From bcce55f556e824d43f352d76b94509185585e38d Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sat, 19 Dec 2020 13:19:24 +0100 Subject: ppp: Fix PPPIOCUNBRIDGECHAN request number PPPIOCGL2TPSTATS already uses 54. This shouldn't be a problem in practice, but let's keep the logical decreasing assignment scheme. Fixes: 4cf476ced45d ("ppp: add PPPIOCBRIDGECHAN and PPPIOCUNBRIDGECHAN ioctls") Signed-off-by: Guillaume Nault Link: https://lore.kernel.org/r/e3a4c355e3820331d8e1fffef8522739aae58b57.1608380117.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ppp-ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h index 8dbecb3ad036..1cc5ce0ae062 100644 --- a/include/uapi/linux/ppp-ioctl.h +++ b/include/uapi/linux/ppp-ioctl.h @@ -116,7 +116,7 @@ struct pppol2tp_ioc_stats { #define PPPIOCGCHAN _IOR('t', 55, int) /* get ppp channel number */ #define PPPIOCGL2TPSTATS _IOR('t', 54, struct pppol2tp_ioc_stats) #define PPPIOCBRIDGECHAN _IOW('t', 53, int) /* bridge one channel to another */ -#define PPPIOCUNBRIDGECHAN _IO('t', 54) /* unbridge channel */ +#define PPPIOCUNBRIDGECHAN _IO('t', 52) /* unbridge channel */ #define SIOCGPPPSTATS (SIOCDEVPRIVATE + 0) #define SIOCGPPPVER (SIOCDEVPRIVATE + 1) /* NEVER change this!! */ -- cgit v1.2.3 From 429f1571e8f0b14ec42b8fb14efcfc0576b2788f Mon Sep 17 00:00:00 2001 From: Alon Mizrahi Date: Tue, 1 Dec 2020 18:44:11 +0200 Subject: habanalabs: add comment for pll frequency ioctl opcode Forgot to add the comment for the opcode when it was added. Signed-off-by: Alon Mizrahi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 8c15a7d336a0..dc8bcec195cc 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -279,6 +279,7 @@ enum hl_device_status { * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason * HL_INFO_SYNC_MANAGER - Retrieve sync manager info per dcore * HL_INFO_TOTAL_ENERGY - Retrieve total energy consumption + * HL_INFO_PLL_FREQUENCY - Retrieve PLL frequency */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 -- cgit v1.2.3 From a3fd28306329e8e82efab973aafe81e9001dcf6f Mon Sep 17 00:00:00 2001 From: Alon Mizrahi Date: Tue, 8 Dec 2020 16:14:01 +0200 Subject: habanalabs: add validation cs counter, fix misplaced counters Up until now validation errors were counted in the parsing field of the cs_counters struct, so we added a new counter and increased it when needed. In addition, there were some locations where only one of the counters was updated (ctx or aggregate) so add the second one to be updated as well. Signed-off-by: Alon Mizrahi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../misc/habanalabs/common/command_submission.c | 75 ++++++++++++++++------ drivers/misc/habanalabs/common/habanalabs.h | 2 + drivers/misc/habanalabs/common/habanalabs_ioctl.c | 5 ++ include/uapi/misc/habanalabs.h | 4 ++ 4 files changed, 68 insertions(+), 18 deletions(-) (limited to 'include/uapi') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 92c1c516b65f..b2b3d2b0f808 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -472,8 +472,11 @@ static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx, cntr = &hdev->aggregated_cs_counters; cs = kzalloc(sizeof(*cs), GFP_ATOMIC); - if (!cs) + if (!cs) { + atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt); + atomic64_inc(&cntr->out_of_mem_drop_cnt); return -ENOMEM; + } cs->ctx = ctx; cs->submitted = false; @@ -486,6 +489,8 @@ static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx, cs_cmpl = kmalloc(sizeof(*cs_cmpl), GFP_ATOMIC); if (!cs_cmpl) { + atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt); + atomic64_inc(&cntr->out_of_mem_drop_cnt); rc = -ENOMEM; goto free_cs; } @@ -513,6 +518,8 @@ static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx, cs->jobs_in_queue_cnt = kcalloc(hdev->asic_prop.max_queues, sizeof(*cs->jobs_in_queue_cnt), GFP_ATOMIC); if (!cs->jobs_in_queue_cnt) { + atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt); + atomic64_inc(&cntr->out_of_mem_drop_cnt); rc = -ENOMEM; goto free_fence; } @@ -764,11 +771,14 @@ static int hl_cs_sanity_checks(struct hl_fpriv *hpriv, union hl_cs_args *args) static int hl_cs_copy_chunk_array(struct hl_device *hdev, struct hl_cs_chunk **cs_chunk_array, - void __user *chunks, u32 num_chunks) + void __user *chunks, u32 num_chunks, + struct hl_ctx *ctx) { u32 size_to_copy; if (num_chunks > HL_MAX_JOBS_PER_CS) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt); dev_err(hdev->dev, "Number of chunks can NOT be larger than %d\n", HL_MAX_JOBS_PER_CS); @@ -777,11 +787,16 @@ static int hl_cs_copy_chunk_array(struct hl_device *hdev, *cs_chunk_array = kmalloc_array(num_chunks, sizeof(**cs_chunk_array), GFP_ATOMIC); - if (!*cs_chunk_array) + if (!*cs_chunk_array) { + atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt); + atomic64_inc(&hdev->aggregated_cs_counters.out_of_mem_drop_cnt); return -ENOMEM; + } size_to_copy = num_chunks * sizeof(struct hl_cs_chunk); if (copy_from_user(*cs_chunk_array, chunks, size_to_copy)) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt); dev_err(hdev->dev, "Failed to copy cs chunk array from user\n"); kfree(*cs_chunk_array); return -EFAULT; @@ -797,6 +812,7 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, struct hl_device *hdev = hpriv->hdev; struct hl_cs_chunk *cs_chunk_array; struct hl_cs_counters_atomic *cntr; + struct hl_ctx *ctx = hpriv->ctx; struct hl_cs_job *job; struct hl_cs *cs; struct hl_cb *cb; @@ -805,7 +821,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, cntr = &hdev->aggregated_cs_counters; *cs_seq = ULLONG_MAX; - rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks); + rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks, + hpriv->ctx); if (rc) goto out; @@ -832,8 +849,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, rc = validate_queue_index(hdev, chunk, &queue_type, &is_kernel_allocated_cb); if (rc) { - atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt); - atomic64_inc(&cntr->parsing_drop_cnt); + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); goto free_cs_object; } @@ -841,8 +858,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, cb = get_cb_from_cs_chunk(hdev, &hpriv->cb_mgr, chunk); if (!cb) { atomic64_inc( - &hpriv->ctx->cs_counters.parsing_drop_cnt); - atomic64_inc(&cntr->parsing_drop_cnt); + &ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); rc = -EINVAL; goto free_cs_object; } @@ -856,8 +873,7 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, job = hl_cs_allocate_job(hdev, queue_type, is_kernel_allocated_cb); if (!job) { - atomic64_inc( - &hpriv->ctx->cs_counters.out_of_mem_drop_cnt); + atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt); atomic64_inc(&cntr->out_of_mem_drop_cnt); dev_err(hdev->dev, "Failed to allocate a new job\n"); rc = -ENOMEM; @@ -891,7 +907,7 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, rc = cs_parser(hpriv, job); if (rc) { - atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt); + atomic64_inc(&ctx->cs_counters.parsing_drop_cnt); atomic64_inc(&cntr->parsing_drop_cnt); dev_err(hdev->dev, "Failed to parse JOB %d.%llu.%d, err %d, rejecting the CS\n", @@ -901,8 +917,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, } if (int_queues_only) { - atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt); - atomic64_inc(&cntr->parsing_drop_cnt); + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); dev_err(hdev->dev, "Reject CS %d.%llu because only internal queues jobs are present\n", cs->ctx->asid, cs->sequence); @@ -1042,7 +1058,7 @@ out: } static int cs_ioctl_extract_signal_seq(struct hl_device *hdev, - struct hl_cs_chunk *chunk, u64 *signal_seq) + struct hl_cs_chunk *chunk, u64 *signal_seq, struct hl_ctx *ctx) { u64 *signal_seq_arr = NULL; u32 size_to_copy, signal_seq_arr_len; @@ -1052,6 +1068,8 @@ static int cs_ioctl_extract_signal_seq(struct hl_device *hdev, /* currently only one signal seq is supported */ if (signal_seq_arr_len != 1) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt); dev_err(hdev->dev, "Wait for signal CS supports only one signal CS seq\n"); return -EINVAL; @@ -1060,13 +1078,18 @@ static int cs_ioctl_extract_signal_seq(struct hl_device *hdev, signal_seq_arr = kmalloc_array(signal_seq_arr_len, sizeof(*signal_seq_arr), GFP_ATOMIC); - if (!signal_seq_arr) + if (!signal_seq_arr) { + atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt); + atomic64_inc(&hdev->aggregated_cs_counters.out_of_mem_drop_cnt); return -ENOMEM; + } size_to_copy = chunk->num_signal_seq_arr * sizeof(*signal_seq_arr); if (copy_from_user(signal_seq_arr, u64_to_user_ptr(chunk->signal_seq_arr), size_to_copy)) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt); dev_err(hdev->dev, "Failed to copy signal seq array from user\n"); rc = -EFAULT; @@ -1153,6 +1176,7 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, struct hl_device *hdev = hpriv->hdev; struct hl_cs_compl *sig_waitcs_cmpl; u32 q_idx, collective_engine_id = 0; + struct hl_cs_counters_atomic *cntr; struct hl_fence *sig_fence = NULL; struct hl_ctx *ctx = hpriv->ctx; enum hl_queue_type q_type; @@ -1160,9 +1184,11 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, u64 signal_seq; int rc; + cntr = &hdev->aggregated_cs_counters; *cs_seq = ULLONG_MAX; - rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks); + rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks, + ctx); if (rc) goto out; @@ -1170,6 +1196,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, chunk = &cs_chunk_array[0]; if (chunk->queue_index >= hdev->asic_prop.max_queues) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); dev_err(hdev->dev, "Queue index %d is invalid\n", chunk->queue_index); rc = -EINVAL; @@ -1181,6 +1209,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, q_type = hw_queue_prop->type; if (!hw_queue_prop->supports_sync_stream) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); dev_err(hdev->dev, "Queue index %d does not support sync stream operations\n", q_idx); @@ -1190,6 +1220,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, if (cs_type == CS_TYPE_COLLECTIVE_WAIT) { if (!(hw_queue_prop->collective_mode == HL_COLLECTIVE_MASTER)) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); dev_err(hdev->dev, "Queue index %d is invalid\n", q_idx); rc = -EINVAL; @@ -1200,12 +1232,14 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, } if (cs_type == CS_TYPE_WAIT || cs_type == CS_TYPE_COLLECTIVE_WAIT) { - rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq); + rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq, ctx); if (rc) goto free_cs_chunk_array; sig_fence = hl_ctx_get_fence(ctx, signal_seq); if (IS_ERR(sig_fence)) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); dev_err(hdev->dev, "Failed to get signal CS with seq 0x%llx\n", signal_seq); @@ -1223,6 +1257,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, container_of(sig_fence, struct hl_cs_compl, base_fence); if (sig_waitcs_cmpl->type != CS_TYPE_SIGNAL) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); dev_err(hdev->dev, "CS seq 0x%llx is not of a signal CS\n", signal_seq); @@ -1270,8 +1306,11 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, else if (cs_type == CS_TYPE_COLLECTIVE_WAIT) rc = hdev->asic_funcs->collective_wait_create_jobs(hdev, ctx, cs, q_idx, collective_engine_id); - else + else { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); rc = -EINVAL; + } if (rc) goto free_cs_object; diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 70b778a0d60e..e0d7f5fbaa5c 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -1000,6 +1000,7 @@ struct hl_va_range { * @queue_full_drop_cnt: dropped due to queue full * @device_in_reset_drop_cnt: dropped due to device in reset * @max_cs_in_flight_drop_cnt: dropped due to maximum CS in-flight + * @validation_drop_cnt: dropped due to error in validation */ struct hl_cs_counters_atomic { atomic64_t out_of_mem_drop_cnt; @@ -1007,6 +1008,7 @@ struct hl_cs_counters_atomic { atomic64_t queue_full_drop_cnt; atomic64_t device_in_reset_drop_cnt; atomic64_t max_cs_in_flight_drop_cnt; + atomic64_t validation_drop_cnt; }; /** diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index a0c0d20f6f8f..12efbd9d2e3a 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -335,6 +335,8 @@ static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args) atomic64_read(&cntr->device_in_reset_drop_cnt); cs_counters.total_max_cs_in_flight_drop_cnt = atomic64_read(&cntr->max_cs_in_flight_drop_cnt); + cs_counters.total_validation_drop_cnt = + atomic64_read(&cntr->validation_drop_cnt); if (hpriv->ctx) { cs_counters.ctx_out_of_mem_drop_cnt = @@ -352,6 +354,9 @@ static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args) cs_counters.ctx_max_cs_in_flight_drop_cnt = atomic64_read( &hpriv->ctx->cs_counters.max_cs_in_flight_drop_cnt); + cs_counters.ctx_validation_drop_cnt = + atomic64_read( + &hpriv->ctx->cs_counters.validation_drop_cnt); } return copy_to_user(out, &cs_counters, diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index dc8bcec195cc..dba3827c43ca 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -426,6 +426,8 @@ struct hl_info_sync_manager { * @ctx_device_in_reset_drop_cnt: context dropped due to device in reset * @total_max_cs_in_flight_drop_cnt: total dropped due to maximum CS in-flight * @ctx_max_cs_in_flight_drop_cnt: context dropped due to maximum CS in-flight + * @total_validation_drop_cnt: total dropped due to validation error + * @ctx_validation_drop_cnt: context dropped due to validation error */ struct hl_info_cs_counters { __u64 total_out_of_mem_drop_cnt; @@ -438,6 +440,8 @@ struct hl_info_cs_counters { __u64 ctx_device_in_reset_drop_cnt; __u64 total_max_cs_in_flight_drop_cnt; __u64 ctx_max_cs_in_flight_drop_cnt; + __u64 total_validation_drop_cnt; + __u64 ctx_validation_drop_cnt; }; enum gaudi_dcores { -- cgit v1.2.3 From b4e70d8dd9ea6bd5d5fb3122586f652326ca09cd Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 27 Dec 2020 12:35:43 +0100 Subject: netfilter: nftables: add set expression flags The set flag NFT_SET_EXPR provides a hint to the kernel that userspace supports for multiple expressions per set element. In the same direction, NFT_DYNSET_F_EXPR specifies that dynset expression defines multiple expressions per set element. This allows new userspace software with old kernels to bail out with EOPNOTSUPP. This update is similar to ef516e8625dd ("netfilter: nf_tables: reintroduce the NFT_SET_CONCAT flag"). The NFT_SET_EXPR flag needs to be set on when the NFTA_SET_EXPRESSIONS attribute is specified. The NFT_SET_EXPR flag is not set on with NFTA_SET_EXPR to retain backward compatibility in old userspace binaries. Fixes: 48b0ae046ee9 ("netfilter: nftables: netlink support for several set element expressions") Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 3 +++ net/netfilter/nf_tables_api.c | 6 +++++- net/netfilter/nft_dynset.c | 9 +++++++-- 3 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 28b6ee53305f..b1633e7ba529 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -293,6 +293,7 @@ enum nft_rule_compat_attributes { * @NFT_SET_EVAL: set can be updated from the evaluation path * @NFT_SET_OBJECT: set contains stateful objects * @NFT_SET_CONCAT: set contains a concatenation + * @NFT_SET_EXPR: set contains expressions */ enum nft_set_flags { NFT_SET_ANONYMOUS = 0x1, @@ -303,6 +304,7 @@ enum nft_set_flags { NFT_SET_EVAL = 0x20, NFT_SET_OBJECT = 0x40, NFT_SET_CONCAT = 0x80, + NFT_SET_EXPR = 0x100, }; /** @@ -706,6 +708,7 @@ enum nft_dynset_ops { enum nft_dynset_flags { NFT_DYNSET_F_INV = (1 << 0), + NFT_DYNSET_F_EXPR = (1 << 1), }; /** diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4186b1e52d58..15c467f1a9dd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4162,7 +4162,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | - NFT_SET_OBJECT | NFT_SET_CONCAT)) + NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR)) return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == @@ -4304,6 +4304,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, struct nlattr *tmp; int left; + if (!(flags & NFT_SET_EXPR)) { + err = -EINVAL; + goto err_set_alloc_name; + } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index f35df221a633..0b053f75cd60 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -19,6 +19,7 @@ struct nft_dynset { enum nft_registers sreg_key:8; enum nft_registers sreg_data:8; bool invert; + bool expr; u8 num_exprs; u64 timeout; struct nft_expr *expr_array[NFT_SET_EXPR_MAX]; @@ -175,11 +176,12 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (tb[NFTA_DYNSET_FLAGS]) { u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS])); - - if (flags & ~NFT_DYNSET_F_INV) + if (flags & ~(NFT_DYNSET_F_INV | NFT_DYNSET_F_EXPR)) return -EOPNOTSUPP; if (flags & NFT_DYNSET_F_INV) priv->invert = true; + if (flags & NFT_DYNSET_F_EXPR) + priv->expr = true; } set = nft_set_lookup_global(ctx->net, ctx->table, @@ -261,6 +263,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, struct nlattr *tmp; int left; + if (!priv->expr) + return -EINVAL; + i = 0; nla_for_each_nested(tmp, tb[NFTA_DYNSET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { -- cgit v1.2.3 From cf0720697143f3eaa0779cca5a6602d8557d1c6f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 30 Dec 2020 19:37:53 -0800 Subject: net: suggest L2 discards be counted towards rx_dropped From the existing definitions it's unclear which stat to use to report filtering based on L2 dst addr in old broadcast-medium Ethernet. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 874cc12a34d9..82708c6db432 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -75,8 +75,9 @@ struct rtnl_link_stats { * * @rx_dropped: Number of packets received but not processed, * e.g. due to lack of resources or unsupported protocol. - * For hardware interfaces this counter should not include packets - * dropped by the device which are counted separately in + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in * @rx_missed_errors (since procfs folds those two counters together). * * @tx_dropped: Number of packets dropped on their way to transmission, -- cgit v1.2.3 From 647daca25d24fb6eadc7b6cd680ad3e6eed0f3d5 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 4 Jan 2021 14:20:01 -0600 Subject: KVM: SVM: Add support for booting APs in an SEV-ES guest Typically under KVM, an AP is booted using the INIT-SIPI-SIPI sequence, where the guest vCPU register state is updated and then the vCPU is VMRUN to begin execution of the AP. For an SEV-ES guest, this won't work because the guest register state is encrypted. Following the GHCB specification, the hypervisor must not alter the guest register state, so KVM must track an AP/vCPU boot. Should the guest want to park the AP, it must use the AP Reset Hold exit event in place of, for example, a HLT loop. First AP boot (first INIT-SIPI-SIPI sequence): Execute the AP (vCPU) as it was initialized and measured by the SEV-ES support. It is up to the guest to transfer control of the AP to the proper location. Subsequent AP boot: KVM will expect to receive an AP Reset Hold exit event indicating that the vCPU is being parked and will require an INIT-SIPI-SIPI sequence to awaken it. When the AP Reset Hold exit event is received, KVM will place the vCPU into a simulated HLT mode. Upon receiving the INIT-SIPI-SIPI sequence, KVM will make the vCPU runnable. It is again up to the guest to then transfer control of the AP to the proper location. To differentiate between an actual HLT and an AP Reset Hold, a new MP state is introduced, KVM_MP_STATE_AP_RESET_HOLD, which the vCPU is placed in upon receiving the AP Reset Hold exit event. Additionally, to communicate the AP Reset Hold exit event up to userspace (if needed), a new exit reason is introduced, KVM_EXIT_AP_RESET_HOLD. A new x86 ops function is introduced, vcpu_deliver_sipi_vector, in order to accomplish AP booting. For VMX, vcpu_deliver_sipi_vector is set to the original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(). SVM adds a new function that, for non SEV-ES guests, invokes the original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(), but for SEV-ES guests, implements the logic above. Signed-off-by: Tom Lendacky Message-Id: Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/lapic.c | 2 +- arch/x86/kvm/svm/sev.c | 22 ++++++++++++++++++++++ arch/x86/kvm/svm/svm.c | 10 ++++++++++ arch/x86/kvm/svm/svm.h | 2 ++ arch/x86/kvm/vmx/vmx.c | 2 ++ arch/x86/kvm/x86.c | 26 +++++++++++++++++++++----- include/uapi/linux/kvm.h | 2 ++ 8 files changed, 63 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index afed3da3b3a0..3d6616f6f6ef 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1299,6 +1299,8 @@ struct kvm_x86_ops { void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); + + void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); }; struct kvm_x86_nested_ops { @@ -1480,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 78823227c592..43cceadd073e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2898,7 +2898,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) /* evaluate pending_events before reading the vector */ smp_rmb(); sipi_vector = apic->sipi_vector; - kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); + kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 563ced07b0b8..c8ffdbc81709 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1563,6 +1563,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: + case SVM_VMGEXIT_AP_HLT_LOOP: case SVM_VMGEXIT_AP_JUMP_TABLE: case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; @@ -1888,6 +1889,9 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); break; + case SVM_VMGEXIT_AP_HLT_LOOP: + ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + break; case SVM_VMGEXIT_AP_JUMP_TABLE: { struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; @@ -2040,3 +2044,21 @@ void sev_es_vcpu_put(struct vcpu_svm *svm) wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); } } + +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* First SIPI: Use the values as initially set by the VMM */ + if (!svm->received_first_sipi) { + svm->received_first_sipi = true; + return; + } + + /* + * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where + * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a + * non-zero value. + */ + ghcb_set_sw_exit_info_2(svm->ghcb, 1); +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 6824d611dc5d..7ef171790d02 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4382,6 +4382,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT)); } +static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + if (!sev_es_guest(vcpu->kvm)) + return kvm_vcpu_deliver_sipi_vector(vcpu, vector); + + sev_vcpu_deliver_sipi_vector(vcpu, vector); +} + static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); @@ -4524,6 +4532,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .msr_filter_changed = svm_msr_filter_changed, .complete_emulated_msr = svm_complete_emulated_msr, + + .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5431e6335e2e..0fe874ae5498 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -185,6 +185,7 @@ struct vcpu_svm { struct vmcb_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; + bool received_first_sipi; /* SEV-ES scratch area support */ void *ghcb_sa; @@ -591,6 +592,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu); void sev_es_vcpu_put(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 75c9c6a0a3a4..2af05d3b0590 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7707,6 +7707,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, .cpu_dirty_log_size = vmx_cpu_dirty_log_size, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; static __init int hardware_setup(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f6e7b25c40e2..0287840b93e0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7976,17 +7976,22 @@ void kvm_arch_exit(void) kmem_cache_destroy(x86_fpu_cache); } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) { ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + vcpu->arch.mp_state = state; return 1; } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; + vcpu->run->exit_reason = reason; return 0; } } + +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +{ + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} EXPORT_SYMBOL_GPL(kvm_vcpu_halt); int kvm_emulate_halt(struct kvm_vcpu *vcpu) @@ -8000,6 +8005,14 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -9096,6 +9109,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) kvm_apic_accept_events(vcpu); switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -9522,8 +9536,9 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); - if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && - vcpu->arch.pv.pv_unhalted) + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || + vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && + vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; @@ -10154,6 +10169,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } +EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); int kvm_arch_hardware_enable(void) { diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 886802b8ffba..374c67875cdb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -251,6 +251,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 #define KVM_EXIT_DIRTY_RING_FULL 31 +#define KVM_EXIT_AP_RESET_HOLD 32 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -573,6 +574,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_CHECK_STOP 6 #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 +#define KVM_MP_STATE_AP_RESET_HOLD 9 struct kvm_mp_state { __u32 mp_state; -- cgit v1.2.3 From b16671e8f493e3df40b1fb0dff4078f391c5099a Mon Sep 17 00:00:00 2001 From: Coly Li Date: Mon, 4 Jan 2021 15:41:21 +0800 Subject: bcache: introduce BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE for large bucket When large bucket feature was added, BCH_FEATURE_INCOMPAT_LARGE_BUCKET was introduced into the incompat feature set. It used bucket_size_hi (which was added at the tail of struct cache_sb_disk) to extend current 16bit bucket size to 32bit with existing bucket_size in struct cache_sb_disk. This is not a good idea, there are two obvious problems, - Bucket size is always value power of 2, if store log2(bucket size) in existing bucket_size of struct cache_sb_disk, it is unnecessary to add bucket_size_hi. - Macro csum_set() assumes d[SB_JOURNAL_BUCKETS] is the last member in struct cache_sb_disk, bucket_size_hi was added after d[] which makes csum_set calculate an unexpected super block checksum. To fix the above problems, this patch introduces a new incompat feature bit BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE, when this bit is set, it means bucket_size in struct cache_sb_disk stores the order of power-of-2 bucket size value. When user specifies a bucket size larger than 32768 sectors, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE will be set to incompat feature set, and bucket_size stores log2(bucket size) more than store the real bucket size value. The obsoleted BCH_FEATURE_INCOMPAT_LARGE_BUCKET won't be used anymore, it is renamed to BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET and still only recognized by kernel driver for legacy compatible purpose. The previous bucket_size_hi is renmaed to obso_bucket_size_hi in struct cache_sb_disk and not used in bcache-tools anymore. For cache device created with BCH_FEATURE_INCOMPAT_LARGE_BUCKET feature, bcache-tools and kernel driver still recognize the feature string and display it as "obso_large_bucket". With this change, the unnecessary extra space extend of bcache on-disk super block can be avoided, and csum_set() may generate expected check sum as well. Fixes: ffa470327572 ("bcache: add bucket_size_hi into struct cache_sb_disk for large bucket") Signed-off-by: Coly Li Cc: stable@vger.kernel.org # 5.9+ Signed-off-by: Jens Axboe --- drivers/md/bcache/features.c | 2 +- drivers/md/bcache/features.h | 11 ++++++++--- drivers/md/bcache/super.c | 22 +++++++++++++++++++--- include/uapi/linux/bcache.h | 2 +- 4 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c index 6469223f0b77..d636b7b2d070 100644 --- a/drivers/md/bcache/features.c +++ b/drivers/md/bcache/features.c @@ -17,7 +17,7 @@ struct feature { }; static struct feature feature_list[] = { - {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET, + {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE, "large_bucket"}, {0, 0, 0 }, }; diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index e73724c2b49b..84fc2c0f0101 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -13,11 +13,15 @@ /* Feature set definition */ /* Incompat feature set */ -#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET 0x0001 /* 32bit bucket size */ +/* 32bit bucket size, obsoleted */ +#define BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET 0x0001 +/* real bucket size is (1 << bucket_size) */ +#define BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE 0x0002 #define BCH_FEATURE_COMPAT_SUPP 0 #define BCH_FEATURE_RO_COMPAT_SUPP 0 -#define BCH_FEATURE_INCOMPAT_SUPP BCH_FEATURE_INCOMPAT_LARGE_BUCKET +#define BCH_FEATURE_INCOMPAT_SUPP (BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET| \ + BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE) #define BCH_HAS_COMPAT_FEATURE(sb, mask) \ ((sb)->feature_compat & (mask)) @@ -77,7 +81,8 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \ ~BCH##_FEATURE_INCOMPAT_##flagname; \ } -BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(obso_large_bucket, OBSO_LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LOG_LARGE_BUCKET_SIZE); static inline bool bch_has_unknown_compat_features(struct cache_sb *sb) { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index f4674a3298af..3999641f1775 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -64,9 +64,25 @@ static unsigned int get_bucket_size(struct cache_sb *sb, struct cache_sb_disk *s { unsigned int bucket_size = le16_to_cpu(s->bucket_size); - if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES && - bch_has_feature_large_bucket(sb)) - bucket_size |= le16_to_cpu(s->bucket_size_hi) << 16; + if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES) { + if (bch_has_feature_large_bucket(sb)) { + unsigned int max, order; + + max = sizeof(unsigned int) * BITS_PER_BYTE - 1; + order = le16_to_cpu(s->bucket_size); + /* + * bcache tool will make sure the overflow won't + * happen, an error message here is enough. + */ + if (order > max) + pr_err("Bucket size (1 << %u) overflows\n", + order); + bucket_size = 1 << order; + } else if (bch_has_feature_obso_large_bucket(sb)) { + bucket_size += + le16_to_cpu(s->obso_bucket_size_hi) << 16; + } + } return bucket_size; } diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index 52e8bcb33981..cf7399f03b71 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -213,7 +213,7 @@ struct cache_sb_disk { __le16 keys; }; __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ - __le16 bucket_size_hi; + __le16 obso_bucket_size_hi; /* obsoleted */ }; /* -- cgit v1.2.3