53e0ab5c0845..4553241f0fb2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1624,7 +1624,7 @@ static inline void __clear_hugetlb_destructor(struct hstate *h, { lockdep_assert_held(&hugetlb_lock); - folio_clear_hugetlb(folio); + __folio_clear_hugetlb(folio); } /* @@ -1711,7 +1711,7 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, h->surplus_huge_pages_node[nid]++; } - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above @@ -2049,7 +2049,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); @@ -2159,22 +2159,6 @@ static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, return __prep_compound_gigantic_folio(folio, order, true); } -/* - * PageHuge() only returns true for hugetlbfs pages, but not for normal or - * transparent huge pages. See the PageTransHuge() documentation for more - * details. - */ -int PageHuge(const struct page *page) -{ - const struct folio *folio; - - if (!PageCompound(page)) - return 0; - folio = page_folio(page); - return folio_test_hugetlb(folio); -} -EXPORT_SYMBOL_GPL(PageHuge); - /* * Find and lock address space (mapping) in write mode. * -- cgit v1.2.3 From ce0abef6a1d540acef85068e0e82bdf1fbeeb0e9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 19 Apr 2024 17:05:55 -0700 Subject: cpu: Ignore "mitigations" kernel parameter if CPU_MITIGATIONS=n Explicitly disallow enabling mitigations at runtime for kernels that were built with CONFIG_CPU_MITIGATIONS=n, as some architectures may omit code entirely if mitigations are disabled at compile time. E.g. on x86, a large pile of Kconfigs are buried behind CPU_MITIGATIONS, and trying to provide sane behavior for retroactively enabling mitigations is extremely difficult, bordering on impossible. E.g. page table isolation and call depth tracking require build-time support, BHI mitigations will still be off without additional kernel parameters, etc. [ bp: Touchups. ] Signed-off-by: Sean Christopherson Signed-off-by: Borislav Petkov (AMD) Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240420000556.2645001-3-seanjc@google.com --- Documentation/admin-guide/kernel-parameters.txt | 3 +++ arch/x86/Kconfig | 8 ++++++-- include/linux/cpu.h | 11 +++++++++++ kernel/cpu.c | 14 ++++++++++---- 4 files changed, 30 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 902ecd92a29f..213d0719e2b7 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3423,6 +3423,9 @@ arch-independent options, each of which is an aggregation of existing arch-specific options. + Note, "mitigations" is supported if and only if the + kernel was built with CPU_MITIGATIONS=y. + off Disable all optional CPU mitigations. This improves system performance, but it may also diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 619a04d5c131..928820e61cb5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2495,9 +2495,13 @@ menuconfig CPU_MITIGATIONS help Say Y here to enable options which enable mitigations for hardware vulnerabilities (usually related to speculative execution). + Mitigations can be disabled or restricted to SMT systems at runtime + via the "mitigations" kernel parameter. - If you say N, all mitigations will be disabled. You really - should know what you are doing to say so. + If you say N, all mitigations will be disabled. This CANNOT be + overridden at runtime. + + Say 'Y', unless you really know what you are doing. if CPU_MITIGATIONS diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 272e4e79e15c..861c3bfc5f17 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -221,7 +221,18 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_CPU_MITIGATIONS extern bool cpu_mitigations_off(void); extern bool cpu_mitigations_auto_nosmt(void); +#else +static inline bool cpu_mitigations_off(void) +{ + return true; +} +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return false; +} +#endif #endif /* _LINUX_CPU_H_ */ diff --git a/kernel/cpu.c b/kernel/cpu.c index bb0ff275fb46..63447eb85dab 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -3196,6 +3196,7 @@ void __init boot_cpu_hotplug_init(void) this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } +#ifdef CONFIG_CPU_MITIGATIONS /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. @@ -3206,9 +3207,7 @@ enum cpu_mitigations { CPU_MITIGATIONS_AUTO_NOSMT, }; -static enum cpu_mitigations cpu_mitigations __ro_after_init = - IS_ENABLED(CONFIG_CPU_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : - CPU_MITIGATIONS_OFF; +static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { @@ -3224,7 +3223,6 @@ static int __init mitigations_parse_cmdline(char *arg) return 0; } -early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) @@ -3239,3 +3237,11 @@ bool cpu_mitigations_auto_nosmt(void) return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); +#else +static int __init mitigations_parse_cmdline(char *arg) +{ + pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); + return 0; +} +#endif +early_param("mitigations", mitigations_parse_cmdline); -- cgit v1.2.3 From e877d705704d7c8fe17b6b5ebdfdb14b84c207a7 Mon Sep 17 00:00:00 2001 From: Christian Gmeiner Date: Sat, 20 Apr 2024 15:41:58 +0200 Subject: Revert "drm/etnaviv: Expose a few more chipspecs to userspace" This reverts commit 1dccdba084897443d116508a8ed71e0ac8a031a4. In userspace a different approach was choosen - hwdb. As a result, there is no need for these values. Signed-off-by: Christian Gmeiner Reviewed-by: Tomeu Vizoso Signed-off-by: Lucas Stach --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 20 -------------------- drivers/gpu/drm/etnaviv/etnaviv_gpu.h | 12 ------------ drivers/gpu/drm/etnaviv/etnaviv_hwdb.c | 34 ---------------------------------- include/uapi/drm/etnaviv_drm.h | 5 ----- 4 files changed, 71 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 6f763038c21a..a9bf426f69b3 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -164,26 +164,6 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *value = gpu->identity.eco_id; break; - case ETNAVIV_PARAM_GPU_NN_CORE_COUNT: - *value = gpu->identity.nn_core_count; - break; - - case ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE: - *value = gpu->identity.nn_mad_per_core; - break; - - case ETNAVIV_PARAM_GPU_TP_CORE_COUNT: - *value = gpu->identity.tp_core_count; - break; - - case ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE: - *value = gpu->identity.on_chip_sram_size; - break; - - case ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE: - *value = gpu->identity.axi_sram_size; - break; - default: DBG("%s: invalid param: %u", dev_name(gpu->dev), param); return -EINVAL; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index 7d5e9158e13c..197e0037732e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -54,18 +54,6 @@ struct etnaviv_chip_identity { /* Number of Neural Network cores. */ u32 nn_core_count; - /* Number of MAD units per Neural Network core. */ - u32 nn_mad_per_core; - - /* Number of Tensor Processing cores. */ - u32 tp_core_count; - - /* Size in bytes of the SRAM inside the NPU. */ - u32 on_chip_sram_size; - - /* Size in bytes of the SRAM across the AXI bus. */ - u32 axi_sram_size; - /* Size of the vertex cache. */ u32 vertex_cache_size; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index d8e7334de8ce..8665f2658d51 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -17,10 +17,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 128, .shader_core_count = 1, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 8, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -52,11 +48,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .register_max = 64, .thread_count = 256, .shader_core_count = 1, - .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 8, .vertex_output_buffer_size = 512, .pixel_pipes = 1, @@ -89,10 +80,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 512, .shader_core_count = 2, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -125,10 +112,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 512, .shader_core_count = 2, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -160,11 +143,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .register_max = 64, .thread_count = 512, .shader_core_count = 2, - .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -197,10 +175,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 1024, .shader_core_count = 4, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 2, @@ -233,10 +207,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 256, .shader_core_count = 1, .nn_core_count = 8, - .nn_mad_per_core = 64, - .tp_core_count = 4, - .on_chip_sram_size = 524288, - .axi_sram_size = 1048576, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -269,10 +239,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 256, .shader_core_count = 1, .nn_core_count = 6, - .nn_mad_per_core = 64, - .tp_core_count = 3, - .on_chip_sram_size = 262144, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h index d87410a8443a..af024d90453d 100644 --- a/include/uapi/drm/etnaviv_drm.h +++ b/include/uapi/drm/etnaviv_drm.h @@ -77,11 +77,6 @@ struct drm_etnaviv_timespec { #define ETNAVIV_PARAM_GPU_PRODUCT_ID 0x1c #define ETNAVIV_PARAM_GPU_CUSTOMER_ID 0x1d #define ETNAVIV_PARAM_GPU_ECO_ID 0x1e -#define ETNAVIV_PARAM_GPU_NN_CORE_COUNT 0x1f -#define ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE 0x20 -#define ETNAVIV_PARAM_GPU_TP_CORE_COUNT 0x21 -#define ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE 0x22 -#define ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE 0x23 #define ETNA_MAX_PIPES 4 -- cgit v1.2.3 From 475747a19316b08e856c666a20503e73d7ed67ed Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Tue, 23 Apr 2024 11:13:02 -0700 Subject: macsec: Enable devices to advertise whether they update sk_buff md_dst during offloads Cannot know whether a Rx skb missing md_dst is intended for MACsec or not without knowing whether the device is able to update this field during an offload. Assume that an offload to a MACsec device cannot support updating md_dst by default. Capable devices can advertise that they do indicate that an skb is related to a MACsec offloaded packet using the md_dst. Cc: Sabrina Dubroca Cc: stable@vger.kernel.org Fixes: 860ead89b851 ("net/macsec: Add MACsec skb_metadata_dst Rx Data path support") Signed-off-by: Rahul Rameshbabu Reviewed-by: Benjamin Poirier Reviewed-by: Cosmin Ratiu Reviewed-by: Sabrina Dubroca Link: https://lore.kernel.org/r/20240423181319.115860-2-rrameshbabu@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/macsec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/macsec.h b/include/net/macsec.h index dbd22180cc5c..de216cbc6b05 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -321,6 +321,7 @@ struct macsec_context { * for the TX tag * @needed_tailroom: number of bytes reserved at the end of the sk_buff for the * TX tag + * @rx_uses_md_dst: whether MACsec device offload supports sk_buff md_dst */ struct macsec_ops { /* Device wide */ @@ -352,6 +353,7 @@ struct macsec_ops { struct sk_buff *skb); unsigned int needed_headroom; unsigned int needed_tailroom; + bool rx_uses_md_dst; }; void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa); -- cgit v1.2.3 From 6e159fd653d7ebf6290358e0330a0cb8a75cf73b Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Tue, 23 Apr 2024 11:13:03 -0700 Subject: ethernet: Add helper for assigning packet type when dest address does not match device address Enable reuse of logic in eth_type_trans for determining packet type. Suggested-by: Sabrina Dubroca Cc: stable@vger.kernel.org Signed-off-by: Rahul Rameshbabu Reviewed-by: Sabrina Dubroca Link: https://lore.kernel.org/r/20240423181319.115860-3-rrameshbabu@nvidia.com Signed-off-by: Jakub Kicinski --- include/linux/etherdevice.h | 25 +++++++++++++++++++++++++ net/ethernet/eth.c | 12 +----------- 2 files changed, 26 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 224645f17c33..297231854ada 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -607,6 +607,31 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, eth_hw_addr_set(dev, addr); } +/** + * eth_skb_pkt_type - Assign packet type if destination address does not match + * @skb: Assigned a packet type if address does not match @dev address + * @dev: Network device used to compare packet address against + * + * If the destination MAC address of the packet does not match the network + * device address, assign an appropriate packet type. + */ +static inline void eth_skb_pkt_type(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct ethhdr *eth = eth_hdr(skb); + + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + skb->pkt_type = PACKET_OTHERHOST; + } + } +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 2edc8b796a4e..049c3adeb850 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -164,17 +164,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); - if (unlikely(!ether_addr_equal_64bits(eth->h_dest, - dev->dev_addr))) { - if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { - if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) - skb->pkt_type = PACKET_BROADCAST; - else - skb->pkt_type = PACKET_MULTICAST; - } else { - skb->pkt_type = PACKET_OTHERHOST; - } - } + eth_skb_pkt_type(skb, dev); /* * Some variants of DSA tagging don't have an ethertype field -- cgit v1.2.3 From 0844370f8945086eb9335739d10205dcea8d707b Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 24 Apr 2024 12:25:47 +0200 Subject: tls: fix lockless read of strp->msg_ready in ->poll tls_sk_poll is called without locking the socket, and needs to read strp->msg_ready (via tls_strp_msg_ready). Convert msg_ready to a bool and use READ_ONCE/WRITE_ONCE where needed. The remaining reads are only performed when the socket is locked. Fixes: 121dca784fc0 ("tls: suppress wakeups unless we have a full record") Signed-off-by: Sabrina Dubroca Link: https://lore.kernel.org/r/0b7ee062319037cf86af6b317b3d72f7bfcd2e97.1713797701.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- include/net/tls.h | 3 ++- net/tls/tls.h | 2 +- net/tls/tls_strp.c | 6 +++--- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 340ad43971e4..33f657d3c051 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -111,7 +111,8 @@ struct tls_strparser { u32 stopped : 1; u32 copy_mode : 1; u32 mixed_decrypted : 1; - u32 msg_ready : 1; + + bool msg_ready; struct strp_msg stm; diff --git a/net/tls/tls.h b/net/tls/tls.h index 762f424ff2d5..e5e47452308a 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -215,7 +215,7 @@ static inline struct sk_buff *tls_strp_msg(struct tls_sw_context_rx *ctx) static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) { - return ctx->strp.msg_ready; + return READ_ONCE(ctx->strp.msg_ready); } static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index ca1e0e198ceb..5df08d848b5c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -360,7 +360,7 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); } @@ -528,7 +528,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); return 0; @@ -580,7 +580,7 @@ void tls_strp_msg_done(struct tls_strparser *strp) else tls_strp_flush_anchor_copy(strp); - strp->msg_ready = 0; + WRITE_ONCE(strp->msg_ready, 0); memset(&strp->stm, 0, sizeof(strp->stm)); tls_strp_check_rcv(strp); -- cgit v1.2.3 From 1971d13ffa84a551d29a81fdf5b5ec5be166ac83 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 24 Apr 2024 10:04:43 -0700 Subject: af_unix: Suppress false-positive lockdep splat for spin_lock() in __unix_gc(). syzbot reported a lockdep splat regarding unix_gc_lock and unix_state_lock(). One is called from recvmsg() for a connected socket, and another is called from GC for TCP_LISTEN socket. So, the splat is false-positive. Let's add a dedicated lock class for the latter to suppress the splat. Note that this change is not necessary for net-next.git as the issue is only applied to the old GC impl. [0]: WARNING: possible circular locking dependency detected 6.9.0-rc5-syzkaller-00007-g4d2008430ce8 #0 Not tainted ----------------------------------------------------- kworker/u8:1/11 is trying to acquire lock: ffff88807cea4e70 (&u->lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff88807cea4e70 (&u->lock){+.+.}-{2:2}, at: __unix_gc+0x40e/0xf70 net/unix/garbage.c:302 but task is already holding lock: ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: __unix_gc+0x117/0xf70 net/unix/garbage.c:261 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (unix_gc_lock){+.+.}-{2:2}: lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] unix_notinflight+0x13d/0x390 net/unix/garbage.c:140 unix_detach_fds net/unix/af_unix.c:1819 [inline] unix_destruct_scm+0x221/0x350 net/unix/af_unix.c:1876 skb_release_head_state+0x100/0x250 net/core/skbuff.c:1188 skb_release_all net/core/skbuff.c:1200 [inline] __kfree_skb net/core/skbuff.c:1216 [inline] kfree_skb_reason+0x16d/0x3b0 net/core/skbuff.c:1252 kfree_skb include/linux/skbuff.h:1262 [inline] manage_oob net/unix/af_unix.c:2672 [inline] unix_stream_read_generic+0x1125/0x2700 net/unix/af_unix.c:2749 unix_stream_splice_read+0x239/0x320 net/unix/af_unix.c:2981 do_splice_read fs/splice.c:985 [inline] splice_file_to_pipe+0x299/0x500 fs/splice.c:1295 do_splice+0xf2d/0x1880 fs/splice.c:1379 __do_splice fs/splice.c:1436 [inline] __do_sys_splice fs/splice.c:1652 [inline] __se_sys_splice+0x331/0x4a0 fs/splice.c:1634 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f -> #0 (&u->lock){+.+.}-{2:2}: check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18cb/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] __unix_gc+0x40e/0xf70 net/unix/garbage.c:302 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa10/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f0/0x390 kernel/kthread.c:388 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(unix_gc_lock); lock(&u->lock); lock(unix_gc_lock); lock(&u->lock); *** DEADLOCK *** 3 locks held by kworker/u8:1/11: #0: ffff888015089148 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3229 [inline] #0: ffff888015089148 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_scheduled_works+0x8e0/0x17c0 kernel/workqueue.c:3335 #1: ffffc90000107d00 (unix_gc_work){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3230 [inline] #1: ffffc90000107d00 (unix_gc_work){+.+.}-{0:0}, at: process_scheduled_works+0x91b/0x17c0 kernel/workqueue.c:3335 #2: ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] #2: ffffffff8f6ab638 (unix_gc_lock){+.+.}-{2:2}, at: __unix_gc+0x117/0xf70 net/unix/garbage.c:261 stack backtrace: CPU: 0 PID: 11 Comm: kworker/u8:1 Not tainted 6.9.0-rc5-syzkaller-00007-g4d2008430ce8 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Workqueue: events_unbound __unix_gc Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 check_noncircular+0x36a/0x4a0 kernel/locking/lockdep.c:2187 check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18cb/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] __unix_gc+0x40e/0xf70 net/unix/garbage.c:302 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa10/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f0/0x390 kernel/kthread.c:388 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Fixes: 47d8ac011fe1 ("af_unix: Fix garbage collector racing against connect()") Reported-and-tested-by: syzbot+fa379358c28cc87cc307@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=fa379358c28cc87cc307 Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20240424170443.9832-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/af_unix.h | 3 +++ net/unix/garbage.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 627ea8e2d915..3dee0b2721aa 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -85,6 +85,9 @@ enum unix_socket_lock_class { U_LOCK_NORMAL, U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ + U_LOCK_GC_LISTENER, /* used for listening socket while determining gc + * candidates to close a small race window. + */ }; static inline void unix_state_lock_nested(struct sock *sk, diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 6433a414acf8..0104be9d4704 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -299,7 +299,7 @@ static void __unix_gc(struct work_struct *work) __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); if (sk->sk_state == TCP_LISTEN) { - unix_state_lock(sk); + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); unix_state_unlock(sk); } } -- cgit v1.2.3 From 2e5449f4f21a1b0bd9beec4c4b580eb1f9b9ed7f Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sat, 27 Apr 2024 15:27:58 +0900 Subject: profiling: Remove create_prof_cpu_mask(). create_prof_cpu_mask() is no longer used after commit 1f44a225777e ("s390: convert interrupt handling to use generic hardirq"). Signed-off-by: Tetsuo Handa Signed-off-by: Linus Torvalds --- include/linux/profile.h | 5 ----- kernel/profile.c | 43 ------------------------------------------- 2 files changed, 48 deletions(-) (limited to 'include') diff --git a/include/linux/profile.h b/include/linux/profile.h index 11db1ec516e2..04ae5ebcb637 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,13 +18,8 @@ struct proc_dir_entry; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) -void create_prof_cpu_mask(void); int create_proc_profile(void); #else -static inline void create_prof_cpu_mask(void) -{ -} - static inline int create_proc_profile(void) { return 0; diff --git a/kernel/profile.c b/kernel/profile.c index 8a77769bc4b4..2b775cc5c28f 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -344,49 +344,6 @@ void profile_tick(int type) #include #include -static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); - return 0; -} - -static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, prof_cpu_mask_proc_show, NULL); -} - -static ssize_t prof_cpu_mask_proc_write(struct file *file, - const char __user *buffer, size_t count, loff_t *pos) -{ - cpumask_var_t new_value; - int err; - - if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) - return -ENOMEM; - - err = cpumask_parse_user(buffer, count, new_value); - if (!err) { - cpumask_copy(prof_cpu_mask, new_value); - err = count; - } - free_cpumask_var(new_value); - return err; -} - -static const struct proc_ops prof_cpu_mask_proc_ops = { - .proc_open = prof_cpu_mask_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = single_release, - .proc_write = prof_cpu_mask_proc_write, -}; - -void create_prof_cpu_mask(void) -{ - /* create /proc/irq/prof_cpu_mask */ - proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops); -} - /* * This function accesses profiling information. The returned data is * binary: the sampling step and the actual contents of the profile -- cgit v1.2.3