45824fc0da
- Initial support for running on a system with an Ultravisor, which is software that runs below the hypervisor and protects guests against some attacks by the hypervisor. - Support for building the kernel to run as a "Secure Virtual Machine", ie. as a guest capable of running on a system with an Ultravisor. - Some changes to our DMA code on bare metal, to allow devices with medium sized DMA masks (> 32 && < 59 bits) to use more than 2GB of DMA space. - Support for firmware assisted crash dumps on bare metal (powernv). - Two series fixing bugs in and refactoring our PCI EEH code. - A large series refactoring our exception entry code to use gas macros, both to make it more readable and also enable some future optimisations. As well as many cleanups and other minor features & fixups. Thanks to: Adam Zerella, Alexey Kardashevskiy, Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Anshuman Khandual, Balbir Singh, Benjamin Herrenschmidt, Cédric Le Goater, Christophe JAILLET, Christophe Leroy, Christopher M. Riedl, Christoph Hellwig, Claudio Carvalho, Daniel Axtens, David Gibson, David Hildenbrand, Desnes A. Nunes do Rosario, Ganesh Goudar, Gautham R. Shenoy, Greg Kurz, Guerney Hunt, Gustavo Romero, Halil Pasic, Hari Bathini, Joakim Tjernlund, Jonathan Neuschafer, Jordan Niethe, Leonardo Bras, Lianbo Jiang, Madhavan Srinivasan, Mahesh Salgaonkar, Mahesh Salgaonkar, Masahiro Yamada, Maxiwell S. Garcia, Michael Anderson, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Qian Cai, Ram Pai, Ravi Bangoria, Reza Arbab, Ryan Grimm, Sam Bobroff, Santosh Sivaraj, Segher Boessenkool, Sukadev Bhattiprolu, Thiago Bauermann, Thiago Jung Bauermann, Thomas Gleixner, Tom Lendacky, Vasant Hegde. -----BEGIN PGP SIGNATURE----- iQJHBAABCAAxFiEEJFGtCPCthwEv2Y/bUevqPMjhpYAFAl2EtEcTHG1wZUBlbGxl cm1hbi5pZC5hdQAKCRBR6+o8yOGlgPfsD/9uXyBXn3anI/H08+mk74k5gCsmMQpn D442CD/ByogZcccp23yBTlhawtCE03hcHnCLygn0Xgd8a4YvHts/RGHUe3fPHqlG bEyZ7jsLVz5ebNZQP7r4eGs2pSzCajwJy2N9HJ/C1ojf15rrfRxoVJtnyhE2wXpm DL+6o2K+nUCB3gTQ1Inr3DnWzoGOOUfNTOea2u+J+yfHwGRqOBYpevwqiwy5eelK aRjUJCqMTvrzra49MeFwjo0Nt3/Y8UNcwA+JlGdeR8bRuWhFrYmyBRiZEKPaujNO 5EAfghBBlB0KQCqvF/tRM/c0OftHqK59AMobP9T7u9oOaBXeF/FpZX/iXjzNDPsN j9Oo2tKLTu/YVEXqBFuREGP+znANr1Wo4CFyOG8SbvYz0HFjR6XbtRJsS+0e8GWl kqX5/ZhYz3lBnKSNe9jgWOrh/J0KCSFigBTEWJT3xsn4YE8x8kK2l9KPqAIldWEP sKb2UjGS7v0NKq+NvShH88Q9AeQUEIjTcg/9aDDQDe6FaRQ7KiF8bUxSdwSPi+Fn j0lnF6i+1ATWZKuCr85veVi7C5qoe/+MqalnmP7MxULyzgXLLxUgN0SzEYO6QofK LQK/VaH2XVr5+M5YAb7K4/NX5gbM3s1bKrCiUy4EyHNvgG7gricYdbz6HgAjKpR7 oP0rHfgmVYvF1g== =WlW+ -----END PGP SIGNATURE----- Merge tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc updates from Michael Ellerman: "This is a bit late, partly due to me travelling, and partly due to a power outage knocking out some of my test systems *while* I was travelling. - Initial support for running on a system with an Ultravisor, which is software that runs below the hypervisor and protects guests against some attacks by the hypervisor. - Support for building the kernel to run as a "Secure Virtual Machine", ie. as a guest capable of running on a system with an Ultravisor. - Some changes to our DMA code on bare metal, to allow devices with medium sized DMA masks (> 32 && < 59 bits) to use more than 2GB of DMA space. - Support for firmware assisted crash dumps on bare metal (powernv). - Two series fixing bugs in and refactoring our PCI EEH code. - A large series refactoring our exception entry code to use gas macros, both to make it more readable and also enable some future optimisations. As well as many cleanups and other minor features & fixups. Thanks to: Adam Zerella, Alexey Kardashevskiy, Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Anshuman Khandual, Balbir Singh, Benjamin Herrenschmidt, Cédric Le Goater, Christophe JAILLET, Christophe Leroy, Christopher M. Riedl, Christoph Hellwig, Claudio Carvalho, Daniel Axtens, David Gibson, David Hildenbrand, Desnes A. Nunes do Rosario, Ganesh Goudar, Gautham R. Shenoy, Greg Kurz, Guerney Hunt, Gustavo Romero, Halil Pasic, Hari Bathini, Joakim Tjernlund, Jonathan Neuschafer, Jordan Niethe, Leonardo Bras, Lianbo Jiang, Madhavan Srinivasan, Mahesh Salgaonkar, Mahesh Salgaonkar, Masahiro Yamada, Maxiwell S. Garcia, Michael Anderson, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Qian Cai, Ram Pai, Ravi Bangoria, Reza Arbab, Ryan Grimm, Sam Bobroff, Santosh Sivaraj, Segher Boessenkool, Sukadev Bhattiprolu, Thiago Bauermann, Thiago Jung Bauermann, Thomas Gleixner, Tom Lendacky, Vasant Hegde" * tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (264 commits) powerpc/mm/mce: Keep irqs disabled during lockless page table walk powerpc: Use ftrace_graph_ret_addr() when unwinding powerpc/ftrace: Enable HAVE_FUNCTION_GRAPH_RET_ADDR_PTR ftrace: Look up the address of return_to_handler() using helpers powerpc: dump kernel log before carrying out fadump or kdump docs: powerpc: Add missing documentation reference powerpc/xmon: Fix output of XIVE IPI powerpc/xmon: Improve output of XIVE interrupts powerpc/mm/radix: remove useless kernel messages powerpc/fadump: support holes in kernel boot memory area powerpc/fadump: remove RMA_START and RMA_END macros powerpc/fadump: update documentation about option to release opalcore powerpc/fadump: consider f/w load area powerpc/opalcore: provide an option to invalidate /sys/firmware/opal/core file powerpc/opalcore: export /sys/firmware/opal/core for analysing opal crashes powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP powerpc/fadump: add support to preserve crash data on FADUMP disabled kernel powerpc/fadump: improve how crashed kernel's memory is reserved powerpc/fadump: consider reserved ranges while releasing memory powerpc/fadump: make crash memory ranges array allocation generic ...
213 lines
6.4 KiB
C
213 lines
6.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
|
|
*
|
|
* Provide default implementations of the DMA mapping callbacks for
|
|
* busses using the iommu infrastructure
|
|
*/
|
|
|
|
#include <linux/dma-direct.h>
|
|
#include <linux/pci.h>
|
|
#include <asm/iommu.h>
|
|
|
|
/*
|
|
* Generic iommu implementation
|
|
*/
|
|
|
|
/*
|
|
* The coherent mask may be smaller than the real mask, check if we can
|
|
* really use a direct window.
|
|
*/
|
|
static inline bool dma_iommu_alloc_bypass(struct device *dev)
|
|
{
|
|
return dev->archdata.iommu_bypass && !iommu_fixed_is_weak &&
|
|
dma_direct_supported(dev, dev->coherent_dma_mask);
|
|
}
|
|
|
|
static inline bool dma_iommu_map_bypass(struct device *dev,
|
|
unsigned long attrs)
|
|
{
|
|
return dev->archdata.iommu_bypass &&
|
|
(!iommu_fixed_is_weak || (attrs & DMA_ATTR_WEAK_ORDERING));
|
|
}
|
|
|
|
/* Allocates a contiguous real buffer and creates mappings over it.
|
|
* Returns the virtual address of the buffer and sets dma_handle
|
|
* to the dma address (mapping) of the first page.
|
|
*/
|
|
static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
|
|
dma_addr_t *dma_handle, gfp_t flag,
|
|
unsigned long attrs)
|
|
{
|
|
if (dma_iommu_alloc_bypass(dev))
|
|
return dma_direct_alloc(dev, size, dma_handle, flag, attrs);
|
|
return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
|
|
dma_handle, dev->coherent_dma_mask, flag,
|
|
dev_to_node(dev));
|
|
}
|
|
|
|
static void dma_iommu_free_coherent(struct device *dev, size_t size,
|
|
void *vaddr, dma_addr_t dma_handle,
|
|
unsigned long attrs)
|
|
{
|
|
if (dma_iommu_alloc_bypass(dev))
|
|
dma_direct_free(dev, size, vaddr, dma_handle, attrs);
|
|
else
|
|
iommu_free_coherent(get_iommu_table_base(dev), size, vaddr,
|
|
dma_handle);
|
|
}
|
|
|
|
/* Creates TCEs for a user provided buffer. The user buffer must be
|
|
* contiguous real kernel storage (not vmalloc). The address passed here
|
|
* comprises a page address and offset into that page. The dma_addr_t
|
|
* returned will point to the same byte within the page as was passed in.
|
|
*/
|
|
static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
|
|
unsigned long offset, size_t size,
|
|
enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
if (dma_iommu_map_bypass(dev, attrs))
|
|
return dma_direct_map_page(dev, page, offset, size, direction,
|
|
attrs);
|
|
return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
|
|
size, dma_get_mask(dev), direction, attrs);
|
|
}
|
|
|
|
|
|
static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
|
|
size_t size, enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
if (!dma_iommu_map_bypass(dev, attrs))
|
|
iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size,
|
|
direction, attrs);
|
|
else
|
|
dma_direct_unmap_page(dev, dma_handle, size, direction, attrs);
|
|
}
|
|
|
|
|
|
static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
|
|
int nelems, enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
if (dma_iommu_map_bypass(dev, attrs))
|
|
return dma_direct_map_sg(dev, sglist, nelems, direction, attrs);
|
|
return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
|
|
dma_get_mask(dev), direction, attrs);
|
|
}
|
|
|
|
static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
|
|
int nelems, enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
if (!dma_iommu_map_bypass(dev, attrs))
|
|
ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
|
|
direction, attrs);
|
|
else
|
|
dma_direct_unmap_sg(dev, sglist, nelems, direction, attrs);
|
|
}
|
|
|
|
static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
|
|
{
|
|
struct pci_dev *pdev = to_pci_dev(dev);
|
|
struct pci_controller *phb = pci_bus_to_host(pdev->bus);
|
|
|
|
return phb->controller_ops.iommu_bypass_supported &&
|
|
phb->controller_ops.iommu_bypass_supported(pdev, mask);
|
|
}
|
|
|
|
/* We support DMA to/from any memory page via the iommu */
|
|
int dma_iommu_dma_supported(struct device *dev, u64 mask)
|
|
{
|
|
struct iommu_table *tbl = get_iommu_table_base(dev);
|
|
|
|
if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
|
|
dev->archdata.iommu_bypass = true;
|
|
dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
|
|
return 1;
|
|
}
|
|
|
|
if (!tbl) {
|
|
dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask);
|
|
return 0;
|
|
}
|
|
|
|
if (tbl->it_offset > (mask >> tbl->it_page_shift)) {
|
|
dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
|
|
dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
|
|
mask, tbl->it_offset << tbl->it_page_shift);
|
|
return 0;
|
|
}
|
|
|
|
dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
|
|
dev->archdata.iommu_bypass = false;
|
|
return 1;
|
|
}
|
|
|
|
u64 dma_iommu_get_required_mask(struct device *dev)
|
|
{
|
|
struct iommu_table *tbl = get_iommu_table_base(dev);
|
|
u64 mask;
|
|
|
|
if (!tbl)
|
|
return 0;
|
|
|
|
if (dev_is_pci(dev)) {
|
|
u64 bypass_mask = dma_direct_get_required_mask(dev);
|
|
|
|
if (dma_iommu_bypass_supported(dev, bypass_mask))
|
|
return bypass_mask;
|
|
}
|
|
|
|
mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
|
|
mask += mask - 1;
|
|
|
|
return mask;
|
|
}
|
|
|
|
static void dma_iommu_sync_for_cpu(struct device *dev, dma_addr_t addr,
|
|
size_t size, enum dma_data_direction dir)
|
|
{
|
|
if (dma_iommu_alloc_bypass(dev))
|
|
dma_direct_sync_single_for_cpu(dev, addr, size, dir);
|
|
}
|
|
|
|
static void dma_iommu_sync_for_device(struct device *dev, dma_addr_t addr,
|
|
size_t sz, enum dma_data_direction dir)
|
|
{
|
|
if (dma_iommu_alloc_bypass(dev))
|
|
dma_direct_sync_single_for_device(dev, addr, sz, dir);
|
|
}
|
|
|
|
extern void dma_iommu_sync_sg_for_cpu(struct device *dev,
|
|
struct scatterlist *sgl, int nents, enum dma_data_direction dir)
|
|
{
|
|
if (dma_iommu_alloc_bypass(dev))
|
|
dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir);
|
|
}
|
|
|
|
extern void dma_iommu_sync_sg_for_device(struct device *dev,
|
|
struct scatterlist *sgl, int nents, enum dma_data_direction dir)
|
|
{
|
|
if (dma_iommu_alloc_bypass(dev))
|
|
dma_direct_sync_sg_for_device(dev, sgl, nents, dir);
|
|
}
|
|
|
|
const struct dma_map_ops dma_iommu_ops = {
|
|
.alloc = dma_iommu_alloc_coherent,
|
|
.free = dma_iommu_free_coherent,
|
|
.map_sg = dma_iommu_map_sg,
|
|
.unmap_sg = dma_iommu_unmap_sg,
|
|
.dma_supported = dma_iommu_dma_supported,
|
|
.map_page = dma_iommu_map_page,
|
|
.unmap_page = dma_iommu_unmap_page,
|
|
.get_required_mask = dma_iommu_get_required_mask,
|
|
.sync_single_for_cpu = dma_iommu_sync_for_cpu,
|
|
.sync_single_for_device = dma_iommu_sync_for_device,
|
|
.sync_sg_for_cpu = dma_iommu_sync_sg_for_cpu,
|
|
.sync_sg_for_device = dma_iommu_sync_sg_for_device,
|
|
.mmap = dma_common_mmap,
|
|
.get_sgtable = dma_common_get_sgtable,
|
|
};
|