diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..80ae758 --- /dev/null +++ b/.gitignore @@ -0,0 +1,8 @@ +.vscode +*.o +*.o.cmd +*.ko +*.ko.cmd +.tmp_versions +igc.mod.c +modules.order \ No newline at end of file diff --git a/Makefile b/Makefile index 1c3051d..82b1b8b 100644 --- a/Makefile +++ b/Makefile @@ -5,7 +5,8 @@ # Intel(R) I225-LM/I225-V 2.5G Ethernet Controller # -obj-$(CONFIG_IGC) += igc.o +obj-m = igc.o +# TODO enable ethtool api igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ -igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o +igc_diag.o igc_ptp.o igc_dump.o igc_tsn.o diff --git a/backport.h b/backport.h new file mode 100644 index 0000000..3b88f0e --- /dev/null +++ b/backport.h @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Jim Ma */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) +{ + return skb->head + skb->csum_start; +} + +static inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) +{ + *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); +} + +static inline void net_prefetch(void *p) +{ + prefetch(p); +#if L1_CACHE_BYTES < 128 + prefetch((u8 *)p + L1_CACHE_BYTES); +#endif +} + +static inline bool dev_page_is_reusable(struct page *page) +{ + return likely(page_to_nid(page) == numa_mem_id() && + !page_is_pfmemalloc(page)); +} + +/** + * refcount_read - get a refcount's value + * @r: the refcount + * + * Return: the refcount's value + */ +static inline unsigned int refcount_read(atomic_t *r) +{ + return atomic_read(r); +} + +// static inline __must_check bool __refcount_sub_and_test(int i, atomic_t *r, int *oldp) +// { +// // int old = atomic_fetch_sub_release(i, r); + +// // if (oldp) +// // *oldp = old; + +// // if (old == i) { +// // smp_acquire__after_ctrl_dep(); +// // return true; +// // } + +// // if (unlikely(old < 0 || old - i < 0)) +// // refcount_warn_saturate(r, REFCOUNT_SUB_UAF); + +// return false; +// } + +/** + * refcount_sub_and_test - subtract from a refcount and test if it is 0 + * @i: amount to subtract from the refcount + * @r: the refcount + * + * Similar to atomic_dec_and_test(), but it will WARN, return false and + * ultimately leak on underflow and will fail to decrement when saturated + * at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_dec(), or one of its variants, should instead be used to + * decrement a reference count. + * + * Return: true if the resulting refcount is 0, false otherwise + */ +// static inline __must_check bool refcount_sub_and_test(int i, atomic_t *r) +// { +// return __refcount_sub_and_test(i, r, NULL); +// } + +// static inline __must_check bool __refcount_dec_and_test(atomic_t *r, int *oldp) +// { +// return __refcount_sub_and_test(1, r, oldp); +// } + +/** + * refcount_dec_and_test - decrement a refcount and test if it is 0 + * @r: the refcount + * + * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to + * decrement when saturated at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Return: true if the resulting refcount is 0, false otherwise + */ +// static inline __must_check bool refcount_dec_and_test(atomic_t *r) +// { +// return __refcount_dec_and_test(r, NULL); +// } + +/** + * skb_unref - decrement the skb's reference count + * @skb: buffer + * + * Returns true if we can free the skb. + */ +// static inline bool skb_unref(struct sk_buff *skb) +// { +// if (unlikely(!skb)) +// return false; +// if (likely(atomic_read(&skb->users) == 1)) +// smp_rmb(); +// else if (likely(!refcount_dec_and_test(&skb->users))) +// return false; + +// return true; +// } + +// static void skb_release_all(struct sk_buff *skb) +// { +// skb_release_head_state(skb); +// if (likely(skb->head)) +// skb_release_data(skb); +// } + +// static void napi_consume_skb(struct sk_buff *skb, int budget) +// { +// /* Zero budget indicate non-NAPI context called us, like netpoll */ +// if (unlikely(!budget)) { +// dev_consume_skb_any(skb); +// return; +// } + +// // lockdep_assert_in_softirq(); + +// if (!skb_unref(skb)) +// return; + +// /* if reaching here SKB is ready to free */ +// trace_consume_skb(skb); + +// /* if SKB is a clone, don't handle this case */ +// if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { +// __kfree_skb(skb); +// return; +// } + +// skb_release_all(skb); +// napi_skb_cache_put(skb); +// } + +static inline int +pci_request_mem_regions(struct pci_dev *pdev, const char *name) +{ + return pci_request_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_MEM), name); +} + +static inline void +pci_release_mem_regions(struct pci_dev *pdev) +{ + return pci_release_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_MEM)); +} \ No newline at end of file diff --git a/backport_overflow.h b/backport_overflow.h new file mode 100644 index 0000000..8712ff7 --- /dev/null +++ b/backport_overflow.h @@ -0,0 +1,278 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +#ifndef __LINUX_OVERFLOW_H +#define __LINUX_OVERFLOW_H + +#include + +/* + * In the fallback code below, we need to compute the minimum and + * maximum values representable in a given type. These macros may also + * be useful elsewhere, so we provide them outside the + * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. + * + * It would seem more obvious to do something like + * + * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) + * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) + * + * Unfortunately, the middle expressions, strictly speaking, have + * undefined behaviour, and at least some versions of gcc warn about + * the type_max expression (but not if -fsanitize=undefined is in + * effect; in that case, the warning is deferred to runtime...). + * + * The slightly excessive casting in type_min is to make sure the + * macros also produce sensible values for the exotic type _Bool. [The + * overflow checkers only almost work for _Bool, but that's + * a-feature-not-a-bug, since people shouldn't be doing arithmetic on + * _Bools. Besides, the gcc builtins don't allow _Bool* as third + * argument.] + * + * Idea stolen from + * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html - + * credit to Christian Biere. + */ +#define is_signed_type(type) (((type)(-1)) < (type)1) +#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) +#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) +#define type_min(T) ((T)((T)-type_max(T)-(T)1)) + + +#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW +/* + * For simplicity and code hygiene, the fallback code below insists on + * a, b and *d having the same type (similar to the min() and max() + * macros), whereas gcc's type-generic overflow checkers accept + * different types. Hence we don't just make check_add_overflow an + * alias for __builtin_add_overflow, but add type checks similar to + * below. + */ +#define check_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_add_overflow(__a, __b, __d); \ +}) + +#define check_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_sub_overflow(__a, __b, __d); \ +}) + +#define check_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_mul_overflow(__a, __b, __d); \ +}) + +#else + + +/* Checking for unsigned overflow is relatively easy without causing UB. */ +#define __unsigned_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a + __b; \ + *__d < __a; \ +}) +#define __unsigned_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a - __b; \ + __a < __b; \ +}) +/* + * If one of a or b is a compile-time constant, this avoids a division. + */ +#define __unsigned_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a * __b; \ + __builtin_constant_p(__b) ? \ + __b > 0 && __a > type_max(typeof(__a)) / __b : \ + __a > 0 && __b > type_max(typeof(__b)) / __a; \ +}) + +/* + * For signed types, detecting overflow is much harder, especially if + * we want to avoid UB. But the interface of these macros is such that + * we must provide a result in *d, and in fact we must produce the + * result promised by gcc's builtins, which is simply the possibly + * wrapped-around value. Fortunately, we can just formally do the + * operations in the widest relevant unsigned type (u64) and then + * truncate the result - gcc is smart enough to generate the same code + * with and without the (u64) casts. + */ + +/* + * Adding two signed integers can overflow only if they have the same + * sign, and overflow has happened iff the result has the opposite + * sign. + */ +#define __signed_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a + (u64)__b; \ + (((~(__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Subtraction is similar, except that overflow can now happen only + * when the signs are opposite. In this case, overflow has happened if + * the result has the opposite sign of a. + */ +#define __signed_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a - (u64)__b; \ + ((((__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Signed multiplication is rather hard. gcc always follows C99, so + * division is truncated towards 0. This means that we can write the + * overflow check like this: + * + * (a > 0 && (b > MAX/a || b < MIN/a)) || + * (a < -1 && (b > MIN/a || b < MAX/a) || + * (a == -1 && b == MIN) + * + * The redundant casts of -1 are to silence an annoying -Wtype-limits + * (included in -Wextra) warning: When the type is u8 or u16, the + * __b_c_e in check_mul_overflow obviously selects + * __unsigned_mul_overflow, but unfortunately gcc still parses this + * code and warns about the limited range of __b. + */ + +#define __signed_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + typeof(a) __tmax = type_max(typeof(a)); \ + typeof(a) __tmin = type_min(typeof(a)); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a * (u64)__b; \ + (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ + (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ + (__b == (typeof(__b))-1 && __a == __tmin); \ +}) + + +#define check_add_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_add_overflow(a, b, d), \ + __unsigned_add_overflow(a, b, d)) + +#define check_sub_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_sub_overflow(a, b, d), \ + __unsigned_sub_overflow(a, b, d)) + +#define check_mul_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_mul_overflow(a, b, d), \ + __unsigned_mul_overflow(a, b, d)) + + +#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ + +/** + * array_size() - Calculate size of 2-dimensional array. + * + * @a: dimension one + * @b: dimension two + * + * Calculates size of 2-dimensional array: @a * @b. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array_size(size_t a, size_t b) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * array3_size() - Calculate size of 3-dimensional array. + * + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + if (check_mul_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(n, size, &bytes)) + return SIZE_MAX; + if (check_add_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * struct_size() - Calculate size of structure with trailing array. + * @p: Pointer to the structure. + * @member: Name of the array member. + * @n: Number of elements in the array. + * + * Calculates size of memory needed for structure @p followed by an + * array of @n @member elements. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define struct_size(p, member, n) \ + __ab_c_size(n, \ + sizeof(*(p)->member) + __must_be_array((p)->member),\ + sizeof(*(p))) + +#endif /* __LINUX_OVERFLOW_H */ diff --git a/igc_ethtool.c b/igc_ethtool.c index 8722294..6771259 100644 --- a/igc_ethtool.c +++ b/igc_ethtool.c @@ -8,6 +8,7 @@ #include "igc.h" #include "igc_diag.h" +#include "backport_overflow.h" /* forward declaration */ struct igc_stats { @@ -16,6 +17,14 @@ struct igc_stats { int stat_offset; }; +/** + * sizeof_field(TYPE, MEMBER) + * + * @TYPE: The structure containing the field of interest + * @MEMBER: The field to return the size of + */ +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) + #define IGC_STAT(_name, _stat) { \ .stat_string = _name, \ .sizeof_stat = sizeof_field(struct igc_adapter, _stat), \ @@ -380,7 +389,7 @@ static int igc_ethtool_set_wol(struct net_device *netdev, { struct igc_adapter *adapter = netdev_priv(netdev); - if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER)) + if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE)) return -EOPNOTSUPP; if (!(adapter->flags & IGC_FLAG_WOL_SUPPORTED)) diff --git a/igc_main.c b/igc_main.c index 4d989eb..82898ca 100644 --- a/igc_main.c +++ b/igc_main.c @@ -16,6 +16,8 @@ #include "igc.h" #include "igc_hw.h" #include "igc_tsn.h" +#include "backport.h" +#include "backport_overflow.h" #define DRV_SUMMARY "Intel(R) 2.5G Ethernet Linux Driver" @@ -362,13 +364,11 @@ static void igc_clean_rx_ring(struct igc_ring *rx_ring) DMA_FROM_DEVICE); /* free resources associated with mapping */ - dma_unmap_page_attrs(rx_ring->dev, - buffer_info->dma, - igc_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IGC_RX_DMA_ATTR); - __page_frag_cache_drain(buffer_info->page, - buffer_info->pagecnt_bias); + dma_unmap_page(rx_ring->dev, + buffer_info->dma, + igc_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); + __free_page(buffer_info->page); i++; if (i == rx_ring->count) @@ -629,6 +629,29 @@ static void igc_configure_tx(struct igc_adapter *adapter) igc_configure_tx_ring(adapter, adapter->tx_ring[i]); } +// FIXME copy from igc_ethtool.c, remove this function after enable ethtool api +void igc_write_rss_indir_tbl(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 reg = IGC_RETA(0); + u32 shift = 0; + int i = 0; + + while (i < IGC_RETA_SIZE) { + u32 val = 0; + int j; + + for (j = 3; j >= 0; j--) { + val <<= 8; + val |= adapter->rss_indir_tbl[i + j]; + } + + wr32(reg, val << shift); + reg += 4; + i += 4; + } +} + /** * igc_setup_mrqc - configure the multiple receive queue control registers * @adapter: Board private structure @@ -897,6 +920,7 @@ static __le32 igc_tx_launchtime(struct igc_adapter *adapter, ktime_t txtime) { ktime_t cycle_time = adapter->cycle_time; ktime_t base_time = adapter->base_time; + ktime_t sub_time = ktime_sub(txtime, base_time); u32 launchtime; /* FIXME: when using ETF together with taprio, we may have a @@ -905,7 +929,7 @@ static __le32 igc_tx_launchtime(struct igc_adapter *adapter, ktime_t txtime) * IGC_BASET, as the value writen into the launchtime * descriptor field may be misinterpreted. */ - div_s64_rem(ktime_sub_ns(txtime, base_time), cycle_time, &launchtime); + div_s64_rem(sub_time.tv64, cycle_time.tv64, &launchtime); return cpu_to_le32(launchtime); } @@ -966,16 +990,17 @@ csum_failed: switch (skb->csum_offset) { case offsetof(struct tcphdr, check): type_tucmd = IGC_ADVTXD_TUCMD_L4T_TCP; - fallthrough; + break; case offsetof(struct udphdr, check): break; case offsetof(struct sctphdr, checksum): /* validate that this is actually an SCTP request */ - if (skb_csum_is_sctp(skb)) { - type_tucmd = IGC_ADVTXD_TUCMD_L4T_SCTP; - break; - } - fallthrough; + // if (skb->csum_not_inet) { + // type_tucmd = IGC_ADVTXD_TUCMD_L4T_SCTP; + // break; + // } + skb_checksum_help(skb); + goto csum_failed; default: skb_checksum_help(skb); goto csum_failed; @@ -1173,7 +1198,7 @@ static int igc_tx_map(struct igc_ring *tx_ring, /* Make sure there is space in the ring for the next send. */ igc_maybe_stop_tx(tx_ring, DESC_NEEDED); - if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); } @@ -1596,7 +1621,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IGC_RX_HDR_LEN) - headlen = eth_get_headlen(skb->dev, va, IGC_RX_HDR_LEN); + headlen = eth_get_headlen(va, IGC_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); @@ -1659,7 +1684,7 @@ static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely(atomic_read(&page->_count) - pagecnt_bias > 1)) return false; #else #define IGC_LAST_OFFSET \ @@ -1674,7 +1699,7 @@ static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer) * number of references the driver holds. */ if (unlikely(!pagecnt_bias)) { - page_ref_add(page, USHRT_MAX); + atomic_add(USHRT_MAX, &page->_count); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -1752,11 +1777,10 @@ static void igc_put_rx_buffer(struct igc_ring *rx_ring, /* We are not reusing the buffer so unmap it and free * any references we are holding to it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - igc_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - IGC_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buffer->page, - rx_buffer->pagecnt_bias); + dma_unmap_page(rx_ring->dev, rx_buffer->dma, + igc_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); + __free_page(rx_buffer->page); } /* clear contents of rx_buffer */ @@ -1786,10 +1810,9 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, } /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, - igc_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IGC_RX_DMA_ATTR); + dma = dma_map_page(rx_ring->dev, page, 0, + igc_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use @@ -2016,7 +2039,7 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) total_packets += tx_buffer->gso_segs; /* free the skb */ - napi_consume_skb(tx_buffer->skb, napi_budget); + dev_consume_skb_any(tx_buffer->skb); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -3291,10 +3314,10 @@ static int igc_poll(struct napi_struct *napi, int budget) /* Exit the polling mode, but don't re-enable interrupts if stack might * poll us due to busy-polling */ - if (likely(napi_complete_done(napi, work_done))) - igc_ring_irq_enable(q_vector); + napi_complete_done(napi, work_done); + igc_ring_irq_enable(q_vector); - return min(work_done, budget - 1); + return 0; } /** @@ -3771,7 +3794,7 @@ void igc_down(struct igc_adapter *adapter) /* flush and sleep below */ /* set trans_start so we don't get spurious watchdogs during reset */ - netif_trans_update(netdev); + netdev->trans_start = jiffies; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); @@ -3951,23 +3974,11 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, mac_hdr_len = skb_network_header(skb) - skb->data; if (unlikely(mac_hdr_len > IGC_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | - NETIF_F_SCTP_CRC | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_TSO | - NETIF_F_TSO6); + NETIF_F_HW_VLAN_CTAG_TX); network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb); if (unlikely(network_hdr_len > IGC_MAX_NETWORK_HDR_LEN)) - return features & ~(NETIF_F_HW_CSUM | - NETIF_F_SCTP_CRC | - NETIF_F_TSO | - NETIF_F_TSO6); - - /* We can only support IPv4 TSO in tunnels if we can mangle the - * inner IP ID field, so strip TSO if MANGLEID is not supported. - */ - if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) - features &= ~NETIF_F_TSO; + return features & ~(NETIF_F_HW_CSUM); return features; } @@ -4683,10 +4694,10 @@ static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue, ring = adapter->tx_ring[queue]; ring->launchtime_enable = enable; - if (adapter->base_time) + if (adapter->base_time.tv64) return 0; - adapter->cycle_time = NSEC_PER_SEC; + adapter->cycle_time.tv64 = NSEC_PER_SEC; for (i = 0; i < adapter->num_tx_queues; i++) { ring = adapter->tx_ring[i]; @@ -4706,143 +4717,143 @@ static bool is_base_time_past(ktime_t base_time, const struct timespec64 *now) return timespec64_compare(now, &b) > 0; } -static bool validate_schedule(struct igc_adapter *adapter, - const struct tc_taprio_qopt_offload *qopt) -{ - int queue_uses[IGC_MAX_TX_QUEUES] = { }; - struct timespec64 now; - size_t n; +// static bool validate_schedule(struct igc_adapter *adapter, +// const struct tc_taprio_qopt_offload *qopt) +// { +// int queue_uses[IGC_MAX_TX_QUEUES] = { }; +// struct timespec64 now; +// size_t n; - if (qopt->cycle_time_extension) - return false; +// if (qopt->cycle_time_extension) +// return false; - igc_ptp_read(adapter, &now); +// igc_ptp_read(adapter, &now); - /* If we program the controller's BASET registers with a time - * in the future, it will hold all the packets until that - * time, causing a lot of TX Hangs, so to avoid that, we - * reject schedules that would start in the future. - */ - if (!is_base_time_past(qopt->base_time, &now)) - return false; +// /* If we program the controller's BASET registers with a time +// * in the future, it will hold all the packets until that +// * time, causing a lot of TX Hangs, so to avoid that, we +// * reject schedules that would start in the future. +// */ +// if (!is_base_time_past(qopt->base_time, &now)) +// return false; - for (n = 0; n < qopt->num_entries; n++) { - const struct tc_taprio_sched_entry *e; - int i; +// for (n = 0; n < qopt->num_entries; n++) { +// const struct tc_taprio_sched_entry *e; +// int i; - e = &qopt->entries[n]; +// e = &qopt->entries[n]; - /* i225 only supports "global" frame preemption - * settings. - */ - if (e->command != TC_TAPRIO_CMD_SET_GATES) - return false; +// /* i225 only supports "global" frame preemption +// * settings. +// */ +// if (e->command != TC_TAPRIO_CMD_SET_GATES) +// return false; - for (i = 0; i < IGC_MAX_TX_QUEUES; i++) { - if (e->gate_mask & BIT(i)) - queue_uses[i]++; +// for (i = 0; i < IGC_MAX_TX_QUEUES; i++) { +// if (e->gate_mask & BIT(i)) +// queue_uses[i]++; - if (queue_uses[i] > 1) - return false; - } - } +// if (queue_uses[i] > 1) +// return false; +// } +// } - return true; -} +// return true; +// } -static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, - struct tc_etf_qopt_offload *qopt) -{ - struct igc_hw *hw = &adapter->hw; - int err; +// static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, +// struct tc_etf_qopt_offload *qopt) +// { +// struct igc_hw *hw = &adapter->hw; +// int err; - if (hw->mac.type != igc_i225) - return -EOPNOTSUPP; +// if (hw->mac.type != igc_i225) +// return -EOPNOTSUPP; - err = igc_save_launchtime_params(adapter, qopt->queue, qopt->enable); - if (err) - return err; +// err = igc_save_launchtime_params(adapter, qopt->queue, qopt->enable); +// if (err) +// return err; - return igc_tsn_offload_apply(adapter); -} +// return igc_tsn_offload_apply(adapter); +// } -static int igc_save_qbv_schedule(struct igc_adapter *adapter, - struct tc_taprio_qopt_offload *qopt) -{ - u32 start_time = 0, end_time = 0; - size_t n; +// static int igc_save_qbv_schedule(struct igc_adapter *adapter, +// struct tc_taprio_qopt_offload *qopt) +// { +// u32 start_time = 0, end_time = 0; +// size_t n; - if (!qopt->enable) { - adapter->base_time = 0; - return 0; - } +// if (!qopt->enable) { +// adapter->base_time = 0; +// return 0; +// } - if (adapter->base_time) - return -EALREADY; +// if (adapter->base_time) +// return -EALREADY; - if (!validate_schedule(adapter, qopt)) - return -EINVAL; +// if (!validate_schedule(adapter, qopt)) +// return -EINVAL; - adapter->cycle_time = qopt->cycle_time; - adapter->base_time = qopt->base_time; +// adapter->cycle_time = qopt->cycle_time; +// adapter->base_time = qopt->base_time; - /* FIXME: be a little smarter about cases when the gate for a - * queue stays open for more than one entry. - */ - for (n = 0; n < qopt->num_entries; n++) { - struct tc_taprio_sched_entry *e = &qopt->entries[n]; - int i; +// /* FIXME: be a little smarter about cases when the gate for a +// * queue stays open for more than one entry. +// */ +// for (n = 0; n < qopt->num_entries; n++) { +// struct tc_taprio_sched_entry *e = &qopt->entries[n]; +// int i; - end_time += e->interval; +// end_time += e->interval; - for (i = 0; i < IGC_MAX_TX_QUEUES; i++) { - struct igc_ring *ring = adapter->tx_ring[i]; +// for (i = 0; i < IGC_MAX_TX_QUEUES; i++) { +// struct igc_ring *ring = adapter->tx_ring[i]; - if (!(e->gate_mask & BIT(i))) - continue; +// if (!(e->gate_mask & BIT(i))) +// continue; - ring->start_time = start_time; - ring->end_time = end_time; - } +// ring->start_time = start_time; +// ring->end_time = end_time; +// } - start_time += e->interval; - } +// start_time += e->interval; +// } - return 0; -} +// return 0; +// } -static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, - struct tc_taprio_qopt_offload *qopt) -{ - struct igc_hw *hw = &adapter->hw; - int err; +// static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, +// struct tc_taprio_qopt_offload *qopt) +// { +// struct igc_hw *hw = &adapter->hw; +// int err; - if (hw->mac.type != igc_i225) - return -EOPNOTSUPP; +// if (hw->mac.type != igc_i225) +// return -EOPNOTSUPP; - err = igc_save_qbv_schedule(adapter, qopt); - if (err) - return err; +// err = igc_save_qbv_schedule(adapter, qopt); +// if (err) +// return err; - return igc_tsn_offload_apply(adapter); -} +// return igc_tsn_offload_apply(adapter); +// } -static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, - void *type_data) -{ - struct igc_adapter *adapter = netdev_priv(dev); +// static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, +// void *type_data) +// { +// struct igc_adapter *adapter = netdev_priv(dev); - switch (type) { - case TC_SETUP_QDISC_TAPRIO: - return igc_tsn_enable_qbv_scheduling(adapter, type_data); +// switch (type) { +// case TC_SETUP_QDISC_TAPRIO: +// return igc_tsn_enable_qbv_scheduling(adapter, type_data); - case TC_SETUP_QDISC_ETF: - return igc_tsn_enable_launchtime(adapter, type_data); +// case TC_SETUP_QDISC_ETF: +// return igc_tsn_enable_launchtime(adapter, type_data); - default: - return -EOPNOTSUPP; - } -} +// default: +// return -EOPNOTSUPP; +// } +// } static const struct net_device_ops igc_netdev_ops = { .ndo_open = igc_open, @@ -4856,7 +4867,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_features = igc_set_features, .ndo_features_check = igc_features_check, .ndo_do_ioctl = igc_ioctl, - .ndo_setup_tc = igc_setup_tc, + // .ndo_setup_tc = igc_setup_tc, }; /* PCIe configuration access */ @@ -5047,7 +5058,7 @@ static int igc_probe(struct pci_dev *pdev, hw->hw_addr = adapter->io_addr; netdev->netdev_ops = &igc_netdev_ops; - igc_ethtool_set_ops(netdev); + // igc_ethtool_set_ops(netdev); netdev->watchdog_timeo = 5 * HZ; netdev->mem_start = pci_resource_start(pdev, 0); @@ -5071,23 +5082,11 @@ static int igc_probe(struct pci_dev *pdev, /* Add supported features to the features list*/ netdev->features |= NETIF_F_SG; - netdev->features |= NETIF_F_TSO; - netdev->features |= NETIF_F_TSO6; - netdev->features |= NETIF_F_TSO_ECN; + // netdev->features |= NETIF_F_TSO; + // netdev->features |= NETIF_F_TSO6; + // netdev->features |= NETIF_F_TSO_ECN; netdev->features |= NETIF_F_RXCSUM; netdev->features |= NETIF_F_HW_CSUM; - netdev->features |= NETIF_F_SCTP_CRC; - netdev->features |= NETIF_F_HW_TC; - -#define IGC_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ - NETIF_F_GSO_GRE_CSUM | \ - NETIF_F_GSO_IPXIP4 | \ - NETIF_F_GSO_IPXIP6 | \ - NETIF_F_GSO_UDP_TUNNEL | \ - NETIF_F_GSO_UDP_TUNNEL_CSUM) - - netdev->gso_partial_features = IGC_GSO_PARTIAL_FEATURES; - netdev->features |= NETIF_F_GSO_PARTIAL | IGC_GSO_PARTIAL_FEATURES; /* setup the private structure */ err = igc_sw_init(adapter); @@ -5102,8 +5101,8 @@ static int igc_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_HIGHDMA; /* MTU range: 68 - 9216 */ - netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; + // netdev->min_mtu = ETH_MIN_MTU; + // netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; /* before reading the NVM, reset the controller to put the device in a * known good starting state @@ -5118,11 +5117,11 @@ static int igc_probe(struct pci_dev *pdev, } } - if (eth_platform_get_mac_address(&pdev->dev, hw->mac.addr)) { + // if (eth_platform_get_mac_address(&pdev->dev, hw->mac.addr)) { /* copy the MAC address out of the NVM */ if (hw->mac.ops.read_mac_addr(hw)) dev_err(&pdev->dev, "NVM Read Error\n"); - } + // } memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len); @@ -5182,10 +5181,11 @@ static int igc_probe(struct pci_dev *pdev, adapter->ei = *ei; /* print pcie link status and MAC address */ - pcie_print_link_status(pdev); + // TODO backport pcie_print_link_status from drivers/pci/pci.c + // pcie_print_link_status(pdev); netdev_info(netdev, "MAC: %pM\n", netdev->dev_addr); - dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); + // dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); /* Disable EEE for internal PHY devices */ hw->dev_spec._base.eee_enable = false; adapter->flags &= ~IGC_FLAG_EEE; @@ -5206,7 +5206,8 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: - pci_release_mem_regions(pdev); + pci_release_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_MEM)); err_pci_reg: err_dma: pci_disable_device(pdev); diff --git a/igc_ptp.c b/igc_ptp.c index 545f4d0..7314556 100644 --- a/igc_ptp.c +++ b/igc_ptp.c @@ -16,6 +16,31 @@ #define IGC_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9) #define IGC_PTP_TX_TIMEOUT (HZ * 15) +#define netdev_level_once(level, dev, fmt, ...) \ +do { \ + static bool __print_once __read_mostly; \ + \ + if (!__print_once) { \ + __print_once = true; \ + netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ + } \ +} while (0) + +#define netdev_emerg_once(dev, fmt, ...) \ + netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) +#define netdev_alert_once(dev, fmt, ...) \ + netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) +#define netdev_crit_once(dev, fmt, ...) \ + netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) +#define netdev_err_once(dev, fmt, ...) \ + netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) +#define netdev_warn_once(dev, fmt, ...) \ + netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) +#define netdev_notice_once(dev, fmt, ...) \ + netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) +#define netdev_info_once(dev, fmt, ...) \ + netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) + /* SYSTIM read access for I225 */ void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts) { @@ -84,8 +109,7 @@ static int igc_ptp_adjtime_i225(struct ptp_clock_info *ptp, s64 delta) } static int igc_ptp_gettimex64_i225(struct ptp_clock_info *ptp, - struct timespec64 *ts, - struct ptp_system_timestamp *sts) + struct timespec64 *ts) { struct igc_adapter *igc = container_of(ptp, struct igc_adapter, ptp_caps); @@ -94,10 +118,8 @@ static int igc_ptp_gettimex64_i225(struct ptp_clock_info *ptp, spin_lock_irqsave(&igc->tmreg_lock, flags); - ptp_read_system_prets(sts); ts->tv_nsec = rd32(IGC_SYSTIML); ts->tv_sec = rd32(IGC_SYSTIMH); - ptp_read_system_postts(sts); spin_unlock_irqrestore(&igc->tmreg_lock, flags); @@ -308,7 +330,7 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_NTP_ALL: + // case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_ALL: igc_ptp_enable_rx_timestamp(adapter); config->rx_filter = HWTSTAMP_FILTER_ALL; @@ -491,9 +513,9 @@ void igc_ptp_init(struct igc_adapter *adapter) snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 62499999; - adapter->ptp_caps.adjfine = igc_ptp_adjfine_i225; + // adapter->ptp_caps.adjfine = igc_ptp_adjfine_i225; adapter->ptp_caps.adjtime = igc_ptp_adjtime_i225; - adapter->ptp_caps.gettimex64 = igc_ptp_gettimex64_i225; + adapter->ptp_caps.gettime64 = igc_ptp_gettimex64_i225; adapter->ptp_caps.settime64 = igc_ptp_settime_i225; adapter->ptp_caps.enable = igc_ptp_feature_enable_i225; break; diff --git a/igc_tsn.c b/igc_tsn.c index 174103c..91cb002 100644 --- a/igc_tsn.c +++ b/igc_tsn.c @@ -30,7 +30,7 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED)) return 0; - adapter->cycle_time = 0; + adapter->cycle_time.tv64 = 0; wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); @@ -71,7 +71,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) if (adapter->flags & IGC_FLAG_TSN_QBV_ENABLED) return 0; - cycle = adapter->cycle_time; + cycle = adapter->cycle_time.tv64; base_time = adapter->base_time; wr32(IGC_TSAUXC, 0); @@ -92,7 +92,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_STQT(i), ring->start_time); wr32(IGC_ENDQT(i), ring->end_time); - if (adapter->base_time) { + if (adapter->base_time.tv64) { /* If we have a base_time we are in "taprio" * mode and we need to be strict about the * cycles: only transmit a packet if it can be @@ -116,11 +116,12 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) if (ktime_compare(systim, base_time) > 0) { s64 n; - n = div64_s64(ktime_sub_ns(systim, base_time), cycle); + ktime_t sub_time = ktime_sub(systim, base_time); + n = div64_s64(sub_time.tv64, cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); } - baset_h = div_s64_rem(base_time, NSEC_PER_SEC, &baset_l); + baset_h = div_s64_rem(base_time.tv64, NSEC_PER_SEC, &baset_l); wr32(IGC_BASET_H, baset_h); wr32(IGC_BASET_L, baset_l); @@ -132,7 +133,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) int igc_tsn_offload_apply(struct igc_adapter *adapter) { - bool is_any_enabled = adapter->base_time || is_any_launchtime(adapter); + bool is_any_enabled = adapter->base_time.tv64 || is_any_launchtime(adapter); if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED) && !is_any_enabled) return 0;