mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-08-05 16:54:27 +00:00

Patch series "mm: ioremap: Convert architectures to take GENERIC_IOREMAP way", v8. Motivation and implementation: ============================== Currently, many architecutres have't taken the standard GENERIC_IOREMAP way to implement ioremap_prot(), iounmap(), and ioremap_xx(), but make these functions specifically under each arch's folder. Those cause many duplicated code of ioremap() and iounmap(). In this patchset, firstly introduce generic_ioremap_prot() and generic_iounmap() to extract the generic code for GENERIC_IOREMAP. By taking GENERIC_IOREMAP method, the generic generic_ioremap_prot(), generic_iounmap(), and their generic wrapper ioremap_prot(), ioremap() and iounmap() are all visible and available to arch. Arch needs to provide wrapper functions to override the generic version if there's arch specific handling in its corresponding ioremap_prot(), ioremap() or iounmap(). With these changes, duplicated ioremap/iounmap() code uder ARCH-es are removed, and the equivalent functioality is kept as before. Background info: ================ 1) The converting more architectures to take GENERIC_IOREMAP way is suggested by Christoph in below discussion: https://lore.kernel.org/all/Yp7h0Jv6vpgt6xdZ@infradead.org/T/#u 2) In the previous v1 to v3, it's basically further action after arm64 has converted to GENERIC_IOREMAP way in below patchset. It's done by adding hook ioremap_allowed() and iounmap_allowed() in ARCH to add ARCH specific handling the middle of ioremap_prot() and iounmap(). [PATCH v5 0/6] arm64: Cleanup ioremap() and support ioremap_prot() https://lore.kernel.org/all/20220607125027.44946-1-wangkefeng.wang@huawei.com/T/#u Later, during v3 reviewing, Christophe Leroy suggested to introduce generic_ioremap_prot() and generic_iounmap() to generic codes, and ARCH can provide wrapper function ioremap_prot(), ioremap() or iounmap() if needed. Christophe made a RFC patchset as below to specially demonstrate his idea. This is what v4 and now v5 is doing. [RFC PATCH 0/8] mm: ioremap: Convert architectures to take GENERIC_IOREMAP way https://lore.kernel.org/all/cover.1665568707.git.christophe.leroy@csgroup.eu/T/#u Testing: ======== In v8, I only applied this patchset onto the latest linus's tree to build and run on arm64 and s390. This patch (of 19): Let's use '#define ioremap_xx' and "#ifdef ioremap_xx" instead. To remove defined ARCH_HAS_IOREMAP_xx macros in <asm/io.h> of each ARCH, the ARCH's own ioremap_wc|wt|np definition need be above "#include <asm-generic/iomap.h>. Otherwise the redefinition error would be seen during compiling. So the relevant adjustments are made to avoid compiling error: loongarch: - doesn't include <asm-generic/iomap.h>, defining ARCH_HAS_IOREMAP_WC is redundant, so simply remove it. m68k: - selected GENERIC_IOMAP, <asm-generic/iomap.h> has been added in <asm-generic/io.h>, and <asm/kmap.h> is included above <asm-generic/iomap.h>, so simply remove ARCH_HAS_IOREMAP_WT defining. mips: - move "#include <asm-generic/iomap.h>" below ioremap_wc definition in <asm/io.h> powerpc: - remove "#include <asm-generic/iomap.h>" in <asm/io.h> because it's duplicated with the one in <asm-generic/io.h>, let's rely on the latter. x86: - selected GENERIC_IOMAP, remove #include <asm-generic/iomap.h> in the middle of <asm/io.h>. Let's rely on <asm-generic/io.h>. Link: https://lkml.kernel.org/r/20230706154520.11257-2-bhe@redhat.com Signed-off-by: Baoquan He <bhe@redhat.com> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: David Laight <David.Laight@ACULAB.COM> Cc: Helge Deller <deller@gmx.de> Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Niklas Schnelle <schnelle@linux.ibm.com> Cc: Stafford Horne <shorne@gmail.com> Cc: Brian Cain <bcain@quicinc.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Rich Felker <dalias@libc.org> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@kernel.org> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
310 lines
9.9 KiB
C
310 lines
9.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/****************************************************************************
|
|
* Driver for Solarflare network controllers and boards
|
|
* Copyright 2005-2006 Fen Systems Ltd.
|
|
* Copyright 2006-2013 Solarflare Communications Inc.
|
|
*/
|
|
|
|
#ifndef EFX_IO_H
|
|
#define EFX_IO_H
|
|
|
|
#include <linux/io.h>
|
|
#include <linux/spinlock.h>
|
|
|
|
/**************************************************************************
|
|
*
|
|
* NIC register I/O
|
|
*
|
|
**************************************************************************
|
|
*
|
|
* Notes on locking strategy for the Falcon architecture:
|
|
*
|
|
* Many CSRs are very wide and cannot be read or written atomically.
|
|
* Writes from the host are buffered by the Bus Interface Unit (BIU)
|
|
* up to 128 bits. Whenever the host writes part of such a register,
|
|
* the BIU collects the written value and does not write to the
|
|
* underlying register until all 4 dwords have been written. A
|
|
* similar buffering scheme applies to host access to the NIC's 64-bit
|
|
* SRAM.
|
|
*
|
|
* Writes to different CSRs and 64-bit SRAM words must be serialised,
|
|
* since interleaved access can result in lost writes. We use
|
|
* efx_nic::biu_lock for this.
|
|
*
|
|
* We also serialise reads from 128-bit CSRs and SRAM with the same
|
|
* spinlock. This may not be necessary, but it doesn't really matter
|
|
* as there are no such reads on the fast path.
|
|
*
|
|
* The DMA descriptor pointers (RX_DESC_UPD and TX_DESC_UPD) are
|
|
* 128-bit but are special-cased in the BIU to avoid the need for
|
|
* locking in the host:
|
|
*
|
|
* - They are write-only.
|
|
* - The semantics of writing to these registers are such that
|
|
* replacing the low 96 bits with zero does not affect functionality.
|
|
* - If the host writes to the last dword address of such a register
|
|
* (i.e. the high 32 bits) the underlying register will always be
|
|
* written. If the collector and the current write together do not
|
|
* provide values for all 128 bits of the register, the low 96 bits
|
|
* will be written as zero.
|
|
* - If the host writes to the address of any other part of such a
|
|
* register while the collector already holds values for some other
|
|
* register, the write is discarded and the collector maintains its
|
|
* current state.
|
|
*
|
|
* The EF10 architecture exposes very few registers to the host and
|
|
* most of them are only 32 bits wide. The only exceptions are the MC
|
|
* doorbell register pair, which has its own latching, and
|
|
* TX_DESC_UPD, which works in a similar way to the Falcon
|
|
* architecture.
|
|
*/
|
|
|
|
#if BITS_PER_LONG == 64
|
|
#define EFX_USE_QWORD_IO 1
|
|
#endif
|
|
|
|
/* Hardware issue requires that only 64-bit naturally aligned writes
|
|
* are seen by hardware. Its not strictly necessary to restrict to
|
|
* x86_64 arch, but done for safety since unusual write combining behaviour
|
|
* can break PIO.
|
|
*/
|
|
#ifdef CONFIG_X86_64
|
|
/* PIO is a win only if write-combining is possible */
|
|
#ifdef ioremap_wc
|
|
#define EFX_USE_PIO 1
|
|
#endif
|
|
#endif
|
|
|
|
static inline u32 efx_reg(struct efx_nic *efx, unsigned int reg)
|
|
{
|
|
return efx->reg_base + reg;
|
|
}
|
|
|
|
#ifdef EFX_USE_QWORD_IO
|
|
static inline void _efx_writeq(struct efx_nic *efx, __le64 value,
|
|
unsigned int reg)
|
|
{
|
|
__raw_writeq((__force u64)value, efx->membase + reg);
|
|
}
|
|
static inline __le64 _efx_readq(struct efx_nic *efx, unsigned int reg)
|
|
{
|
|
return (__force __le64)__raw_readq(efx->membase + reg);
|
|
}
|
|
#endif
|
|
|
|
static inline void _efx_writed(struct efx_nic *efx, __le32 value,
|
|
unsigned int reg)
|
|
{
|
|
__raw_writel((__force u32)value, efx->membase + reg);
|
|
}
|
|
static inline __le32 _efx_readd(struct efx_nic *efx, unsigned int reg)
|
|
{
|
|
return (__force __le32)__raw_readl(efx->membase + reg);
|
|
}
|
|
|
|
/* Write a normal 128-bit CSR, locking as appropriate. */
|
|
static inline void efx_writeo(struct efx_nic *efx, const efx_oword_t *value,
|
|
unsigned int reg)
|
|
{
|
|
unsigned long flags __attribute__ ((unused));
|
|
|
|
netif_vdbg(efx, hw, efx->net_dev,
|
|
"writing register %x with " EFX_OWORD_FMT "\n", reg,
|
|
EFX_OWORD_VAL(*value));
|
|
|
|
spin_lock_irqsave(&efx->biu_lock, flags);
|
|
#ifdef EFX_USE_QWORD_IO
|
|
_efx_writeq(efx, value->u64[0], reg + 0);
|
|
_efx_writeq(efx, value->u64[1], reg + 8);
|
|
#else
|
|
_efx_writed(efx, value->u32[0], reg + 0);
|
|
_efx_writed(efx, value->u32[1], reg + 4);
|
|
_efx_writed(efx, value->u32[2], reg + 8);
|
|
_efx_writed(efx, value->u32[3], reg + 12);
|
|
#endif
|
|
spin_unlock_irqrestore(&efx->biu_lock, flags);
|
|
}
|
|
|
|
/* Write 64-bit SRAM through the supplied mapping, locking as appropriate. */
|
|
static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase,
|
|
const efx_qword_t *value, unsigned int index)
|
|
{
|
|
unsigned int addr = index * sizeof(*value);
|
|
unsigned long flags __attribute__ ((unused));
|
|
|
|
netif_vdbg(efx, hw, efx->net_dev,
|
|
"writing SRAM address %x with " EFX_QWORD_FMT "\n",
|
|
addr, EFX_QWORD_VAL(*value));
|
|
|
|
spin_lock_irqsave(&efx->biu_lock, flags);
|
|
#ifdef EFX_USE_QWORD_IO
|
|
__raw_writeq((__force u64)value->u64[0], membase + addr);
|
|
#else
|
|
__raw_writel((__force u32)value->u32[0], membase + addr);
|
|
__raw_writel((__force u32)value->u32[1], membase + addr + 4);
|
|
#endif
|
|
spin_unlock_irqrestore(&efx->biu_lock, flags);
|
|
}
|
|
|
|
/* Write a 32-bit CSR or the last dword of a special 128-bit CSR */
|
|
static inline void efx_writed(struct efx_nic *efx, const efx_dword_t *value,
|
|
unsigned int reg)
|
|
{
|
|
netif_vdbg(efx, hw, efx->net_dev,
|
|
"writing register %x with "EFX_DWORD_FMT"\n",
|
|
reg, EFX_DWORD_VAL(*value));
|
|
|
|
/* No lock required */
|
|
_efx_writed(efx, value->u32[0], reg);
|
|
}
|
|
|
|
/* Read a 128-bit CSR, locking as appropriate. */
|
|
static inline void efx_reado(struct efx_nic *efx, efx_oword_t *value,
|
|
unsigned int reg)
|
|
{
|
|
unsigned long flags __attribute__ ((unused));
|
|
|
|
spin_lock_irqsave(&efx->biu_lock, flags);
|
|
value->u32[0] = _efx_readd(efx, reg + 0);
|
|
value->u32[1] = _efx_readd(efx, reg + 4);
|
|
value->u32[2] = _efx_readd(efx, reg + 8);
|
|
value->u32[3] = _efx_readd(efx, reg + 12);
|
|
spin_unlock_irqrestore(&efx->biu_lock, flags);
|
|
|
|
netif_vdbg(efx, hw, efx->net_dev,
|
|
"read from register %x, got " EFX_OWORD_FMT "\n", reg,
|
|
EFX_OWORD_VAL(*value));
|
|
}
|
|
|
|
/* Read 64-bit SRAM through the supplied mapping, locking as appropriate. */
|
|
static inline void efx_sram_readq(struct efx_nic *efx, void __iomem *membase,
|
|
efx_qword_t *value, unsigned int index)
|
|
{
|
|
unsigned int addr = index * sizeof(*value);
|
|
unsigned long flags __attribute__ ((unused));
|
|
|
|
spin_lock_irqsave(&efx->biu_lock, flags);
|
|
#ifdef EFX_USE_QWORD_IO
|
|
value->u64[0] = (__force __le64)__raw_readq(membase + addr);
|
|
#else
|
|
value->u32[0] = (__force __le32)__raw_readl(membase + addr);
|
|
value->u32[1] = (__force __le32)__raw_readl(membase + addr + 4);
|
|
#endif
|
|
spin_unlock_irqrestore(&efx->biu_lock, flags);
|
|
|
|
netif_vdbg(efx, hw, efx->net_dev,
|
|
"read from SRAM address %x, got "EFX_QWORD_FMT"\n",
|
|
addr, EFX_QWORD_VAL(*value));
|
|
}
|
|
|
|
/* Read a 32-bit CSR or SRAM */
|
|
static inline void efx_readd(struct efx_nic *efx, efx_dword_t *value,
|
|
unsigned int reg)
|
|
{
|
|
value->u32[0] = _efx_readd(efx, reg);
|
|
netif_vdbg(efx, hw, efx->net_dev,
|
|
"read from register %x, got "EFX_DWORD_FMT"\n",
|
|
reg, EFX_DWORD_VAL(*value));
|
|
}
|
|
|
|
/* Write a 128-bit CSR forming part of a table */
|
|
static inline void
|
|
efx_writeo_table(struct efx_nic *efx, const efx_oword_t *value,
|
|
unsigned int reg, unsigned int index)
|
|
{
|
|
efx_writeo(efx, value, reg + index * sizeof(efx_oword_t));
|
|
}
|
|
|
|
/* Read a 128-bit CSR forming part of a table */
|
|
static inline void efx_reado_table(struct efx_nic *efx, efx_oword_t *value,
|
|
unsigned int reg, unsigned int index)
|
|
{
|
|
efx_reado(efx, value, reg + index * sizeof(efx_oword_t));
|
|
}
|
|
|
|
/* default VI stride (step between per-VI registers) is 8K on EF10 and
|
|
* 64K on EF100
|
|
*/
|
|
#define EFX_DEFAULT_VI_STRIDE 0x2000
|
|
#define EF100_DEFAULT_VI_STRIDE 0x10000
|
|
|
|
/* Calculate offset to page-mapped register */
|
|
static inline unsigned int efx_paged_reg(struct efx_nic *efx, unsigned int page,
|
|
unsigned int reg)
|
|
{
|
|
return page * efx->vi_stride + reg;
|
|
}
|
|
|
|
/* Write the whole of RX_DESC_UPD or TX_DESC_UPD */
|
|
static inline void _efx_writeo_page(struct efx_nic *efx, efx_oword_t *value,
|
|
unsigned int reg, unsigned int page)
|
|
{
|
|
reg = efx_paged_reg(efx, page, reg);
|
|
|
|
netif_vdbg(efx, hw, efx->net_dev,
|
|
"writing register %x with " EFX_OWORD_FMT "\n", reg,
|
|
EFX_OWORD_VAL(*value));
|
|
|
|
#ifdef EFX_USE_QWORD_IO
|
|
_efx_writeq(efx, value->u64[0], reg + 0);
|
|
_efx_writeq(efx, value->u64[1], reg + 8);
|
|
#else
|
|
_efx_writed(efx, value->u32[0], reg + 0);
|
|
_efx_writed(efx, value->u32[1], reg + 4);
|
|
_efx_writed(efx, value->u32[2], reg + 8);
|
|
_efx_writed(efx, value->u32[3], reg + 12);
|
|
#endif
|
|
}
|
|
#define efx_writeo_page(efx, value, reg, page) \
|
|
_efx_writeo_page(efx, value, \
|
|
reg + \
|
|
BUILD_BUG_ON_ZERO((reg) != 0x830 && (reg) != 0xa10), \
|
|
page)
|
|
|
|
/* Write a page-mapped 32-bit CSR (EVQ_RPTR, EVQ_TMR (EF10), or the
|
|
* high bits of RX_DESC_UPD or TX_DESC_UPD)
|
|
*/
|
|
static inline void
|
|
_efx_writed_page(struct efx_nic *efx, const efx_dword_t *value,
|
|
unsigned int reg, unsigned int page)
|
|
{
|
|
efx_writed(efx, value, efx_paged_reg(efx, page, reg));
|
|
}
|
|
#define efx_writed_page(efx, value, reg, page) \
|
|
_efx_writed_page(efx, value, \
|
|
reg + \
|
|
BUILD_BUG_ON_ZERO((reg) != 0x180 && \
|
|
(reg) != 0x200 && \
|
|
(reg) != 0x400 && \
|
|
(reg) != 0x420 && \
|
|
(reg) != 0x830 && \
|
|
(reg) != 0x83c && \
|
|
(reg) != 0xa18 && \
|
|
(reg) != 0xa1c), \
|
|
page)
|
|
|
|
/* Write TIMER_COMMAND. This is a page-mapped 32-bit CSR, but a bug
|
|
* in the BIU means that writes to TIMER_COMMAND[0] invalidate the
|
|
* collector register.
|
|
*/
|
|
static inline void _efx_writed_page_locked(struct efx_nic *efx,
|
|
const efx_dword_t *value,
|
|
unsigned int reg,
|
|
unsigned int page)
|
|
{
|
|
unsigned long flags __attribute__ ((unused));
|
|
|
|
if (page == 0) {
|
|
spin_lock_irqsave(&efx->biu_lock, flags);
|
|
efx_writed(efx, value, efx_paged_reg(efx, page, reg));
|
|
spin_unlock_irqrestore(&efx->biu_lock, flags);
|
|
} else {
|
|
efx_writed(efx, value, efx_paged_reg(efx, page, reg));
|
|
}
|
|
}
|
|
#define efx_writed_page_locked(efx, value, reg, page) \
|
|
_efx_writed_page_locked(efx, value, \
|
|
reg + BUILD_BUG_ON_ZERO((reg) != 0x420), \
|
|
page)
|
|
|
|
#endif /* EFX_IO_H */
|