From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=185.171.202.116 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795035226; b=zlWFYlOj3XPbyEeqwkiNoKb1PJ6ueeqVMtt1zVtQ0EIMzg+MSsp3lBAH0ugljSQn5iPc ZEFsV3OG1nFmy/LTnu1Xe+ES5ltlezIPzbTxLClikJsXT2uz7cUPcYe2i5TWT+pacN0Y9 XAmUhakA42jw9BBNFpcMmLCbAoc9SSRh8sHk+G85iLRhxL6jsHZylqRk9kGPdiwOSdTFU M6GCWYFTT98Tvtz/GhWccw8yzkawPRPmc4+CK4/jmD0RUTELRX5SRle6KC9Ri/8Zks/HO RXPoZfdLROwyhFdiZfrtdh9nnZ/Gzn+qayHTgGgH0K6wbc7M6lXjef5nBvUe/fm38/g== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795035226; h=DMARC-Filter:Received:Received:Received:DKIM-Signature:From:Date: Subject:MIME-Version:Content-Type:Content-Transfer-Encoding: Message-Id:References:In-Reply-To:To:Cc:X-Mailer: X-Last-TLS-Session-Version; bh=XEH3qk3Abm9nkekxnFqqH/9AwO9nDPm/bhd6K4j0MIM=; b=f+esGrtXEZkdQ2PEx9nsxhU4b+0CEhFC/DJAcvcq3j+9Uq4UJDn9eLwLMTPmF7Xcm5zp phZIJAxMax3O3sIBb4zmRR2tJZUW/wRaYhorCZaU60ZSs36BBIgxkm3EIPukCZkiCmiZX AO7QuM0/lO2u6GszKyyGoC40sUHnXDuhtMw9B0idkyf2i4fo1nh3cWYDyXMhrbmszEcNL X64StBh1YNp5G7d0H177OANAyg0HK2aoVSMWEu3tbc6cjhweXu0Y6PQBhQjezUSKslrDL s/n0CzS/5PRcLoJJJNyoLX9qot6Fs7SizrETH9kYMR8QWBNaiGtVB7jZhKYcncqqCPQ== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=bootlin.com; spf=pass smtp.mailfrom=bootlin.com; dkim=pass header.d=bootlin.com header.i=@bootlin.com header.a=rsa-sha256 header.s=dkim header.b=umfqq3Mp; arc=none smtp.remote-ip=185.171.202.116 Received: from smtpout-04.galae.net (smtpout-04.galae.net [185.171.202.116]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 37925606A33B; Wed, 18 Nov 2026 20:53:45 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 37925606A33B Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=bootlin.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bootlin.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bootlin.com header.i=@bootlin.com header.a=rsa-sha256 header.s=dkim header.b=umfqq3Mp Received: from smtpout-01.galae.net (smtpout-01.galae.net [212.83.139.233]) by smtpout-04.galae.net (Postfix) with ESMTPS id C3ECBC4F77A; Wed, 18 Nov 2026 20:53:48 +0000 (UTC) Received: from mail.galae.net (mail.galae.net [212.83.136.155]) by smtpout-01.galae.net (Postfix) with ESMTPS id CC7A55FE9B; Wed, 18 Nov 2026 20:53:43 +0000 (UTC) Received: from [127.0.0.1] (localhost [127.0.0.1]) by localhost (Mailerdaemon) with ESMTPSA id 81D2C11BC3099; Wed, 18 Nov 2026 21:53:37 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bootlin.com; s=dkim; t=1795035218; h=from:subject:date:message-id:to:cc:mime-version:content-type: content-transfer-encoding:in-reply-to:references; bh=XEH3qk3Abm9nkekxnFqqH/9AwO9nDPm/bhd6K4j0MIM=; b=umfqq3MpSedIY1i6Sx03c229MPV3PXiPDQJTSuEIG1pVN0n9sLcNJneC3jKp+4cGJdGNDY WVIOQfAMovDcdK4Nzx4FtFEQUWkwmH4Lx6a54UIFzm1X31bQaNOqwBJUoetowB5eSLUND9 A+h7SU/Ag9ZrmRumvzI6Tn5u1HLHUNiG6DKnS7q1TOx098hJcn0+RniOvRFltmcY4NQuCf Q8CxKTY/A1y6bYAxIb+vmEXdaU+dICZmMxmctMJ6UjS2psm4hGUDpD7z1zQb9HRmOLW7mK u1GB72SiT3EUSIoVYzbTDB9n5xHeePPRlJ1FRfWSBbci3FumsCQWQZDyhIs6LA== From: =?utf-8?q?Th=C3=A9o_Lebrun?= Date: Wed, 18 Nov 2026 21:53:25 +0100 Subject: [PATCH net-next v7 3/3] net: macb: distribute evenly Tx SRAM segments X-Mailing-List: netdev@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit Message-Id: <20261118-macb-set-channels-v7-3-2dbc00f686af@bootlin.com> References: <20261118-macb-set-channels-v7-0-2dbc00f686af@bootlin.com> In-Reply-To: <20261118-macb-set-channels-v7-0-2dbc00f686af@bootlin.com> To: Conor Dooley , Andrew Lunn , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Russell King Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Nicolai Buchwitz , Paolo Valerio , Vladimir Kondratiev , Gregory CLEMENT , =?utf-8?q?Beno=C3=AEt_Monin?= , Tawfik Bayouk , Thomas Petazzoni , =?utf-8?q?Th=C3=A9o_Lebrun?= X-Mailer: b4 0.16.0 X-Last-TLS-Session-Version: TLSv1.3 GEM has registers to configure the Tx SRAM segments distribution across active queues. The reset value is appropriate (even spread) but we need to care if/when number of active queues is modified (or if we inherited unevenly initialised hardware from bootloader). To distribute segments, we take as input the number of queues (current context num_queues) and the number of segments (found inside DCFG6). Its output is a number of segments for each queue, formatted as powers-of-two. For example, 2 for queue 0 means it has 2^2=4 segments. We define register offset GEM_TXQSEGALLOC_UPPER which is never used. It shall be used when an IP supports >8 number of queues. Note that the manual mentions explicitly that only active queues are taken into account. So when we write 0x1 in TXQSEGALLOC and a single queue is active, this means we assign (1<<1) == 2 segments to the first (active) queue and none on the others. Signed-off-by: Théo Lebrun --- drivers/net/ethernet/cadence/macb.h | 14 ++++++ drivers/net/ethernet/cadence/macb_main.c | 73 +++++++++++++++++++++++++++++++- 2 files changed, 85 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index d60b06e41b83..f8335b9fd129 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -194,6 +194,10 @@ /* Screener Type 2 match registers */ #define GEM_SCRT2 0x540 +/* Tx queue segment allocation */ +#define GEM_TXQSEGALLOC_LOWER 0x05A0 +#define GEM_TXQSEGALLOC_UPPER 0x05A4 + /* EtherType registers */ #define GEM_ETHT 0x06E0 @@ -545,6 +549,8 @@ #define GEM_PBUF_CUTTHRU_SIZE 1 #define GEM_DAW64_OFFSET 23 #define GEM_DAW64_SIZE 1 +#define GEM_SEGMENTS_BIT_SIZE_OFFSET 16 +#define GEM_SEGMENTS_BIT_SIZE_SIZE 4 /* Bitfields in DCFG8. */ #define GEM_T1SCR_OFFSET 24 @@ -657,6 +663,13 @@ #define GEM_CMPCEN_OFFSET 30 /* Compare C Enable */ #define GEM_CMPCEN_SIZE 1 +/* Bitfields in TXQSEGALLOC (Q0 at 2:0, Q1 at 6:4, etc.) */ +#define GEM_TXQSEGALLOC_MASK(q_) \ + ({ \ + typeof(q_) q__ = (q_); \ + GENMASK(4 * (q__) + 2, 4 * (q__)); \ + }) + /* Bitfields in ETHT */ #define GEM_ETHTCMP_OFFSET 0 /* EtherType compare value */ #define GEM_ETHTCMP_SIZE 16 @@ -785,6 +798,7 @@ #define MACB_CAPS_USRIO_HAS_MII BIT(26) #define MACB_CAPS_USRIO_HAS_REFCLK_SOURCE BIT(27) #define MACB_CAPS_USRIO_HAS_TSUCLK_SOURCE BIT(28) +#define MACB_CAPS_TXQSEGALLOC BIT(29) /* LSO settings */ #define MACB_LSO_UFO_ENABLE 0x01 diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 180da5d62f09..5d382f0e4aec 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3319,6 +3319,69 @@ static u32 macb_dbw(struct macb *bp) } } +/* + * Distribute evenly available segments across active queues. The computation + * is complex because (1) segments are counted in powers of two and (2) a queue + * can only use up to 128 segments. There are four types of cases: + * - Sharing all segments equally is doable. Take num_queues=4 and + * num_segments=16. Each queue will get 2^2=4 segments. + * - Sharing all segments is doable. Take num_queues=5 and num_segments=16. + * Three queues will get 2^2=4 segments and two will get 2^1=2 segments. + * - Sharing all segments is not doable because not enough queues are + * available. Take num_queues=1 and num_segments=256; queue 0 can only + * have 128 segments. + * - Sharing all segments is not doable because not enough segments are + * available. Take num_queues=4 and num_segments=2. + * + * We start by computing the power each queue will have. For num_queues=5 and + * num_segments=16, each queue will have at least 2^1 segments. That leaves us + * with remaining_segments=6. If we increase the power for a queue, we get a + * delta of 2 (2^2-2^1). The first three queues will therefore be advantaged + * and each have 2^2 segments. The remaining 2 queues will only have 2^1 + * segments. + */ +static void gem_sram_distribute_segments(struct macb *bp) +{ + unsigned int num_segments, pow, remaining_segments, i; + unsigned int num_queues = bp->ctx->num_queues; + unsigned int num_advantaged_queues = 0; + u32 val = 0; + + if (!(bp->caps & MACB_CAPS_TXQSEGALLOC)) + return; + + num_segments = 1U << GEM_BFEXT(SEGMENTS_BIT_SIZE, gem_readl(bp, DCFG6)); + + /* When growing the max # of queues, make sure to return a u64 here and + * to write into GEM_TXQSEGALLOC_UPPER. + */ + static_assert(MACB_MAX_QUEUES == 8); + + /* pow=0 for all queues. ilog2(0) is dangerous. */ + if (num_queues >= num_segments) + goto writel; + + pow = min_t(unsigned int, ilog2(num_segments / num_queues), 7); + remaining_segments = num_segments - num_queues * (1U << pow); + + /* We can only distribute remaining segments if (1) there are remaining + * segments and (2) we did not reach the max segments per queue (2^7). + */ + if (remaining_segments != 0 && pow != 7) { + unsigned int delta = (1U << (pow + 1)) - (1U << pow); + + num_advantaged_queues = remaining_segments / delta; + } + + for (i = 0; i < num_advantaged_queues; i++) + val |= field_prep(GEM_TXQSEGALLOC_MASK(i), pow + 1); + for (i = num_advantaged_queues; i < num_queues; i++) + val |= field_prep(GEM_TXQSEGALLOC_MASK(i), pow); + +writel: + gem_writel(bp, TXQSEGALLOC_LOWER, val); +} + /* Configure the receive DMA engine * - use the correct receive buffer size * - set best burst length for DMA operations @@ -3450,6 +3513,8 @@ static void macb_context_swap_end(struct macb *bp, /* Re-arm normal interrupt processing before enabling IRQs. */ bp->irq_quiesced = false; + gem_sram_distribute_segments(bp); + macb_configure_dma(bp); if (bp->link_up) { @@ -3517,6 +3582,8 @@ static void macb_init_hw(struct macb *bp) if (bp->caps & MACB_CAPS_JUMBO) bp->rx_frm_len_mask = MACB_RX_JFRMLEN_MASK; + gem_sram_distribute_segments(bp); + macb_configure_dma(bp); /* Enable RX partial store and forward and set watermark */ @@ -6226,6 +6293,7 @@ static const struct macb_config zynqmp_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH | + MACB_CAPS_TXQSEGALLOC | MACB_CAPS_USRIO_HAS_MII, .dma_burst_length = 16, .init = init_reset_optional, @@ -6293,7 +6361,7 @@ static const struct macb_config versal_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH | MACB_CAPS_NEED_TSUCLK | MACB_CAPS_QUEUE_DISABLE | - MACB_CAPS_QBV | + MACB_CAPS_QBV | MACB_CAPS_TXQSEGALLOC | MACB_CAPS_USRIO_HAS_MII, .dma_burst_length = 16, .init = init_reset_optional, @@ -6304,7 +6372,8 @@ static const struct macb_config versal_config = { static const struct macb_config eyeq5_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_QUEUE_DISABLE | - MACB_CAPS_NO_LSO | MACB_CAPS_EEE | MACB_CAPS_QBV, + MACB_CAPS_NO_LSO | MACB_CAPS_EEE | MACB_CAPS_QBV | + MACB_CAPS_TXQSEGALLOC, .dma_burst_length = 16, .init = eyeq5_init, .jumbo_max_len = 10240, -- 2.56.1